← OSS.Radar home

Powered by aegismemory.com · Aegis Memory repository

Multimodal Media AI repositories

OSS Radar projects in the multimodal media category.

harry0703/MoneyPrinterTurbo

利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

Category
multimodal media
Stars
102,101
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
8/100 · high confidence

Why: +1,309 stars in 7 days; 42 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity; open issue backlog is stable or shrinking

Strongest signals: push recency, commit activity, contributor breadth. Risks: no pull-request review responses in 30 days. Missing inputs: None.

Capped lower bounds: response activity.

ai-video-generator content-creation ffmpeg instagram-reels llm python

unslothai/unsloth

Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, GLM and other models.

Category
multimodal media
Stars
69,693
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +406 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

agent deepseek fine-tuning gemma gemma3 gpt-oss

mudler/LocalAI

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Category
multimodal media
Stars
48,314
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +248 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors, response activity.

agents ai api audio-generation decentralized distributed

2noise/ChatTTS

A generative speech model for daily dialogue.

Category
multimodal media
Stars
39,748
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
watch
Maintenance risk
28/100 · high confidence

Why: +31 stars in 7 days; 57 lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: contributor breadth, issue load, documentation. Risks: no push in 119 days, no pull-request review responses in 30 days. Missing inputs: None.

agent chat chatgpt chattts chinese chinese-language

Zackriya-Solutions/meetily

Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetily (

Category
multimodal media
Stars
28,443
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
watch
Maintenance risk
18/100 · high confidence

Why: +784 stars in 7 days; 11 lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: contributor breadth, issue load, documentation. Risks: recent commit cadence is 0/20.0 of its monthly baseline. Missing inputs: None.

Capped lower bounds: response activity.

ai ai-meeting-assistant llm local-ai mac meeting-minutes

zai-org/CogVideo

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Category
multimodal media
Stars
12,941
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +17 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 276 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

cogvideox image-to-video llm sora text-to-video video-generation

op7418/guizang-ppt-skill

AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.

Category
multimodal media
Stars
23,464
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +592 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent claude-code codex html-deck image-generation ppt

leon-ai/leon

🧠 Leon is your open-source personal assistant.

Category
multimodal media
Stars
17,419
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +23 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent ai-assistant artificial-intelligence assistant automation

ArcReel/ArcReel

AI Agent 驱动的开源可自部署视频工作台：将小说与剧本转为角色、场景、道具资产、分镜、视频和剪映草稿，支持跨镜头一致性、多供应商与费用追踪 | Self-hosted AI video workspace for stories, storyboards and short-form video production

Category
multimodal media
Stars
3,906
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +111 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-workflow ai-agent ai-animation ai-video-generator capcut claude-agent-sdk

helloianneo/ian-xiaohei-illustrations

中文小黑怪诞正文配图生成 Skill | 16:9 白底手绘 | 少量红橙蓝批注 | Codex Skill

Category
multimodal media
Stars
9,158
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +325 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent chinese codex-skill handdrawn illustration image-generation

op7418/guizang-social-card-skill

🪧 Claude Code / Codex skill — generate Xiaohongshu carousels & WeChat 21:9+1:1 cover pairs. Editorial × Swiss visual systems, 28 layouts, 10 themes, single-file HTML → PNG. 小红书图文 + 公众号封面对

Category
multimodal media
Stars
6,047
Readiness
needs review (59/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +327 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skill ai-agent anthropic claude-code claude-skill codex

nexu-io/html-video

Programmatic video for coding agents — HTML to video on your laptop. Turn HTML, CSS & data into real MP4s with pluggable render engines, 21 templates, AI soundtrack. Apache-2.0, no per-render fees. An

Category
multimodal media
Stars
4,278
Readiness
needs review (64/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +48 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent apache-2 coding-agent css ffmpeg html

helloianneo/ian-handdrawn-ppt

中文手绘技术 PPT 整页图像生成 Skill | 21:9 封面 + 16:9 正文配图 | PNG 输出

Category
multimodal media
Stars
1,310
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
17/100 · low confidence

Why: +15 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 104 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent chinese codex-skill handdrawn image-generation ppt

MiniMax-AI/MiniMax-MCP

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

Category
multimodal media
Stars
1,556
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +9 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-generation image-to-video mcp mcp-server mcp-tools text-to-image

RunanywhereAI/RCLI

Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG

Category
multimodal media
Stars
1,540
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-assistant apple-silicon kitten-tts kokoro-tts lfm2 llama-cpp

netease-youdao/Confucius4-TTS

Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

Category
multimodal media
Stars
740
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +14 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

audio cross-lingual deep-learning fine-tuning multi-lingual python

QwenAudio/CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Category
multimodal media
Stars
22,635
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
watch
Maintenance risk
18/100 · high confidence

Why: +119 stars in 7 days; 43 lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: contributor breadth, issue load, documentation. Risks: recent commit cadence is 0/2.0 of its monthly baseline. Missing inputs: release recency.

Capped lower bounds: response activity.

audio-generation cantonese chatbot chatgpt chinese cosyvoice

BlackMixture/Mix-Studio

The cleanest, responsive AI workspace. Run highly tuned image and video workflows flawlessly from your desktop or your phone. Built on ComfyUI.

Category
multimodal media
Stars
237
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +44 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art comfyui image-generation lora mixstudio mobile-first

inlineresearch/Inline-Studio

AI filmmaking on a node canvas. Generate locally on your own GPU with the Inline Core engine (Z-Image, Krea 2, FLUX.2, MiniMax H3), or use hosted models with no GPU. Train your own LoRAs locally on th

Category
multimodal media
Stars
198
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +16 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art ai-film ai-filmmaking ai-video controlnet creative-tools

PRITHIVSAKTHIUR/Qwen-Image-Edit-2511-LoRAs-Fast-Lazy-Load

Demonstration for the Qwen-Image-Edit-2511 model with lazy-loaded LoRA adapters for advanced single- and multi-image editing. Supports 7+ specialized LoRAs including photo-to-anime, multi-angle camera

Category
multimodal media
Stars
117
Readiness
ready (99/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusers flash-attention-3 huggingface-transformers image-editor image-generation image-to-image

finegrain-ai/refiners

A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation

Category
multimodal media
Stars
837
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
100/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: repository is archived, no push in 324 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

background-generation background-removal controlnet diffusion-models dinov2 image-generation

FotographerAI/ZenCtrl

In-context subject-driven image generation while preserving foreground fidelity

Category
multimodal media
Stars
351
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 422 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models flux image-generation img2img lora subject-driven-generation

Anil-matcha/Open-Generative-AI

Unrestricted Open-source alternative to AI video platforms — Free AI image & video generation studio with 500+ models (Flux, Midjourney, Kling, Sora, Veo). No content filters. Self-hosted, MIT license

Category
multimodal media
Stars
25,808
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +529 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art-generator ai-image-generation ai-video-generation creative-tools fal-ai-alternative flux-1

HBAI-Ltd/Toonflow-app

Toonflow 是开源一站式 AI 短剧创作工具，将小说、剧本快速转化为动画短剧。集成 AI 编剧、智能分镜、角色与视频生成，跨平台桌面端轻量部署，助力创作者低成本批量产出视觉内容。Toonflow is an open-source AI tool that turns stories and scripts into animated short dramas. Features AI sc

Category
multimodal media
Stars
13,536
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +387 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-content-creation ai-tool ai-video-generation automation content-generation

SamurAIGPT/Generative-Media-Skills

Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.

Category
multimodal media
Stars
3,998
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +51 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills agent-tools ai-agents ai-video claude-code claude-code-skills

HanaokaYuzu/Gemini-API

✨ Reverse-engineered Python API for Google Gemini web app

Category
multimodal media
Stars
3,379
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +19 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai api async bard chatbot gemini

dramaclaw/dramaclaw

A general-purpose AIGC video engine: script to finished film in one pipeline — dramas, ads, product videos, otome games, and more. | 通用 AIGC 视频引擎 —— 从剧本到成片一条流水线，漫剧、广告、电商、乙游皆可

Category
multimodal media
Stars
3,337
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +518 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-filmmaking ai-video aigc aigc-pipeline content-creation

rsxdalv/TTS-WebUI

A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, Au

Category
multimodal media
Stars
3,230
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +10 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ace-step ai audio-generation cosyvoice generative-ai generator

FoundationVision/VAR

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *

Category
multimodal media
Stars
8,724
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 270 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

auto-regressive-model autoregressive-models diffusion-models generative-ai generative-model gpt

open-mmlab/mmagic

OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generatio

Category
multimodal media
Stars
7,450
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 731 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc computer-vision deep-learning diffusion diffusion-models generative-adversarial-network

fofr/cog-face-to-many

Turn any face into a video game character, pixel art, claymation, 3D or toy

Category
multimodal media
Stars
1,363
Readiness
needs review (48/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 850 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai cog comfyui generative-ai replicate text-to-image

Shilin-LU/TF-ICON

[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official Implementation)

Category
multimodal media
Stars
814
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 519 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-model generative-ai image-composition image-inversion stable-diffusion text-to-image

Boese0601/MagicDance

[ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

Category
multimodal media
Stars
777
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 765 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

behavior-generation cartoon-animation diffusion-models generative-ai generative-model image-editing

kwsong0113/diffusion-forcing-transformer

[ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"

Category
multimodal media
Stars
706
Readiness
high risk (43/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 402 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models generative-ai image-to-video transformer video-generation

Anil-matcha/awesome-generative-ai-apps

50+ open-source generative AI apps you can clone, deploy, and monetize — image generators, video tools, virtual try-ons, AI SaaS templates, and platform integrations. One-click Vercel deploy on every

Category
multimodal media
Stars
2,852
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +55 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-apps ai-image-generator ai-saas ai-tools ai-video-generator awesome

foxhui/WebAI2API

WebAI2API: 基于 Camoufox 的网页 AI 转 API 工具，支持 LMArena/Gemini等，多窗口并发与账号隔离。 | Web AI to OpenAI API via Camoufox. Supports LMArena/Gemini and more, multi-window concurrency & account isolation.

Category
multimodal media
Stars
1,212
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +20 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-tools browser-automation generative-ai image-generation openai-api text-generation

SamurAIGPT/muapi-cli

Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.

Category
multimodal media
Stars
1,037
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-api ai-tools api-client audio-generation cli

SamurAIGPT/Text-To-Video-AI

Generate video from text using AI

Category
multimodal media
Stars
795
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-api ai-tools ai-video ai-video-generator artificial-intelligence generative-ai

software-mansion/react-native-executorch

Declarative way to run AI models in React Native on device, powered by ExecuTorch.

Category
multimodal media
Stars
1,685
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

computer-vision executorch image-embeddings llm-inference object-detection ocr

YouMind-OpenLab/awesome-nano-banana-pro-prompts

🍌 World's largest Nano Banana Pro prompt library — 10,000+ curated prompts with preview images, 16 languages. Google Gemini AI image generation. Free & open source.

Category
multimodal media
Stars
13,086
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +68 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-image-generation ai-prompts awesome awesome-list gemini gemini-ai

YouMind-OpenLab/awesome-gpt-image-2

🚀 World's largest GPT Image 2 prompt library, updated daily — 2000+ curated prompts with preview images, 16 languages. OpenAI's next-gen image model with pixel-perfect text rendering, cross-image cons

Category
multimodal media
Stars
9,175
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +171 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-image-generation ai-prompts awesome awesome-list commercial-illustration duct-tape

promptslab/Awesome-Prompt-Engineering

This repository contains a hand-curated resources for Prompt Engineering with a focus on Generative Pre-trained Transformer (GPT), ChatGPT, PaLM etc

Category
multimodal media
Stars
6,234
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +22 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

chatgpt chatgpt-api deep-learning few-shot-learning gpt gpt-3

Open-Less/openless

Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows. (按住快捷键说话，松开即得润色后的文字)

Category
multimodal media
Stars
2,979
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +68 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-prompt asr dictation linux llm macos

YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill

AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.

Category
multimodal media
Stars
1,817
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +26 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-image claude-code-skill clawhub content-creation gemini

YouMind-OpenLab/awesome-seedance-2-prompts

🎬 2000+ curated Seedance 2.0 video generation prompts — cinematic, anime, UGC, ads, meme styles. Includes Seedance API guides, character consistency tips, and advanced video workflows.

Category
multimodal media
Stars
1,799
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +64 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video awesome awesome-list prompt-engineering seedance seedance-2

jamez-bondos/awesome-gpt4o-images

Awesome curated collection of images and prompts generated by GPT-4o and gpt-image-1. Explore AI generated visuals created with ChatGPT and Sora, showcasing OpenAI’s advanced image generation capabili

Category
multimodal media
Stars
8,116
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
18/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 438 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art ai-image-examples anime-ai-art awesome-list cartoon-style curated-collection

Hunyuan-PromptEnhancer/PromptEnhancer

[CVPR 2026] PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.

Category
multimodal media
Stars
3,748
Readiness
needs review (46/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

hunyuan hunyuan-image image-editing image-to-image prompt prompt-engineering

poloclub/diffusiondb

A large-scale text-to-image prompt gallery dataset based on Stable Diffusion

Category
multimodal media
Stars
1,389
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 757 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art computer-vision image-generation prompt-engineering stable-diffusion

jau123/nanobanana-trending-prompts

1,400+ curated trending AI image prompts from X, ranked by engagement. Works with NanoBanana, GPT Image 2, Midjourney

Category
multimodal media
Stars
706
Readiness
needs review (47/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

awesome-list gemini3proimage gpt-image image-generation midjourney nanobanana

ImgEdify/Awesome-GPT4o-Image-Prompts

📚 GPT4o Prompts Dictionary | Curated Collection of AI Image Generation Prompts

Category
multimodal media
Stars
583
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
18/100 · low confidence

Why: +3 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 450 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-image-creator ai-image-editing ai-image-generator ai-logo-maker aiimagegenerator

crmne/ruby_llm

One delightful Ruby framework for every major AI provider. Build AI agents, chatbots, RAG apps, and multimodal workflows in beautiful, expressive code.

Category
multimodal media
Stars
4,286
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agents ai anthropic chatgpt claude deepseek

waybarrios/vllm-mlx

OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX bac

Category
multimodal media
Stars
1,495
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +22 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

anthropic apple-silicon audio-processing claude-code computer-vision image-understanding

victoryangzhijie/stt-server

Real-time speech-to-text WebSocket server with pluggable ASR backends, energy-based VAD, streaming partial results, and Prometheus observability.

Category
multimodal media
Stars
90
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai asr qwen qwen-asr qwen3 qwen3-asr

Robitx/gp.nvim

Gp.nvim (GPT prompt) Neovim AI plugin: ChatGPT sessions & Instructable text/code operations & Speech to text [OpenAI, Ollama, Anthropic, ..]

Category
multimodal media
Stars
1,322
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 361 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

claude codeium copilot gemini gpt-4o gpt4o

amanvirparhar/chaplin

A real-time silent speech recognition tool.

Category
multimodal media
Stars
749
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +5 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 278 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

auto-avsr avsr llm ollama speech-recognition speech-to-text

NVlabs/Sana

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Category
multimodal media
Stars
8,719
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +85 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion dit linear-transformer nvfp4 pytorch reinforcement-learning

Blaizzy/mlx-audio

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

Category
multimodal media
Stars
7,694
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +32 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

apple-silicon audio-processing mlx multimodal speech-recognition speech-synthesis

argmaxinc/argmax-oss-swift

On-device Speech AI for Apple Silicon

Category
multimodal media
Stars
6,311
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

inference ios macos pyannote qwen3-tts speaker-diarization

gokayfem/awesome-vlm-architectures

Curated visual catalog of 155+ vision-language model (VLM/MLLM) architectures: papers, diagrams, training recipes, datasets, and a release timeline for multimodal AI agents.

Category
multimodal media
Stars
1,295
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents architecture-diagrams arxiv awesome awesome-list computer-vision

speechbrain/speechbrain

A PyTorch-based Speech Toolkit

Category
multimodal media
Stars
11,743
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +14 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr audio audio-processing deep-learning huggingface language-model

lucidrains/DALLE-pytorch

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

Category
multimodal media
Stars
5,628
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 902 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence attention-mechanism deep-learning multi-modal text-to-image transformers

lucidrains/deep-daze

Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun

Category
multimodal media
Stars
4,316
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1608 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence deep-learning implicit-neural-representation multi-modality siren text-to-image

linto-ai/whisper-timestamped

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

Category
multimodal media
Stars
2,836
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 332 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr attention-is-all-you-need attention-mechanism attention-model attention-network attention-seq2seq

saharmor/dalle-playground

A playground to generate images from any text prompt using Stable Diffusion (past: using DALL-E Mini)

Category
multimodal media
Stars
2,742
Readiness
needs review (60/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 795 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial artificial-intelligence dall-e dalle dalle-mini gan

zai-org/CogView

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

Category
multimodal media
Stars
1,799
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1047 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

pretrained-models pytorch text-to-image transformers

FoundationVision/Infinity

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

Category
multimodal media
Stars
1,587
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
19/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 113 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

auto-regressive-model autoregressive-models generative-model gpt gpt-2 image-generation

lucidrains/soundstorm-pytorch

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

Category
multimodal media
Stars
1,545
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 470 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence attention-mechanism audio-generation deep-learning non-autoregressive transformers

edwko/OuteTTS

Interface for OuteTTS models.

Category
multimodal media
Stars
1,437
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
23/100 · low confidence

Why: +1 stars in 30 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 137 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

gguf llama text-to-speech transformers tts

dorarad/gansformer

Generative Adversarial Transformers

Category
multimodal media
Stars
1,346
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1515 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

attention compositionality gans generative-adversarial-networks image-generation scene-generation

schmitech/orbit

Self-hosted, OpenAI-compatible AI gateway for private RAG, natural-language data access, and tool-calling agents.

Category
multimodal media
Stars
333
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-assistant ai-gateway ai-safety anthropic chatbot developer-tools

rapidaai/voice-ai

Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state mana

Category
multimodal media
Stars
709
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-framework ai-voice ai-voice-agent audio-streaming golang open-source

vllm-project/vllm-omni

A framework for efficient model inference with omni-modality models

Category
multimodal media
Stars
5,943
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +177 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

audio-generation diffusion image-generation inference model-serving multimodal

dograh-hq/dograh

Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.

Category
multimodal media
Stars
5,166
Readiness
ready (99/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +67 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-calling asterisk-ari conversational-ai inbound-calls local-llm no-code

sfortis/openai_tts

Custom TTS component for Home Assistant. Utilizes the OpenAI speech engine or any compatible endpoint to deliver high-quality speech. Optionally offers chime and audio normalization features.

Category
multimodal media
Stars
204
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
16/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, fork interest, documentation. Risks: no push in 94 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai chime ha hacs home-assistant homeassistant

fluxions-ai/vui

Real-time voice assistant — WebRTC streaming, faster-whisper ASR, local LLM, Vui Nano (300M) TTS. OpenAI Realtime API compatible. Voice cloning, barge-in, ~9× realtime on a 4090. Apache 2.0.

Category
multimodal media
Stars
741
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

audio-generation conversational-ai edge-ai lightweight llama multi-speaker

soniqo/speech-android

On-device speech SDK for Android — ASR, TTS, VAD, and noise cancellation powered by ONNX Runtime with Qualcomm NNAPI acceleration

Category
multimodal media
Stars
131
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

android asr automotive edge-ai kotlin nnapi

soniqo/speech-core

On-device VAD / streaming STT / TTS / diarization in C++17 (ONNX + LiteRT) with a voice-agent pipeline. Linux, Windows, Android.

Category
multimodal media
Stars
64
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

android cpp17 edge-ai kokoro litert nemotron

THU-MIG/edge-dit.cpp

edge-dit.cpp — a native C/C++ inference engine for Diffusion Transformers (DiT), designed for local and resource-constrained devices with automatic VRAM-aware precision, placement, and offloading.

Category
multimodal media
Stars
25
Readiness
ready (99/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

cpp diffusion-transformers dit edge-ai generative-ai ggml

suharvest/rkvoice-stream

Deploy streaming ASR + TTS on RK3576/RK3588 — 120ms TTS, 52-language ASR, one Docker command

Category
multimodal media
Stars
20
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr edge-ai npu rk3576 rk3588 rknn

Picovoice/speech-to-text-benchmark

speech to text benchmark framework

Category
multimodal media
Stars
697
Readiness
ready (73/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aws-transcribe cheetah deep-learning deep-neural-networks deepspeech edge-ai

rudrankriyam/Foundation-Models-Framework-Lab

A practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.

Category
multimodal media
Stars
1,165
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai apple-foundation-models apple-intelligence foundation-models foundation-models-framework generative-ai

Muesli-HQ/muesli

Muesli - local meeting transcription + dictation for macOS (Granola + WisprFlow alternative)

Category
multimodal media
Stars
901
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +41 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

apple-silicon dictation macos meeting-assistant meeting-notes on-device-ai

CodeBySonu95/VoxSherpa-TTS

🎙️ VoxSherpa TTS Offline Neural Text-to-Speech Engine for Android ⚡ Sherpa-ONNX powered 🔊 Natural voice synthesis 📱 Fully offline processing 🚀 No cloud • No limits

Category
multimodal media
Stars
192
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

android android-ai android-app hindi-tts kokoro-82m kokoro-onnx

mattmireles/kokoro-coreml

PyTorch → CoreML conversion pipeline for Kokoro TTS. Unlocks fast on-device text-to-speech on Apple Neural Engine.

Category
multimodal media
Stars
57
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

apple-neural-engine apple-silicon on-device-ai text-to-speech

vlr-code/dictly

On-device speech-to-text for macOS. Hold a hotkey → Whisper transcribes locally via CoreML → text auto-pastes into the focused app. 99 languages, free, open-source.

Category
multimodal media
Stars
46
Readiness
ready (72/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

apple-silicon dictation macos on-device-ai productivity speech-to-text

nicedreamzapp/NarrateClaude

Hands-free on-device voice loop for macOS: Apple SFSpeechRecognizer + cloned-voice TTS, continuous listening, zero cloud. Originally built to drive claude-code-local.

Category
multimodal media
Stars
45
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

apple-silicon claude-code hands-free local-ai macos offline-ai

getdictus/dictus-ios

Open-source iOS voice dictation keyboard — fully offline, private, no subscription required for core features.

Category
multimodal media
Stars
20
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

coreml dictation ios keyboard-extension offline on-device-ai

Mininglamp-AI/Mano-P

Mano-P: Open-source GUI-VLA agent for edge devices. #1 on OSWorld (specialized, 58.2%). Runs locally on Apple M4 Mac mini/MacBook — no data leaves your device.Mano-P 是一个开源 GUI-VLA 项目，支持在 Mac mini/MacB

Category
multimodal media
Stars
2,492
Readiness
needs review (65/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +20 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

computer-use-agents desktop-automation edge-computing gui-automation gui-grounding local-inference

PrismML-Eng/Bonsai-Image-Demo

Generate images locally

Category
multimodal media
Stars
525
Readiness
needs review (60/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

1-bit bonsai image-generation on-device-ai small-models ternary

QwenAudio/SenseVoice

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

Category
multimodal media
Stars
9,032
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +59 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr audio-analysis audio-event-detection cantonese cross-lingual emotion-detection

Osmantic/ODS

Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.

Category
multimodal media
Stars
4,049
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +215 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents amd comfyui docker llama-cpp llm

timoncool/dub-studio

Free offline AI video dubbing studio for Windows — voice cloning, translation, subtitles & on-screen-text localization. 100% local, one native .exe, zero Python.

Category
multimodal media
Stars
87
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-dubbing ai-video asr dubbing llama-cpp

Etamus/NeveAI

Neve AI é uma plataforma de IA local privacy-first, desenvolvida para oferecer uma experiência de alta performance na execução de LLMs, reduzindo a dependência de grandes plataformas, assinaturas cara

Category
multimodal media
Stars
49
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-workflow image-generation llama-cpp llm llms mtp

modelship-ai/modelship

Self-hosted, OpenAI-compatible inference for the agentic era: reasoning LLMs, universal tool calling, and the Responses API alongside embeddings, speech, and image models — many models sharing your GP

Category
multimodal media
Stars
38
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic diffusers embeddings gpu image-generation inference-server

calesthio/OpenMontage

World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video produc

Category
multimodal media
Stars
45,916
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +1,554 stars in 7 days; 50 commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: release recency.

agent agentic-ai ai claude copilot cursor

TonyLianLong/LLM-groundedDiffusion

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models (LLM-grounded Diffusion: LMD, TMLR 2024)

Category
multimodal media
Stars
484
Readiness
high risk (40/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 697 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-generation llm stable-diffusion stable-diffusion-webui text-to-image

Auto1111SDK/Auto1111SDK

An SDK/Python library for Automatic 1111 to run state-of-the-art diffusion models

Category
multimodal media
Stars
412
Readiness
high risk (43/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 793 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-art api automatic1111 deep-learning diffusers

AgnesAI-Labs/AgnesAI-Models

Official Agnes AI gateway and model catalog for OpenAI-compatible text, image, video, and agent workflows.

Category
multimodal media
Stars
2,694
Readiness
needs review (69/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +504 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agnes-ai ai-api free-api multimodal-ai

AutoArk/EVA-OS

EVA OS — A real-time multimodal AIOS for next-generation hardware, enabling your devices being “alive” and as intelligent as a real brain.

Category
multimodal media
Stars
1,304
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +154 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aios multimodal-ai real-time robotics smart-devices voice-assistant

yashab-cyber/opendroid

Your Open Autonomous Android Agent — A production-ready, self-planning AI assistant powered by local/remote LLMs and accessibility-driven screen automation.

Category
multimodal media
Stars
571
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +36 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

accessibility ai-agent android automation autonomous kotlin

Correr-Zhou/OmniShow

[ICML 2026] ByteDance's All-in-One Video Generation Model for Human-Object Interaction Video Generation

Category
multimodal media
Stars
464
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
watch
Maintenance risk
0/100 · high confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: maintenance is concentrated in one contributor. Missing inputs: release recency.

aigc computer-vision deep-learning diffusion-models dit icml

OpenMOSS/MOSS-VL

MOSS-VL is the core multimodal model series within the OpenMOSS ecosystem, dedicated to visual understanding.

Category
multimodal media
Stars
409
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

llms long-video-understanding multimodal-ai real-time-ai streaming-video video-understanding

Anil-matcha/awesome-seedance-2.5-api-prompts

Seedance 2.5 API guide, prompts, parameters, and examples for video generation

Category
multimodal media
Stars
282
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +15 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video ai-video-generation bytedance camera-control cinematic-ai generative-ai

Anil-matcha/Flux-3-Dev-API

Python wrapper for Black Forest Labs' FLUX 3 Dev API, available now — fast, low-cost FLUX 3 variant, plus the full FLUX 3 family (Text-to-Image, Image-to-Image, Text-to-Video, Image-to-Video).

Category
multimodal media
Stars
176
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-image ai-image-generation ai-video-generation black-forest-labs black-forest-labs-flux flux-3

Anil-matcha/awesome-flux-3-api-prompts

FLUX 3 video API and image API guide, prompts, parameters, and examples for Black Forest Labs' unified text-to-video, image-to-video, image, and audio generation model

Category
multimodal media
Stars
142
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-image-generation ai-video ai-video-generation api black-forest-labs flux

video-db/skills

Server-side video workflows for agents: ingest, understand, search, edit, stream.

Category
multimodal media
Stars
115
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai amp claude claude-code codex multimodal-ai

mims-harvard/OptimusKG

A modern multimodal knowledge graph with type-specific metadata across biomedical domains.

Category
multimodal media
Stars
110
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

biomedical graph-ai heterogeneous-graphs knowledge-graph multimodal-ai multimodal-data

addxai/ReflectWorld

ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Stream

Category
multimodal media
Stars
93
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents computer-vision lifelong-learning long-term-memory multimodal-ai openclaw

BeatAPI/awesome-minimax-h3-prompts

🎬 Curated MiniMax H3 video generation prompts — cinematic, ads, anime, UGC, product videos, and more. Includes playable examples and creator attribution.

Category
multimodal media
Stars
68
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video awesome-list generative-ai image-to-video minimax-h3 multimodal-ai

wq19901103wq/wechat-mac-rpa

基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat

Category
multimodal media
Stars
65
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai-agent ai-automation apple-script automation chatbot

zjunlp/LightMem-Ego

LightMem-Ego: Your AI Memory for Everyday Life

Category
multimodal media
Stars
64
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-memory artificial-intelligence lightmem lightmem-ego multimodal-ai

Supervertaler/Supervertaler-Workbench

Open-source, AI-enhanced CAT tool with multi-LLM support, translation memory, glossary management, 'Superlookup' concordance across TMs/glossaries/web resources, voice commands, Okapi sidecar for file

Category
multimodal media
Stars
50
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ahk ai cafetran cat-tool claude context-aware-translation

qcai0427/FactGroundEval

Evaluation tools and experiments for multimodal factual grounding, entity consistency, and image-text verification.

Category
multimodal media
Stars
35
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

evaluation factual-grounding image-text multimodal-ai vision-language

yang13926151198-ai/AI-Photographer-Agent-ROCm

Private local AI Photographer Agent on AMD Radeon and ROCm

Category
multimodal media
Stars
28
Readiness
ready (74/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent amd-rocm multimodal-ai photography qwen2-vl

tuya/agentic-kit

Multimodal AI SDK for IoT Devices

Category
multimodal media
Stars
27
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent ai embedded iot multimodal-ai sdk

Lum1104/video-to-skill

Turn videos and courses into evidence-grounded Agent Skills for Claude Code and Codex.

Category
multimodal media
Stars
21
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills claude-code codex multimodal-ai video youtube

studerus/pepper-android-realtime-chat

Open-source Android framework for low-latency, LLM-driven multimodal interaction on Pepper. Uses end-to-end speech-to-speech models and extensive Function Calling for agentic robot control (navigation

Category
multimodal media
Stars
18
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

android function-calling human-robot-interaction kotlin large-language-models multimodal-ai

ProjectArgus-cc/libargus.cc

A unified, unmanaged multimodal runtime. Zero-allocation native AI inference for Java 22+.

Category
multimodal media
Stars
15
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

foreign-function-and-memory-api ggml java-22 java-25 jvm llama-cpp

Capslockb/hermes-live-discord-agent-plugin

Hermes Live Discord Agent Plugin — full-duplex Discord voice ↔ Google Gemini Multimodal Live API, with function calling, idle hangup, transcripts, and a 3-min oneshot installer.

Category
multimodal media
Stars
14
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility

Strongest signals: push recency, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

discord-bot gemini-live hermes-agent hermes-plugin multimodal-ai plugin

microsoft/Build26-DEM331-turn-apis-tools-and-data-into-real-agent-velocity

Demo of a Fiber Cut Response Agent using Azure Content Understanding to process multi-modal field documents (PDFs, photos, diagrams, audio) and reason with Foundry models for incident triage. From Mic

Category
multimodal media
Stars
9
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents azure-ai-foundry azure-content-understanding build-2026 document-intelligence microsoft-build

Yale-BIDS-Chen-Lab/MedPMC

MedPMC: a high-fidelity medical image–text curation framework from biomedical literature for multimodal foundation models, with released pipelines, curated data, benchmarks, and pretrained models.

Category
multimodal media
Stars
8
Readiness
ready (75/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

biomedical-literature dataset-curation foundation-models medical-ai medical-imaging multimodal-ai

Anil-matcha/n8n-nodes-seedance2

n8n community node for ByteDance Seedance 2.0 and Seedance 2 Mini — automate Text-to-Video, Image-to-Video, and video generation in n8n workflows.

Category
multimodal media
Stars
7
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-automation ai-video bytedance generative-ai image-to-video low-code

criticaldata/PRIMED-AI

A framework for per-modality failure analysis and missing-data evaluation in multimodal clinical AI.

Category
multimodal media
Stars
7
Readiness
needs review (67/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

clinical-ai failure-analysis healthcare-ai interpretability medical-imaging model-robustness

sx4im/BIMO

Introducing Bimo 5 (Autonomous Multi-Modal AI Agent with real-time voice, vision processing, document analysis, image generation, and web search).

Category
multimodal media
Stars
7
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-assistant ai-chat ai-workspace autonomous-agents flask

kdr/overcast

Video OSINT agent: senses + OSINT reach for any agent.

Category
multimodal media
Stars
7
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills multimodal-ai osint video

pablo-reyes8/kimi-k3-pytorch

Build and train a mini Kimi K3 from scratch — a pure-PyTorch playground from a custom 88M model to 2T-scale LLM profiles.

Category
multimodal media
Stars
7
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

deep-learning generative-ai kimi-k3 kv-cache llm llm-training

ChaoYue0307/awesome-egocentric-atlas

Curated datasets, benchmarks, models, and tools for egocentric AI, embodied intelligence, VLA, world models, robotics, and wearable vision.

Category
multimodal media
Stars
6
Readiness
needs review (63/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

augmented-reality awesome-list benchmarks computer-vision datasets ego4d

ROCK-LAB-PRIVATE-LIMITED/federaide

P2P multi agent orchestration harness, universal automation system and IDE

Category
multimodal media
Stars
6
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-swarms agentic-ai cpp crossplatform deep-research-agent go

alexylon/sofos-web

Multi-model AI chatbot built with React, Next.js, and Material UI, with image analysis and speech-to-text.

Category
multimodal media
Stars
6
Readiness
ready (75/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-chatbot anthropic google-ai image-analysis material-ui multimodal-ai

ThanhChuong12/ecommerce-review-analytics

A Production-grade Multimodal AI System for Real-Time E-Commerce Review Analytics, Aspect Sentiment Analysis, Visual Defect Detection & Zero-Shot Product Reranking.

Category
multimodal media
Stars
5
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

computer-vision deep-learning ecommerce machine-learning multimodal-ai natural-language-processing

arsalanafzal010/SmartRAG

📄 Enable smart conversations with documents, images, and audio files using this advanced Retrieval-Augmented Generation system.

Category
multimodal media
Stars
5
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

autogen automation cli document-processing dotnet gpt

moksh-m9u/Multimodal-Rag

Production-ready multimodal RAG pipeline for PDFs. Extracts text, tables, and images down to the atomic element level via unstructured, chunks and AI-enriches them with a vision LLM, stores them in Ch

Category
multimodal media
Stars
5
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

chromadb multimodal-ai pdf-processing rag rag-pipeline streamlit-dashboard

expropriationhoorayhenry64/social-media-scraper-skill

Extract and summarize social media content from platforms like Instagram, TikTok, X, and YouTube using Claude Code.

Category
multimodal media
Stars
5
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai automation claude-code claude-skill content-analysis data-extraction

duixcom/Duix-Avatar

🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.

Category
multimodal media
Stars
14,377
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
18/100 · low confidence

Why: +97 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 108 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-avatar ai-avatars cloning cloning-tool digital-human multimodal-ai

Open-X-Humanoid/HEX

HEX is a whole-body vision-language-action framework for full-sized humanoid robots.

Category
multimodal media
Stars
328
Readiness
high risk (40/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

cross-embodiment embodied-ai humanoid-robotics imitation-learning multimodal-ai vision-language-action-model

SeanWong17/album-assetizer

个人相册语义资产生成器：扫描照片 → 视觉大模型标注 → 结构化数据 | Semantic asset generator for personal photo albums

Category
multimodal media
Stars
240
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-captioning multimodal-ai openai-compatible photo-management

wuyoscar/GPT-Image2-Skill

GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

Category
multimodal media
Stars
4,211
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +134 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills ai-image-prompts claude-code-skill cli codex-skill gpt-image

Lightricks/ComfyUI-LTXVideo

LTX-Video Support for ComfyUI

Category
multimodal media
Stars
4,038
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +24 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

comfyui diffusion-models dit image-to-video image-to-video-generation text-to-image

FurkanGozukara/Stable-Diffusion

FLUX, Stable Diffusion, SDXL, SD3, LoRA, Fine Tuning, DreamBooth, Training, Automatic1111, Forge WebUI, SwarmUI, DeepFake, TTS, Animation, Text To Video, Tutorials, Guides, Lectures, Courses, ComfyUI,

Category
multimodal media
Stars
2,752
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art coding deepfake-generation dreambooth education flux-dev

jenissimo/unfake.js

Fix AI pixel art and vector images right in your browser

Category
multimodal media
Stars
889
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

browser-tools computer-vision pixel-art text-to-image vector-graphics

VigoZhao/AI-Visual-Prompt-Cookbook

Curated collection of reusable JSON prompt templates & style references for AI image generation. Updated daily.

Category
multimodal media
Stars
541
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +14 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai design-resources generative-ai image-generation json midjourney

ashbuilds/payload-ai

AI Plugin is a powerful extension for the Payload CMS, integrating advanced AI capabilities to enhance content creation and management.

Category
multimodal media
Stars
539
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-translate ai-writing ai-writing-tool content-generation gpt-image-1

Isi-dev/Google-Colab_Notebooks

A Collection of Google Colab Notebooks for various projects

Category
multimodal media
Stars
503
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

animate-x colab-notebooks comfyui-workflow flux-kontext framepack hidream

SamurAIGPT/AI-Faceless-Video-Generator

Generate a video script, voice and a talking face completely with AI

Category
multimodal media
Stars
477
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +5 stars in 7 days

Why it may be a gem: open issue backlog is stable or shrinking

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: release recency.

ai-video-generator artificial-intelligence faceless faceless-video image-to-video shorts

Lakonik/LakonLab

Official implementation of AsymFlow, pi-Flow, GMFlow

Category
multimodal media
Stars
459
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
8/100 · high confidence

Why: +1 stars in 7 days; 12 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: issue load, documentation, license. Risks: no pull-request review responses in 30 days. Missing inputs: None.

diffusion-models distillation flow-matching generative-ai generative-model image-generation

HorizonWind2004/reconstruction-alignment

[ICLR 2026] Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learnin

Category
multimodal media
Stars
411
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc bagel comfy comfyui diffusion image-editing

wooyeolbaek/attention-map-diffusers

attention map tools for huggingface/diffusers

Category
multimodal media
Stars
409
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

attention-map cross-attention cross-attention-diffusers cross-attention-map diffusers huggingface

aqm857886159/Nomi

Open-source AI video workbench. Bring any model or your local ComfyUI, and let Claude Code / Codex / Cursor direct it over MCP — storyboard, references, generation, editable first cut on a real timeli

Category
multimodal media
Stars
399
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +20 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-video ai-video-generator bring-your-own-key comfyui creative-tools

Shilin-LU/MACE

[CVPR 2024] "MACE: Mass Concept Erasure in Diffusion Models" (Official Implementation)

Category
multimodal media
Stars
394
Readiness
needs review (68/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models generative-ai stable-diffusion text-to-image

viiika/Meissonic

[ICLR 2025] Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

Category
multimodal media
Stars
345
Readiness
needs review (69/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-to-image non-autoregressive-transformers text-to-image

SamurAIGPT/AI-Influencer-Generator

Create and customize your AI influencer open-source

Category
multimodal media
Stars
279
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-api ai-influencer ai-tools artificial-intelligence creative-ai flux

zlab-princeton/i1

Code release for "i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models"

Category
multimodal media
Stars
261
Readiness
needs review (68/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models jax pytorch text-to-image

WuMingDao/zenith-image-generator

Modern AI image generator with multi-provider support (Gitee AI, HuggingFace, ModelScope), OpenAI-compatible API, token rotation, and one-click deployment to Cloudflare Pages.

Category
multimodal media
Stars
216
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

biome cloudflare gitee-ai hono huggingface image-generation-ai

gokayfem/ComfyUI-fal-API

Production-ready ComfyUI custom nodes for 1,400+ fal.ai models, auto-updated image, video, audio, LLM and VLM APIs with native media, caching and cost controls.

Category
multimodal media
Stars
203
Readiness
ready (100/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-api audio-generation comfyui comfyui-custom-nodes fal fal-ai

Westlake-AGI-Lab/Awesome-Style-Transfer-with-Diffusion-Models

A curated list of recent style transfer methods with diffusion models

Category
multimodal media
Stars
197
Readiness
needs review (67/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc diffusion-models style-transfer text-to-image text-to-video

Mooshieblob1/MooshieUI

A front-end UI for ComfyUI made for beginner level users.

Category
multimodal media
Stars
168
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art comfyui desktop-app flux generative-ai image-generation

EddieTYP/image-prompt-library

Local-first image prompt library for generating images, saving prompts, tags, and collections.

Category
multimodal media
Stars
127
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-image all-in-one allinone chatgpt fastapi gpt-image-2

volcengine/ark-cli

The fastest way to put Volcengine Ark in your terminal and your AI agent — go from prompt to generated media, multimodal answer, or deployed endpoint in a single command, no API glue code.

Category
multimodal media
Stars
93
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-skills ark cli doubao llm

mir-ashiq/metaai-api

FastAPI wrapper for Meta AI with chat, image generation & video generation. Easy deployment with cookie-based auth. 🚀

Category
multimodal media
Stars
90
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai api api-wrapper chat-api fastapi free

Kewal-Yaduvanshi/GPT-Image-2-Flow-Workbench

Best GPT Image 2 OpenAi Prompts & Tools Guide 2026

Category
multimodal media
Stars
88
Readiness
ready (75/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-image chatgpt gpt-image-2 gpt-image-2-api gpt-image-2-prompts image-editing

Anil-matcha/awesome-ai-image-models

The most complete, up-to-date comparison of AI image generation models — which model, via which API, at what price.

Category
multimodal media
Stars
78
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-image ai-image-generator awesome awesome-list flux generative-ai

doanbactam/awesome-stable-diffusion

A curated list of awesome stable diffusion resources 🌟

Category
multimodal media
Stars
77
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aiart awesome dall-e diffusion diffusion-models dockerfile

moosl/awsome-gpt-image-2-prompts

No description

Category
multimodal media
Stars
74
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

api awsome-list gpt-image-2 gpt-image-2-prompts image-generation image-prompt

yuji-hatakeyama/opencode-gpt-imagegen

OpenCode plugin: image generation via your ChatGPT subscription or OpenAI API

Category
multimodal media
Stars
68
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents chatgpt codex gpt-image-2 image-generation openai

SamurAIGPT/muapi-comfyui

ComfyUI custom nodes for 100+ AI models — Seedance, Kling, Veo3, Flux, HiDream, GPT-image, Imagen4 and more via muapi.ai

Category
multimodal media
Stars
67
Readiness
ready (98/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-image-editing ai-video-generation comfyui comfyui-custom-nodes comfyui-nodes flux

geoffsmith82/Symposium2023

Demonstrates Voice Recognition, Text to Speech, Language Translation, OAuth2, Image Generation, Face Detection and Voice Chatbot.

Category
multimodal media
Stars
66
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai artificial-intelligence claude-3-haiku claude-3-opus claude-3-sonnet computer-vision

kodelyx/flow-agent

⚡ CLI toolkit for Google Flow — Nano Banana Pro images, Omni Flash videos, MCP v2 & OpenAI API.

Category
multimodal media
Stars
63
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +15 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

automation cli google-flow image-generation mcp nano-banana

seehiong/banana-levelup

An interactive web demo for AI avatar creation — generate characters from a text prompt and inspect them in a 360° viewer. Powered by Gemini. 🍌🤖

Category
multimodal media
Stars
52
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

360-viewer ai-art avatar-generator character-generation gemini generative-ai

unstonio/pixelgpt-24x24

Tiny local text-to-24x24 pixel art model, trained on roughly 200K samples in 30 minutes on an RTX 5090.

Category
multimodal media
Stars
52
Readiness
needs review (67/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +21 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

autoregressive-model fastapi generative-ai local-ai pixel-art pytorch

sneezeparty/soupy

Fully-local Discord bot with chat, RAG memory, autonomous Discord posts, Bluesky integration, and image generation. Runs against LM Studio + Stable Diffusion OR Flux, with a FastAPI web control panel

Category
multimodal media
Stars
37
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

bot chatbot chatgpt-api discord discord-bot flux

AbuZar-Ansarii/PrivatePixelPrompt

PortableLM — Zero-dependency, air-gapped local AI that runs entirely from a USB drive. Chat, generate images, and synthesize speech offline on Windows, macOS, or Linux. No installs, no internet, just

Category
multimodal media
Stars
31
Readiness
ready (100/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents ai-model ai-tools image-generation llm

SamurAIGPT/nano-banana-generator

Open-source Nano Banana image generator — production-ready Next.js SaaS for text-to-image and multi-image reference editing. Stripe billing, credits, NextAuth, and Prisma out of the box.

Category
multimodal media
Stars
31
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art-generator ai-image-generator ai-photo-editor ai-saas gemini-2-5-flash gemini-image

SamurAIGPT/Text-To-Video-API

Text to Video API generation documentation

Category
multimodal media
Stars
29
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video-generator image-to-video image-to-video-generation sora-ai sora-video-ai stable-diffusion

dngda/self-bot

Typescript - Lightweights WhatsApp bot 🤖 made to response only self message with Baileys ✨

Category
multimodal media
Stars
28
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

baileys baileys-md bot converter downloader ffmpeg

gbmomo/gemini-image-webapp

Private AI Image Generation Website Source Code powered by Gemini API | Ready-to-use | Text-to-Image/Image-to-Image/Multi-turn Chat | User System + Credits Billing + Redemption Codes | Built with Flas

Category
multimodal media
Stars
28
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-image-generation flask gemini gemini-api generative-ai google-gemini

Syh1906/openai-compatible-imagegen

Agent skill for OpenAI-compatible image generation, editing, and batch workflows.

Category
multimodal media
Stars
25
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-tools batch-generation codex-skill image-generation openai-compatible python

pixelpainter/comfyui-AI-prompt-editor

A full prompt-writing studio in a single ComfyUI node - AI editing, style targeting, prompt browsing, and wireless prompt injection, powered by your local Ollama models. No cloud, no keys.

Category
multimodal media
Stars
24
Readiness
ready (74/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-prompt comfyui comfyui-custom-nodes comfyui-manager comfyui-nodes custom-nodes

AxisEgretDefeat/kling-ai-master

Kling AI Master

Category
multimodal media
Stars
22
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

kling kling-4 kling-ai text-to-image

AtlasCloudAI/atlascloud_comfyui

Use Atlas Cloud's 300+ AI models inside ComfyUI — drop-in nodes for Sora 2, Veo 3.1, Kling 3, Seedance 2, Nano Banana Pro, GPT Image 2, Flux 2 & more.

Category
multimodal media
Stars
20
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai atlascloud comfyui comfyui-nodes generative-ai image-generation

astropuzzo/ComfyUI-MiniMax-H3-Image-Studio

Experimental, entirely AI-coded ComfyUI nodes for MiniMax H3 T2I, I2I, reference editing, arbitrary frames, and optimized still selection.

Category
multimodal media
Stars
19
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-assisted comfyui experimental generative-ai image-editing image-to-image

wubo0927/xiaoyou-aigc-cinematic-director

小优AIGC（抖音小优与AIGC的奇妙冒险）的 AI 摄影剧组 skill —— 电影摄影级生图提示词生成器，可装入 Claude Code / Codex / Hermes

Category
multimodal media
Stars
19
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills aigc claude-code prompt-engineering text-to-image

Senzo13/JoyBoy

Local AI harness/workstation: local AI image editor, Ollama image generation routing, SDXL inpainting UI, CivitAI model imports, 8GB VRAM Stable Diffusion.

Category
multimodal media
Stars
18
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

8gb-vram ai-assistant ai-harness ai-workstation chatgpt-alternative civitai

EnragedAntelope/comfyui-identity-forge

A character forge for ComfyUI: dial in or randomize every detail - face, hair, body, wardrobe, mood - and get a coherent, reproducible person, canonically-described cosplayer, or creature as ready-to-

Category
multimodal media
Stars
15
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

character-creator character-generator comfyui comfyui-custom-nodes prompt-generator text-to-image

paperfoot/nanaban-cli

AI image generation CLI. One command, one image, three seconds. Gemini-powered.

Category
multimodal media
Stars
15
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent-tools ai-art ai-image-generator cli command-line developer-tools

hyeonsangjeon/AIsketcher

Reproducible sketch-to-render studies with ControlNet: seed scouting, variation, export, replay, and a local Studio.

Category
multimodal media
Stars
15
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

canny-edge-detection computer-vision controlnet diffusers generative-ai gradio

404stillhere/upg

Universal Prompt Generator — prompt-engineering system for text-to-image models. Spectrum of 1–5 calibrated prompts per theme, with safety/drift/cliche enforcement built into the pipeline.

Category
multimodal media
Stars
14
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-prompts chatgpt claude flux gemini generative-ai

purohit10saurabh/toyFLUX

A toy PyTorch implementation of FLUX diffusion transformers

Category
multimodal media
Stars
14
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

deep-learning diffusion-transformer educational flux flux-architecture flux-kontext

minkhant1996/soemind-forge

Budget-aware AI agent content studio for creating videos, images, carousels, voiceovers, music, captions, and content calendars with consistent brand assets and cost control.

Category
multimodal media
Stars
13
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-connector ai ai-agents ai-video-toolkit claude-code content-creation-tools

AtlasCloudAI/awesome-gpt-image-2-prompts

Awesome GPT Image 2 Prompts

Category
multimodal media
Stars
12
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai awesome awesome-list generative-ai gpt-image-2 gpt-image-2-prompts

Agents365-ai/imagencn

AI image generation via 5 Chinese platforms — DashScope, Volcano Ark, Hunyuan, Zhipu, StepFun — 30 models, Chinese text excellence

Category
multimodal media
Stars
12
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills ai-art alibaba-cloud claude-code claude-code-skill claude-skills

KDB-Wind/gpt-image-2-studio

轻量 GPT-Image-2 生图工作台，特别支持批量调用 GPT-Image-2：支持 AI 拆分提示词、队列、重试和图生图 / Lightweight GPT-Image-2 studio with batch calls, AI prompt splitting, queueing, retries, and image-to-image.

Category
multimodal media
Stars
12
Readiness
needs review (71/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

desktop-app gpt-image-2 image-to-image local-first openai-compatible tauri

sjh9714/krea2-wildcards

475 tested Krea 2 Turbo prompts. One file, drop it in ComfyUI.

Category
multimodal media
Stars
12
Readiness
ready (99/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art ai-prompts awesome awesome-list generative-ai image-generation

Anil-matcha/Awesome-GPT-Image-2-API-Prompts

Curated GPT-Image-2 prompts for the OpenAI API — portraits, posters, UI mockups, game screenshots, character sheets, and more. Ready-to-use prompts for gpt-image-2.

Category
multimodal media
Stars
12
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art ai-generated-art ai-image api awesome-list chatgpt

1fairyfox/random-ai-prompt

An open-source generator for AI image and text prompts that automatically builds richer, more detailed prompts than most people write by hand. Compose from a large library of scenes, subjects, and sty

Category
multimodal media
Stars
11
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-art comfyui dynamic-prompts generative-ai image-generation

SamurAIGPT/muapi-mcp-server

Mcp server code to setup muapi to work with clients like Claude, Cursor etc.

Category
multimodal media
Stars
10
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-api ai-tools anthropic api audio-generation

VitalikDen0/Model-To-NPU

Model-to-NPU pipelines for Qualcomm Snapdragon: QNN/ONNX/Android runtimes for on-device image and video generation.

Category
multimodal media
Stars
10
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

android diffusion-models hexagon-npu on-device-ai onnx qairt

bean980310/ai-companion

AI companions including generative AI such as chatbots, image generation, text generation, and audio generation.

Category
multimodal media
Stars
9
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-translate chatbot generative-ai image-generation llm

elbruno/ElBruno.Text2Image

A .NET library for local image captioning using ONNX Runtime with automatic HuggingFace model download

Category
multimodal media
Stars
9
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai csharp cuda directml dotnet flux

Adi-UA/start-journey

Text-to-image web app: Stable Diffusion (Diffusers/PyTorch) behind a FastAPI backend that also serves a React frontend, with live streaming generation progress. Runs locally on GPU, CPU, or Apple MPS.

Category
multimodal media
Stars
8
Readiness
ready (72/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusers fastapi pytorch react stable-diffusion text-to-image

avlp12/krea2_alis_mlx

Krea 2 Turbo (12.9B text-to-image) ported to Apple MLX — local web UI + CLI, validated faithful to PyTorch

Category
multimodal media
Stars
8
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

apple-silicon diffusion gradio image-generation krea mlx

Stable-yogi/sd-forge-krea2

Run Krea 2 (Krea AI's 12B DiT) natively in Forge Neo — the first open-source Krea 2 extension. One-click model download, presets, fp8, full + piecewise loading. By Stable Yogi.

Category
multimodal media
Stars
7
Readiness
ready (72/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art forge krea krea2 sd-webui-extension sd-webui-forge

lucidrains/DALLE2-pytorch

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

Category
multimodal media
Stars
11,307
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, license. Risks: no push in 818 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence deep-learning text-to-image

lucidrains/imagen-pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

Category
multimodal media
Stars
8,418
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 669 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence deep-learning imagination-machine text-to-image text-to-video

XavierXiao/Dreambooth-Stable-Diffusion

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

Category
multimodal media
Stars
7,737
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1338 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

pytorch pytorch-lightning stable-diffusion text-to-image

HisMax/RedInk

Red Ink - A one-stop Xiaohongshu image-and-text generator based on the 🍌Nano Banana Pro🍌, "One Sentence, One Image: Generate Xiaohongshu Text and Images."

Category
multimodal media
Stars
5,443
Readiness
needs review (64/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +15 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai aigc content-generator docker flask gemini

kuprel/min-dalle

min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch

Category
multimodal media
Stars
3,497
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 466 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence deep-learning pytorch text-to-image

YangLing0818/Diffusion-Models-Papers-Survey-Taxonomy

Diffusion model papers, survey, and taxonomy

Category
multimodal media
Stars
3,366
Readiness
high risk (41/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 314 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models stable-diffusion survey text-to-3d text-to-image text-to-video

ai-forever/Kandinsky-2

Kandinsky 2 — multilingual text2image latent diffusion model

Category
multimodal media
Stars
2,815
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 828 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion image-generation image2image inpainting ipython-notebook kandinsky

bytedance/InfiniteYou

🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

Category
multimodal media
Stars
2,685
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 350 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusers diffusion diffusion-transformer dit face flux

nerdyrodent/VQGAN-CLIP

Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

Category
multimodal media
Stars
2,649
Readiness
high risk (42/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load. Risks: no push in 1405 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

text-to-image text2image

lucidrains/big-sleep

A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN. Technique was originally created by https://twitter.com/advadnoun

Category
multimodal media
Stars
2,572
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1643 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence deep-learning generative-adversarial-networks multimodality text-to-image

Yutong-Zhou-cv/Awesome-Text-to-Image

(ෆ`꒳´ෆ) A Survey on Text-to-Image Generation/Synthesis.

Category
multimodal media
Stars
2,441
Readiness
needs review (69/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

awseome-list generative-adversarial-network image-generation image-manipulation image-synthesis multimodal

carefree0910/carefree-creator

AI magics meet Infinite draw board.

Category
multimodal media
Stars
1,937
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 820 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-to-image inpainting latent-diffusion outpainting pypi python

YangLing0818/RPG-DiffusionMaster

[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (RPG)

Category
multimodal media
Stars
1,843
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 552 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-editting large-language-models multimodal-large-language-models text-to-image

TencentARC/BrushNet

[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"

Category
multimodal media
Stars
1,740
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 598 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion diffusion-models eccv eccv2024 image-inpainting text-to-image

omerbt/TokenFlow

Official Pytorch Implementation for "TokenFlow: Consistent Diffusion Features for Consistent Video Editing" presenting "TokenFlow" (ICLR 2024)

Category
multimodal media
Stars
1,707
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 550 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

iclr2024 stable-diffusion text-to-image text-to-video tokenflow video-editing

ai-forever/ru-dalle

Generate images from texts. In Russian

Category
multimodal media
Stars
1,645
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1305 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

dalle image-generation openai python pytorch russian

bytedance/UNO

[ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning

Category
multimodal media
Stars
1,361
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 329 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion diffusion-transformer flux image-generation in-context-learning subject-driven-generation

Capsize-Games/airunner

Offline inference engine for art, real-time voice conversations, LLM powered chatbots and automated workflows

Category
multimodal media
Stars
1,312
Readiness
needs review (63/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-art art asset-generator chatbot deep-learning

PRIV-Creation/Awesome-Controllable-T2I-Diffusion-Models

A collection of resources on controllable generation with text-to-image diffusion models.

Category
multimodal media
Stars
1,110
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
24/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 584 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

awesome awesome-list controllable-generation diffusion-models multi-concept personalization

zai-org/CogView4

CogView4, CogView3-Plus and CogView3(ECCV 2024)

Category
multimodal media
Stars
1,100
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 496 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

eccv2024 high-resolution image-generation text-to-image

lukasHoel/text2room

Text2Room generates textured 3D meshes from a given text prompt using 2D text-to-image models (ICCV2023).

Category
multimodal media
Stars
1,087
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 996 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

3d-generation diffusion-models mesh-generation text-to-image

omerbt/MultiDiffusion

Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

Category
multimodal media
Stars
1,065
Readiness
high risk (40/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 1051 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models generative-model icml image-generation multidiffusion stable-diffusion

iptag/jimeng-api

Reverse-engineered the official API for Jimeng/Dreamina’s text-to-image and image-to-image features. Drew inspiration from several experts’ projects and made some tweaks, which significantly improved

Category
multimodal media
Stars
1,044
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
96/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: repository is archived, no push in 158 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

api-reverse-engineering dreamina image-to-image jimeng text-to-image unofficial-api

zai-org/CogView2

official code repo for paper "CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers"

Category
multimodal media
Stars
955
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1465 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

pretrained-models pytorch text-to-image transformer

lucidrains/muse-maskgit-pytorch

Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch

Category
multimodal media
Stars
918
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 890 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence attention-mechanisms deep-learning text-to-image transformers

ChaofanTao/Autoregressive-Models-in-Vision-Survey

[TMLR 2025🔥] A survey for the autoregressive models in vision.

Category
multimodal media
Stars
805
Readiness
high risk (38/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
16/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 94 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

acceleration autoregressive computer-vision deep-learning diffusion embodied-ai

eps696/aphantasia

CLIP + FFT/DWT/RGB = text to image/video

Category
multimodal media
Stars
790
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, license. Risks: no push in 540 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

clip text-to-image text-to-video

mfrashad/text2art

AI-powered Text-to-Art Generator - Text2Art.com

Category
multimodal media
Stars
773
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 1112 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

art colab-notebook deep-learning gan generative-art machine-learning

yuval-alaluf/Attend-and-Excite

Official Implementation for "Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models" (SIGGRAPH 2023)

Category
multimodal media
Stars
770
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, license. Risks: no push in 924 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models stable-diffusion text-to-image

AlonzoLeeeooo/awesome-text-to-image-studies

A collection of awesome text-to-image generation studies.

Category
multimodal media
Stars
763
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence diffusion-models text-to-image text-to-image-ai text-to-image-diffusion

fboulnois/stable-diffusion-docker

Run the official Stable Diffusion releases in a Docker container with txt2img, img2img, depth2img, pix2pix, upscale4x, and inpaint.

Category
multimodal media
Stars
746
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 952 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

dall-e dalle diffusion docker generative-art huggingface

vicgalle/stable-diffusion-aesthetic-gradients

Personalization for Stable Diffusion via Aesthetic Gradients 🎨

Category
multimodal media
Stars
742
Readiness
needs review (45/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 1386 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models laion stable-diffusion text-to-image text2image

jianzhnie/awesome-text-to-video

A Survey on Text-to-Video Generation/Synthesis.

Category
multimodal media
Stars
738
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc image-generation text-to-image text-to-video video-generation

PaddlePaddle/PaddleMIX

Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high per

Category
multimodal media
Stars
724
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
26/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 154 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc clip controlnet deepseek-vl dit eva-clip

markfulton/NanoBananaEditor

The most advanced Nano Banana image generator and editor application. Your central hub for AI image generation and revisions. Intuitive UI features reference images, editing with image masks, version

Category
multimodal media
Stars
704
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aiimages bolt imageediting imageeditor imagegeneration imagegenerator

Tencent-Hunyuan/HunyuanImage-2.1

HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation​

Category
multimodal media
Stars
675
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 297 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc diffusion-models diffusion-transformer image-generation text-to-image

lehduong/OneDiffusion

Official implementation of OneDiffusion paper (CVPR 2025)

Category
multimodal media
Stars
662
Readiness
high risk (42/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 601 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models image-translation novel-view-synthesis single-view-reconstruction stable-diffusion text-to-image

gojasper/flash-diffusion

Flash Diffusion — accelerating conditional diffusion models (AAAI 2025 Oral)

Category
multimodal media
Stars
662
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 514 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models distillation dit inpainting sdxl super-resolution

ChenWu98/cycle-diffusion

[ICCV 2023] A latent space for stochastic diffusion models

Category
multimodal media
Stars
658
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 950 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models generative-models image-synthesis image-to-image-translation score-based-generative-models stable-diffusion

SkyWorkAIGC/SkyPaint-AI-Diffusion

基于Stable Diffusion优化的AI绘画模型。支持输入中英文文本，可生成多种现代艺术风格的高质量图像。| An optimized text-to-image model based on Stable Diffusion. Both Chinese and English text inputs are available to generate images. The model c

Category
multimodal media
Stars
648
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1247 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-painting aigc artificial-intelligence bert clip cv

FoundationVision/Liquid

(Accepted by IJCV) Liquid: Language Models are Scalable and Unified Multi-modal Generators

Category
multimodal media
Stars
642
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

autoregressive-models generative generative-ai image-gen large-language-models llms

fofr/cog-face-to-sticker

face-to-sticker

Category
multimodal media
Stars
642
Readiness
needs review (46/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: issue load, documentation. Risks: no push in 889 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai comfyui generative-ai replicate text-to-image

omriav/blended-latent-diffusion

Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]

Category
multimodal media
Stars
632
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 794 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

computer-vision deep-learning diffusion diffusion-models generative-model image-generation

limuloo/MIGC

[CVPR 2024 Highlight] MIGC and [TPAMI 2024] MIGC++ (Official Implementation)

Category
multimodal media
Stars
612
Readiness
high risk (43/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 449 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc computer-vision cvpr cvpr2024 stable-diffusion text-to-image

zsdonghao/text-to-image

Generative Adversarial Text to Image Synthesis / Please Star -->

Category
multimodal media
Stars
599
Readiness
needs review (47/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 2023 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

gan tensorflow tensorlayer text-to-image

ironjr/semantic-draw

Official code for the CVPR 2025 paper "SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models."

Category
multimodal media
Stars
589
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 432 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

cvpr2025 diffusion-models drawing huggingface-spaces image-generation stable-diffusion

omriav/blended-diffusion

Official implementation for "Blended Diffusion for Text-driven Editing of Natural Images" [CVPR 2022]

Category
multimodal media
Stars
588
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 794 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

blended-diffusion deep-learning diffusion multimodal openai openai-clip

YingqingHe/Awesome-LLMs-meet-Multimodal-Generation

🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).

Category
multimodal media
Stars
551
Readiness
high risk (40/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
20/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 490 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc large-language-models large-vision-language-models llm lvlm mllm

akanimax/T2F

T2F: text to face generation using Deep Learning

Category
multimodal media
Stars
546
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1546 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

adversarial-machine-learning gan generative-adversarial-network progressively-growing-gan text-to-image

lucidrains/parti-pytorch

Implementation of Parti, Google's pure attention-based text-to-image neural network, in Pytorch

Category
multimodal media
Stars
537
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 973 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence attention-mechanism deep-learning text-to-image transformers

jaketae/storyteller

Multimodal AI Story Teller, built with Stable Diffusion, GPT, and neural text-to-speech

Category
multimodal media
Stars
535
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1074 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ddpm diffusion-models gpt image-generation natural-language-generation pytorch

FoundationVision/UniTok

[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding

Category
multimodal media
Stars
530
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 266 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

autoregressive-models generative generative-ai generative-model image-generation image-tokenizer

google/break-a-scene

Official implementation for "Break-A-Scene: Extracting Multiple Concepts from a Single Image" [SIGGRAPH Asia 2023]

Category
multimodal media
Stars
525
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
100/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: repository is archived, no push in 936 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

deep-learning diffusion-models generative-ai multimodal text-to-image

open-mmlab/StyleShot

StyleShot: A SnapShot on Any Style. 一款可以迁移任意风格到任意内容的模型，无需针对图片微调，即能生成高质量的个性风格化图片!

Category
multimodal media
Stars
472
Readiness
needs review (48/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, license. Risks: no push in 403 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

controllable-generation style-transfer text-to-image

AlaaLab/InstructCV

[ ICLR 2024 ] Official Codebase for "InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists"

Category
multimodal media
Stars
461
Readiness
needs review (45/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 832 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models generative-model multi-task-learning stable-diffusion text-to-image vision-language-model

afiaka87/clip-guided-diffusion

A CLI tool/python module for generating images from text using guided diffusion and CLIP from OpenAI.

Category
multimodal media
Stars
459
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
18/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 220 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence deep-learning diffusion image-generation multimodal multimodality

Jermic/awesome-aiart-pics-prompts

🎨 精选 3000+ Gemini Nano Banana Pro 高质量提示词与生成案例 | 涵盖摄影、设计、艺术、营销等多领域 | 双语支持 | JSON 格式

Category
multimodal media
Stars
454
Readiness
high risk (41/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art-prompt-engineering ai-image-generation ai-prompts awesome awesome-list creative-prompts

ATH-MaaS/Ovis-U1

An unified model that seamlessly integrates multimodal understanding, text-to-image generation, and image editing within a single powerful framework.

Category
multimodal media
Stars
451
Readiness
needs review (46/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, license. Risks: no push in 248 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-editing multimodal-large-language-models text-to-image

EleutherAI/DALLE-mtf

Open-AI's DALL-E for large scale training in mesh-tensorflow.

Category
multimodal media
Stars
432
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1637 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence autoregressive multimodal text-to-image transformers variational-autoencoder

XiaomingX/awesome-qwen-prompt-insight

🧠 世界上覆盖最全的优秀Qwen提示语大全，欢迎贡献你的提示词。🧠 The most comprehensive collection of excellent Qwen prompts in the world. Feel free to contribute your own prompts!

Category
multimodal media
Stars
412
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

awesome claude example gpt openai prompt

aelnouby/Text-to-Image-Synthesis

Pytorch implementation of Generative Adversarial Text-to-Image Synthesis paper

Category
multimodal media
Stars
411
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 2205 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

gans image-generation pytorch text-to-image zero-shot-learning

OSU-NLP-Group/MagicBrush

[NeurIPS'23] "MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing".

Category
multimodal media
Stars
411
Readiness
high risk (43/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 533 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models image-editing image-generation image-synthesis instruction-following text-to-image

snap-research/stable-flow

Official implementation for "Stable Flow: Vital Layers for Training-Free Image Editing" [CVPR 2025]

Category
multimodal media
Stars
409
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 425 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

deep-learning diffusion-models flow-models generative-ai image-editing machine-learning

garibida/cross-image-attention

Officail Implementation for "Cross-Image Attention for Zero-Shot Appearance Transfer"

Category
multimodal media
Stars
404
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 824 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

appearance-transfer diffusion-models stable-diffusion style-transfer text-to-image

xuyang-liu16/Awesome-Generation-Acceleration

📚 Collection of awesome generation acceleration resources.

Category
multimodal media
Stars
402
Readiness
high risk (38/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
16/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 396 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models efficient-deep-learning efficient-inference image-generation model-acceleration text-to-image

sayakpaul/diffusers-torchao

End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).

Category
multimodal media
Stars
400
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 211 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

architecture-optimization diffusion-models flux text-to-image torch torch-compile

nerdyrodent/CLIP-Guided-Diffusion

Just playing with getting CLIP Guided Diffusion running locally, rather than having to use colab.

Category
multimodal media
Stars
385
Readiness
high risk (42/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load. Risks: no push in 1439 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

openai-clip text-to-image text2image

krea-ai/flux-krea

Official GitHub repository for FLUX.1 Krea [dev].

Category
multimodal media
Stars
365
Readiness
high risk (39/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 371 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models flux machine-learning text-to-image

jonathandinu/ai4artists

A list of AI Art courses, tools, libraries, people, and places.

Category
multimodal media
Stars
364
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 777 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-art artificial-intelligence awesome awesome-list creative-coding deep-learning

jabir-zheng/TCD

Official Repository of the paper "Trajectory Consistency Distillation"

Category
multimodal media
Stars
360
Readiness
high risk (38/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 831 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

consistency-models diffusion fast-sampling score-based-models stable-diffusion text-to-image

Karine-Huang/T2I-CompBench

[Neurips 2023 & TPAMI] T2I-CompBench (++) for Compositional Text-to-image Generation Evaluation

Category
multimodal media
Stars
345
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
15/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 92 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

benchmark compositionality dataset text-to-image

awekrx/ChatGPT-MidJourney-prompt

This is a ChatGPT based prompt generation model for MidJorney. The purpose of this model is to simplify the creation of images and increase their creativity. By introducing a partial hint, ChatGPT cre

Category
multimodal media
Stars
341
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-art ai-painting chatgpt midjourney prompt

Bria-AI/FIBO

FIBO is a SOTA, first open-source, JSON-native text-to-image model built for controllable, predictable, and legally safe image generation.

Category
multimodal media
Stars
329
Readiness
high risk (43/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 212 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai ai controlable-image-generation creative-ai deep-learning enterprise-ready

tobran/DF-GAN

[CVPR2022 oral] A Simple and Effective Baseline for Text-to-Image Synthesis

Category
multimodal media
Stars
326
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest. Risks: no push in 317 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

generative-adversarial-network text-to-image

mihirp1998/AlignProp

AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (P

Category
multimodal media
Stars
324
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 645 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

alignment diffusion-models reinforcement-learning stable-diffusion text-to-image

mkshing/e4t-diffusion

Implementation of Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models

Category
multimodal media
Stars
323
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1202 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

deep-learning diffusion-models stable-diffusion text-to-image

woctezuma/stable-diffusion-colab

Colab notebook for Stable Diffusion Hyper-SDXL.

Category
multimodal media
Stars
323
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
27/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 479 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

colab colab-notebook colaboratory deep-learning diffusers diffusion

ATH-MaaS/Ovis-Image

Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints.

Category
multimodal media
Stars
321
Readiness
needs review (45/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-generation text-to-image

byliutao/1Prompt1Story

🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

Category
multimodal media
Stars
320
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 291 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion diffusion-model diffusion-models storytelling text-to-image

MohamadZeina/Disco_Diffusion_Local

Getting the latest versions of Disco Diffusion to work locally, instead of colab. Including how I run this on Windows, despite some Linux only dependencies ;)

Category
multimodal media
Stars
316
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1472 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

3d-animation art clip dall-e dalle disco-diffusion

AssemblyAI-Community/MinImagen

MinImagen: A minimal implementation of the Imagen text-to-image model

Category
multimodal media
Stars
312
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 1187 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

deep-learning diffusion-models imagen pytorch super-resolution text-to-image

bytedance/ComfyUI_InfiniteYou

🔥 [ICCV 2025 Highlight] Official ComfyUI native node supporting InfiniteYou with FLUX

Category
multimodal media
Stars
298
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 378 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

comfyui comfyui-nodes diffusion diffusion-transformer dit face

HolmesShuan/FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-Editing

[ICML2025] An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are comparable or even superior to baseline methods)

Category
multimodal media
Stars
295
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 463 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

flux flux-dev generative-model image-editing text-to-image

PKU-YuanGroup/Helios

Helios: Real Real-Time Long Video Generation Model

Category
multimodal media
Stars
2,034
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +20 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

acceleration diffusion diffusion-model diffusion-models efficient-tuning high-quality

Alisa0808/vox-director

Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.

Category
multimodal media
Stars
1,166
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +320 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-video claude-code claude-skill collage-video explainer-video

thu-ml/Causal-Forcing

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

Category
multimodal media
Stars
911
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +19 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

auto-regressive-diffusion-model autoregressive-models consistency-models diffusion diffusion-models distillation

Orkas-AI/Orkas-VideoStudio

Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.

Category
multimodal media
Stars
521
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agents ai-video cli coding-agents ffmpeg generative-ai

Anil-matcha/Open-AI-Micro-Drama-Generator

AI short drama & micro-drama video generator — turns any idea into a complete short-form drama using multi-agent AI pipeline (screenwriter → storyboard → frames → video). Seedance 2 VIP, Kling 3.0 Pro

Category
multimodal media
Stars
451
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +14 stars in 7 days

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: release recency.

agentic-ai ai-drama ai-filmmaking ai-short-drama ai-video-generation drama-generator

gyunggyung/AGI-Papers

A curated archive of breakthroughs in Agents, Architecture, Training, RAG, and On-Device AI.

Category
multimodal media
Stars
421
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
watch
Maintenance risk
0/100 · high confidence

Why: +2 stars in 7 days

Why it may be a gem: open issue backlog is stable or shrinking

Strongest signals: push recency, issue load, documentation. Risks: maintenance is concentrated in one contributor. Missing inputs: release recency.

all-to-all dialogue distillation efficient llm multimodal

james-see/ltx-video-mac

Native macOS app for AI video generation using LTX-Video model, optimized for Apple Silicon

Category
multimodal media
Stars
371
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +9 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-to-video ltx-2 ltx-video mac-app mac-native text-to-video

vargHQ/sdk

AI video generation SDK — JSX for videos. One API for Kling, Flux, ElevenLabs, Veed. Built on Vercel AI SDK.

Category
multimodal media
Stars
333
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-sdk ai-video claude-code cursor elevenlabs flux

jnMetaCode/ai-shortfilm-prompts

Claude Code Skill that turns any idea into a cinematic, model-ready video prompt — Sora · Kling · Veo · Seedance. 21 genre templates, 5-stage structure, eval-tested. Distilled from the AI short Hollyw

Category
multimodal media
Stars
328
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +19 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video chinese cinematic cinematic-prompts claude-code claude-skill

SamurAIGPT/Clip-Anything

Clip any moment from any video with prompts

Category
multimodal media
Stars
285
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video ai-video-generator ai-video-maker clipanything clipbasic shorts

Blizaine/Maestro

An all-in-one, 100% local AI video, image, and music studio. Director mode plans full music videos and short films from a single prompt. Built on the WanGP pipeline. Install via Pinokio.

Category
multimodal media
Stars
239
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +137 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-video image-generation local-ai ltx-video music-generation

Anil-matcha/Open-AI-UGC

Open AI UGC — free, open-source alternative to Arcads and MakeUGC. Generate AI UGC video ads with realistic AI actors using Veo 3.1, Seedance 2, Grok Video, and Happy Horse 1. Self-host on Next.js + S

Category
multimodal media
Stars
233
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +19 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-actors ai-marketing ai-ugc ai-video-ads ai-video-generator arcads-alternative

lcy362/agnes-video-generator

Open-source, self-hosted AI video generator — completely free. Text to multi-scene video with narration, subtitles, and digital anchor via Web UI, powered by Agnes AI.

Category
multimodal media
Stars
214
Readiness
ready (99/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +17 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agnes agnes-video ai-video-generator ai-video-maker free-ai-software free-ai-video

witty-suckerpunch492/daihuo-jianshou

自动生成电商带货短视频：上传商品图，AI 生成脚本、素材并合成视频，适配抖音、快手、小红书

Category
multimodal media
Stars
205
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +13 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video-generation ffmpeg flux kling kuaishou nextjs

idwts/Crayotter

🦦 Crayotter: A Multimodal AI-Agent for Video-Editing, Video-Composing, and Video Production. Powered by Multimodal LLMs for autonomous Text-to-Video agentic framework. | 基于多模态大模型 (Multimodal LLMs) 的 A

Category
multimodal media
Stars
189
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +19 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent mllms text-to-video video-composing video-editing video-production

Anil-matcha/awesome-ai-video-models

The most complete, up-to-date comparison of AI video generation models — which model, via which API, at what price, and how fast.

Category
multimodal media
Stars
179
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video ai-video-generator awesome awesome-list generative-ai hailuo

vericontext/vibeframe

Frontier AI video generation for coding agents - Seedance, Runway, Veo, Kling on your own keys, behind a hard cost cap. CLI + MCP.

Category
multimodal media
Stars
164
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agents claude cli developer-tools ffmpeg

NicholasCone/agnes-ai-video-suite

Best Open Source AI Video Generator 2026: Text to Multi-Scene Movies with Narration & Subtitles

Category
multimodal media
Stars
157
Readiness
ready (75/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agnes agnes-video ai-video-generator ai-video-maker free-ai-software free-ai-video

wordghost1234/agnes-ai-storyboard-studio

2026 Guide to Self-Hosted Open Source AI Video Generation

Category
multimodal media
Stars
156
Readiness
ready (75/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agnes agnes-video ai-video-generator ai-video-maker free-ai-software free-ai-video

seesee75-commits/ComfyUI-MiniMaxH3-Director

A timeline editor for MiniMax H3 inside ComfyUI - storyboard prompts, first/last keyframes, image/video/audio references, joint audio, live sampling preview, retakes and shot chaining.

Category
multimodal media
Stars
153
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

comfyui comfyui-nodes image-to-video minimax minimax-h3 storyboard

Anil-matcha/vox-ai-motion-graphics-generator

🎬 Turn any topic into a finished Vox-style paper-collage explainer / motion graphics video — script, collage keyframes, animation, voice-over, music & captions, all automated. An agent skill for Claud

Category
multimodal media
Stars
138
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +23 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skill ai-motion-graphics ai-video claude-code collage explainer-video

neopen/story-shot-agent

剧本分镜工具智能体（PenShot）：电影/动漫/短剧/小说/剧本→分镜→片段→prompt | 基于 LangGraph+LLM，自动解析任意格式剧本，生成 Sora/Veo/Runway 等模型可用的连贯text-to-video提示词。保持角色/剧情跨片段一致，支持 MCP/REST API/函数调用 | Python库 + A2A集成。（LLM-powered screenplay-to-

Category
multimodal media
Stars
134
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-to-agent ai-filmmaking ai-video-generation character-consistency function-calling kling-ai

AtlasCloudAI/awesome-seedance-2.5-prompts-skills

100+ curated Seedance 2.5 prompts with real video previews, plus an installable Agent Skill that optimizes prompts, creates storyboards, and generates videos via Seedance models.

Category
multimodal media
Stars
132
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +22 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills ai ai-agents ai-video artificial-intelligence awesome-list

calesthio/generative-media-skills

Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.

Category
multimodal media
Stars
121
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-ai ai ai-audio ai-video claude

JuneYaooo/awesome-ai-media-cn

AI 视频制作与自媒体运营工具精选合集 — 涵盖一键生成、文生视频、多平台分发、字幕翻译等 150+ 开源项目，每周更新。

Category
multimodal media
Stars
113
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +15 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video automation awesome awesome-list content-creation short-video

itsjwill/vanta

Open source AI video engine built on Remotion. Voice cloning, AI avatars, animated captions, text-to-video (Wan 2.2/LTX), AI music, video editor, timeline, 100+ transitions. Free Synthesia, HeyGen, Ru

Category
multimodal media
Stars
95
Readiness
ready (79/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-avatars ai-music ai-video auto-captions background-removal capcut-alternative

woodfantasy/Seedance-ShotDesign-Skills

Seedance 2.5 Shot Design Skills

Category
multimodal media
Stars
90
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video claude-skills jimeng prompt-engineering seedance text-to-video

toki-plus/ai-mixed-cut

颠覆性AI内容再创作引擎，通过“解构-重构”爆款视频模式，全自动生成高度原创短视频。AIGC, Content Creation, Video Generation, Automation, LLM, Python, FFmpeg.

Category
multimodal media
Stars
90
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc automation content-creation content-repurposing content-strategy ffmpeg

gongnyang/reelforge

Agent-native AI video factory: one brief → narrated, subtitled, scene-editable videos (shorts & long-form). Deterministic HTML rendering, free keyless stack, Korean-first.

Category
multimodal media
Stars
76
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video-generator faceless-video hyperframes shorts-automation text-to-video video-agent

SamurAIGPT/seedance-2-generator

Open-source Next.js SaaS for Seedance 2.0 , Seedance 2.5 and Seedance 2 Mini video generation — Stripe billing, credits, NextAuth, and Prisma out of the box.

Category
multimodal media
Stars
72
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-saas ai-video ai-video-generator bytedance-seedance generative-ai generative-video

Agions/mangav

MangaV (漫织 AI) - 端到端 AI 漫剧创作平台。集成 13 大 AI 大模型、视听多模态与 FFmpeg 硬件加速引擎，输入一本小说，AI 自动生成 4K 精致漫剧。

Category
multimodal media
Stars
72
Readiness
ready (100/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-manga ai-tools anime-generator computer-vision cyberpunk

Cuongyd196/auto-video-gen

Biến 1 URL tin tức/GitHub thành video 9:16 chuẩn TikTok/Reels/Shorts trong 5 phút — không cần edit, TTS tiếng Việt + motion graphic tự động.

Category
multimodal media
Stars
45
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video-generation shorts-generator text-to-video tiktok-video

Anil-matcha/MiniMax-H3-API

Python SDK for the MiniMax H3 API — text-to-video, image-to-video, and first/last-frame video generation via Muapi.

Category
multimodal media
Stars
45
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +16 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-tools ai-video api artificial-intelligence creative-ai developer-tools

aws-deadline/deadline-cloud-samples

Ready-to-run AWS Deadline Cloud samples for rendering (Maya, Blender, Houdini, Nuke); physical AI (robotics, autonomous driving simulation, MuJoCo, CARLA); synthetic data generation; generative AI vid

Category
multimodal media
Stars
40
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aws aws-deadline-cloud bioinformatics blender carla cloud-rendering

Anil-matcha/seedance2-comfyui

Seedance 2.0, 2.5 & 2 Mini ComfyUI: custom nodes and workflows for ByteDance video generation via MuAPI — text-to-video, image-to-video, Omni Reference, consistent characters, and video extend.

Category
multimodal media
Stars
38
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-video ai-video-generation bytedance comfyui comfyui-custom-nodes

camgraphe/MaxVideoAi

Compare and generate AI videos across Sora, Veo, Kling, Seedance & more.

Category
multimodal media
Stars
35
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-tools ai-video-generation ai-video-generator fal-ai generative-ai image-to-video

YouMind-OpenLab/awesome-grok-imagine-prompts

🎬 Curated Grok Imagine (xAI) video generation prompts — cinematic, action, anime, product, meme styles. Includes prompt engineering tips, style guides, and creative video workflows.

Category
multimodal media
Stars
34
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-video awesome grok grok-imagine prompts

longxiang-ai/awesome-video-diffusions

A curated and auto-updated collection of video diffusion / video generation papers from arXiv, covering text-to-video, image-to-video, controllable generation, world models, video editing, and 16+ res

Category
multimodal media
Stars
34
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

arxiv arxiv-papers awesome awesome-list controllable-generation diffusion-models

CUTEPKQ/NEWTON

NEWTON: Agentic Planning for Physically Grounded Video Generation

Category
multimodal media
Stars
32
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic-ai agentic-video-generation ai-agents aigc computer-vision diffusion-models

sadekxD/cardstock-diorama-myth

Claude skill that turns a single request into a narrated mythic short film in a layered cut-paper diorama style — three-colour cardstock worlds, paper wipes, Unsora MCP + local ffmpeg, one assembled M

Category
multimodal media
Stars
31
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video animation claude claude-code claude-skill claude-skills

Johnson-Jia/video-clipforge

AI 驱动的短视频制作系统。给它一个想法，它帮你写稿、配音、做画面、出成片。9 阶段 DAG 管线 + 自进化评分，支持每日自动执行。基于 Claude Code + HyperFrames。

Category
multimodal media
Stars
29
Readiness
ready (96/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

automation claude-code dag douyin html hyperframes

oolong-tea-2026/arena-ai-leaderboards

📊 Daily auto-updated snapshots of all Arena AI (LMSYS Chatbot Arena) leaderboards — LLM, Vision, Code, Video, Image & more. Structured JSON with historical tracking.

Category
multimodal media
Stars
28
Readiness
ready (100/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-benchmark arena-ai benchmark chatbot-arena leaderboard

itsPremkumar/Automated-Video-Generator

Agentic AI video generator — fully autonomous text-to-video pipeline with free TTS/voice-clone, auto-editing, captions, and 20+ single-task operations. Zero-cost, MIT.

Category
multimodal media
Stars
27
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agentic ai ai-video automation captions chatterbox

Shubham2376G/NanoI2V

Building an Image-to-Video (I2V) Model from Scratch

Category
multimodal media
Stars
25
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

computer-vision deep-learning diffusion-models flow-matching generative-ai huggingface

maciejdzierzek/kling-ai-prompt-generator

Claude plugin for Kling AI video prompts. Works with Claude.ai, Claude Desktop & Claude Code. I2V, T2V, Motion Control, Storyboards. Try live: maciejdzierzek.com

Category
multimodal media
Stars
23
Readiness
ready (98/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-tools ai-video claude-code claude-skill generative-ai image-to-video

paperfoot/seedance-cli

ByteDance Seedance 2.0 / 2.5 from your terminal. Text-to-video, image-to-video, audio & video refs, up to 4K. One agent-ready Rust binary.

Category
multimodal media
Stars
23
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-cli agent-friendly ai ai-video bytedance byteplus

PKU-YuanGroup/Helios-Page

Helios: Real Real-Time Long Video Generation Model

Category
multimodal media
Stars
23
Readiness
ready (72/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

acceleration diffusion diffusion-model diffusion-models efficient-tuning high-quality

GravityVerseYield47/flux-ai-works

Flux AI Works

Category
multimodal media
Stars
21
Readiness
ready (73/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

flux-ai flux-api flux-dev image-to-video-api image-to-video-generation text-to-video

vargHQ/skills

AI agent skills for video, image, speech & music generation. Works with Claude Code, Cursor, Windsurf, OpenCode, ClawHub.

Category
multimodal media
Stars
20
Readiness
needs review (68/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent-skills ai-agent ai-tools ai-video claude-code clawhub

SamurAIGPT/Sora-2-api

Sora 2 api access using http://muapi.ai

Category
multimodal media
Stars
18
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-video api generative-ai openai openai-api python

shim0114/T2V-Diffusion-Search

[NeurIPS 2025] Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search

Category
multimodal media
Stars
18
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

alignment diffusion-models inference-time-scaling neurips-2025 test-time-scaling text-to-video

Anil-matcha/gemini-omni-comfyui

ComfyUI custom nodes for Google Gemini Omni — text-to-video, image-to-video, and video editing via the Gemini Omni API on muapi.ai

Category
multimodal media
Stars
18
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: strong signals despite limited visibility; healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-video ai-video-generation comfyui comfyui-custom-nodes comfyui-nodes

Lightricks/LTX-Video

Official repository for LTX-Video

Category
multimodal media
Stars
10,818
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +31 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 214 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models dit image-to-video image-to-video-generation text-to-video text-to-video-generation

AILab-CVC/VideoCrafter

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

Category
multimodal media
Stars
5,071
Readiness
high risk (40/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load. Risks: no push in 210 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-to-video text-to-video video-generation

Tencent-Hunyuan/HunyuanVideo-1.5

HunyuanVideo-1.5: A leading lightweight video generation model

Category
multimodal media
Stars
4,556
Readiness
high risk (39/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
20/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load. Risks: no push in 119 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-to-video text-to-video video-generation

ChenHsing/Awesome-Video-Diffusion-Models

[CSUR] A Survey on Video Diffusion Models

Category
multimodal media
Stars
2,310
Readiness
needs review (48/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

awesome awesome-list diffusion diffusion-models survey text-to-video

lucidrains/make-a-video-pytorch

Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch

Category
multimodal media
Stars
1,985
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 826 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence attention-mechanisms axial-convolutions deep-learning text-to-video

LingyiChen-AI/AIComicBuilder

AI-powered animated comic generator — transform scripts into fully animated videos with AI-driven character design, storyboarding, and video synthesis.

Category
multimodal media
Stars
1,750
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
17/100 · low confidence

Why: +47 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 102 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-animation ai-animation-generator ai-animation-tools aicomicbuilder storytelling storytelling-ai

Vchitect/VBench

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

Category
multimodal media
Stars
1,724
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
23/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 137 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc benchmark dataset evaluation-kit gen-ai stable-diffusion

Phantom-video/Phantom

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

Category
multimodal media
Stars
1,515
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 330 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc consistency-models text-to-video video-generation

camenduru/text-to-video-synthesis-colab

Text To Video Synthesis Colab

Category
multimodal media
Stars
1,513
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 862 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

colab colab-notebook colaboratory t2v text-to-video

lucidrains/video-diffusion-pytorch

Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch

Category
multimodal media
Stars
1,384
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 826 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence ddpm deep-learning text-to-video video-generation

PKU-YuanGroup/MagicTime

[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

Category
multimodal media
Stars
1,339
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
19/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 115 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models long-video-generation metamorphic-video-generation open-sora-plan text-to-video time-lapse

hotshotco/Hotshot-XL

✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL

Category
multimodal media
Stars
1,111
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 927 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai hotshot hotshot-xl sdxl text-to-gif text-to-video

ShareGPT4Omni/ShareGPT4Video

[NeurIPS 2024] An official implementation of "ShareGPT4Video: Improving Video Understanding and Generation with Better Captions"

Category
multimodal media
Stars
1,092
Readiness
high risk (39/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 667 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

chatgpt gpt gpt-4v large-language-models large-multimodal-models large-video-language-models

Tencent-Hunyuan/HunyuanVideo-Foley

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.

Category
multimodal media
Stars
1,060
Readiness
needs review (45/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 313 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc-audio foley-art foley-sound-synthesis text-to-audio text-to-video text-video-to-audio

showlab/MotionDirector

[ECCV 2024 Oral] MotionDirector: Motion Customization of Text-to-Video Diffusion Models.

Category
multimodal media
Stars
1,049
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 716 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models motion-customization text-to-motion text-to-video text-to-video-generation video-generation

noahgsolomon/brainrot.js

Text to video generator in the brainrot form. Learn about any topic from your favorite personalities 😼.

Category
multimodal media
Stars
955
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
17/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 104 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

automate chatgpt nextjs python remotion text-to-video

360CVGroup/FancyVideo

Video generation from text&image, 1st-gen

Category
multimodal media
Stars
921
Readiness
high risk (35/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load. Risks: no push in 454 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-to-video text-to-video video-generation

PKU-YuanGroup/ConsisID

[CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition

Category
multimodal media
Stars
851
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
19/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 115 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion diffusion-models identity-preserving text-to-video video-generation video-generation-dataset

kandinskylab/kandinsky-5

Kandinsky 5.0: A family of diffusion models for Video & Image generation

Category
multimodal media
Stars
806
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion distillation kandinsky text-to-video video video-generation

lucidrains/phenaki-pytorch

Implementation of Phenaki Video, which uses Mask GIT to produce text guided videos of up to 2 minutes in length, in Pytorch

Category
multimodal media
Stars
790
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 739 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence attention-mechanisms deep-learning imagination-machine text-to-video transformers

SkyworkAI/Matrix-3D

Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text prompt.

Category
multimodal media
Stars
777
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 255 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

3d-generation 3d-reconstruction 3d-scene-generation aigc aigc3d genie

ExponentialML/Text-To-Video-Finetuning

Finetune ModelScope's Text To Video model using Diffusers 🧨

Category
multimodal media
Stars
703
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
100/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: repository is archived, no push in 967 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

deep-learning diffusers diffusion-models modelscope pytorch stable-diffusion

stdstu12/YUME

The official code of Yume

Category
multimodal media
Stars
681
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 205 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-to-video interactive-generation real-time-generation text-to-video world-model

F-R-L/forge-film

Multi-model DAG-driven parallel AI film generation — parallel speedup scales with scene independence; Generate film scenes simultaneously instead of one by one; "把影视生成的执行图从拓扑序变成关键路径最优调度" ; 唯一把场景叙事依赖建

Category
multimodal media
Stars
641
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
22/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 134 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-cinematography ai-filmmaking ai-video-generation cpm critical-path-method

Vchitect/VEnhancer

Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

Category
multimodal media
Stars
578
Readiness
high risk (39/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 690 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc-enhancement diffusion-models frame-interpolation text-to-video video-enhancement video-generation

VideoVerses/VideoTuna

Let's finetune video generation models!

Category
multimodal media
Stars
551
Readiness
high risk (43/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: issue load, documentation. Risks: no push in 326 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai aigc content-production fine-tuning-diffusion text-to-video video-generation

lucidrains/nuwa-pytorch

Implementation of NÜWA, state of the art attention network for text to video synthesis, in Pytorch

Category
multimodal media
Stars
548
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1298 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence attention-mechanism deep-learning text-to-audio text-to-video transformers

TianxingWu/FreeInit

[ECCV 2024] FreeInit: Bridging Initialization Gap in Video Diffusion Models

Category
multimodal media
Stars
544
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 932 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc text-to-video video-diffusion-model video-generation

FoundationVision/FlashVideo

[AAAI-2026]FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation

Category
multimodal media
Stars
484
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +24 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 520 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models efficient-generative-model generative-models text-to-video video-generation

Zhen-Dong/Magic-Me

Codes for ID-Specific Video Customized Diffusion

Category
multimodal media
Stars
458
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 897 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models image-animation image-editting personalized-generation text-to-video video-diffusion

michaelzhang-ai/Text2Video

ICASSP 2022: "Text2Video: text-driven talking-head video synthesis with phonetic dictionary".

Category
multimodal media
Stars
438
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
100/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: repository is archived, no push in 1161 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc avatar deep-learning digital-humanities gan generative-ai

cporter202/ai-agent-tools

A curated collection of AI tools, utilities, and resources for developers and creators

Category
multimodal media
Stars
436
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai ai-agent-directory ai-agents-framework ai-artificial-intelligence ai-tools-directory chatbot

imlixinyang/Director3D

Code for "Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text" (NeurIPS 2024).

Category
multimodal media
Stars
381
Readiness
high risk (43/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 511 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

3d 3d-aigc 3dgs aigc generative-model text-to-3d

Ji4chenLi/t2v-turbo

Code repository for T2V-Turbo and T2V-Turbo-v2

Category
multimodal media
Stars
312
Readiness
high risk (36/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load. Risks: no push in 553 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

consistency-models text-to-video video-generation

G-U-N/Gen-L-Video

The official implementation for "Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising".

Category
multimodal media
Stars
308
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 292 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models long-video-generation stable-diffusion text-to-video text2video video-editing

artkulak/text2youtube

🎥 Create youtube videos from a text prompt in seconds

Category
multimodal media
Stars
303
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 999 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

automation content-creation text-to-video youtube youtube-automation

songweige/TATS

Official PyTorch implementation of TATS: A Long Video Generation Framework with Time-Agnostic VQGAN and Time-Sensitive Transformer (ECCV 2022)

Category
multimodal media
Stars
288
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 828 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

audio-to-video long-video-generation pytorch text-to-video video-generation video-manipulation

RQ-Wu/LAMP

[CVPR 2024] | LAMP: Learn a Motion Pattern for Few-Shot Based Video Generation

Category
multimodal media
Stars
283
Readiness
high risk (42/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 837 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc diffusion diffusion-model diffusion-models few-shot-learning stable-diffusion

lucidrains/lumiere-pytorch

Implementation of Lumiere, SOTA text-to-video generation from Google Deepmind, in Pytorch

Category
multimodal media
Stars
282
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 742 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence deep-learning denoising-diffusion text-to-video

AILab-CVC/VideoGen-Eval

VideoGen-Eval: Agent-based System for Video Generation Evaluation

Category
multimodal media
Stars
269
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 234 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc benchmark image-to-video sora-video-ai text-to-video video-evaluation

ammaarreshi/openjourney

Open-source clone of the MidJourney web interface featuring real AI image and video generation powered by Google's Gemini SDK. Use Imagen 4 to generate images and Veo 2 and 3 for image and text to vid

Category
multimodal media
Stars
263
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 382 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai generative-ai image-generation image-to-video open-source text-to-image

Yazdi9/Talking_Face_Avatar

Avatar Generation For Characters and Game Assets Using Deep Fakes

Category
multimodal media
Stars
234
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 719 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

api audio-to-video avatar-generation conversational-ai deep-fake elevenlabs

FareedKhan-dev/AI-text-to-video-model-from-scratch

In this blog, we will build a small scale text-to-video model from scratch. We will input a text prompt, and our trained model will generate a video based on that prompt.

Category
multimodal media
Stars
232
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 775 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai deep-learning gan gemini gpt-4 openai

PKU-YuanGroup/OpenS2V-Nexus

[NeurIPS 2025 D&B🔥] OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

Category
multimodal media
Stars
226
Readiness
needs review (50/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc benchmark dataset evaluation-kit image-to-video image-to-video-generation

czg1225/AsyncDiff

[NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising

Category
multimodal media
Stars
215
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, documentation, license. Risks: no push in 314 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

diffusion-models distributed-computing efficient-inference inference-acceleration stable-diffusion text-to-image

PKU-YuanGroup/ChronoMagic-Bench

[NeurIPS 2024 D&B Spotlight🔥] ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation

Category
multimodal media
Stars
213
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
19/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, documentation, license. Risks: no push in 115 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aigc benchmark dataset diffusion-models evaluation evaluation-kit

XavierCHEN34/LivePhoto

Official implementations for paper: LivePhoto: Real Image Animation with Text-guided Motion Control

Category
multimodal media
Stars
204
Readiness
needs review (47/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals; strong signals despite limited visibility

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-animation image-to-video text-to-video video-generation

ggml-org/whisper.cpp

Port of OpenAI's Whisper model in C/C++

Category
multimodal media
Stars
52,674
Readiness
ready (94/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: +203 stars in 7 days; 100+ commits in 30 days

Why it may be a gem: consistent human and community activity; healthy maintenance and project fundamentals

Strongest signals: push recency, commit activity, contributor breadth. Risks: None identified. Missing inputs: None.

Capped lower bounds: 30-day commits, lifetime contributors.

inference openai speech-recognition speech-to-text transformer whisper

cjpais/Handy

A free, open source, and extensible speech-to-text application that works completely offline.

Category
multimodal media
Stars
28,978
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +746 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

accessibility cross-platform speech-to-text tauri-v2

m-bain/whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Category
multimodal media
Stars
23,473
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +110 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr speech speech-recognition speech-to-text whisper

jianchang512/pyvideotrans

Translate the video from one language to another and embed dubbing & subtitles.

Category
multimodal media
Stars
18,620
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +111 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

speech-to-text text-to-speech video-transition

k2-fsa/sherpa-onnx

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android

Category
multimodal media
Stars
14,033
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +123 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aarch64 android arm32 asr cpp csharp

huggingface/speech-to-speech

Build local voice agents with open-source models

Category
multimodal media
Stars
11,584
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1,828 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai assistant language-model machine-learning python speech

Uberi/speech_recognition

Speech recognition module for Python, supporting several engines and APIs, online and offline.

Category
multimodal media
Stars
8,982
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

audio python speech-recognition speech-to-text

TalAter/annyang

💬 Speech recognition for your site

Category
multimodal media
Stars
6,818
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

speech speech-recognition speech-to-text voice

snakers4/silero-models

Silero Models: pre-trained text-to-speech models made embarrassingly simple

Category
multimodal media
Stars
6,054
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +21 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

armenian azerbaijani belarus colab georgian kazakh

OpenWhispr/openwhispr

Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

Category
multimodal media
Stars
5,260
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +195 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai anthropic cross-platform gemini groq linux

liuzhao1225/YouDub-webui

开源 AI 视频本地化工具：自动完成 YouTube/Bilibili 视频下载、字幕识别与翻译、语音克隆配音、音轨混合和字幕压制。

Category
multimodal media
Stars
5,250
Readiness
ready (77/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +36 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-dubbing bilibili demucs fastapi ffmpeg nextjs

tmoroney/auto-subs

On-device subtitle generation that connects directly to DaVinci Resolve, Premiere, and After Effects.

Category
multimodal media
Stars
3,982
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +38 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai cross-platform davinci davinci-resolve premiere resolve

SakiRinn/LiveCaptions-Translator

Lightweight and powerful real-time audio/speech translation tool based on Windows LiveCaptions.

Category
multimodal media
Stars
3,466
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +41 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

api api-integration audio-to-text livecaptions real-time speech-to-text

HeyWillow/willow

Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative

Category
multimodal media
Stars
3,086
Readiness
ready (87/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

alexa deep-learning echo esp-adf esp-idf esp32

pluja/whishper

Transcribe any audio to text, translate and edit subtitles 100% locally with a web UI. Powered by whisper models!

Category
multimodal media
Stars
3,052
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai audio-to-text golang speech-recognition speech-to-text stt

FluidInference/FluidAudio

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

Category
multimodal media
Stars
2,628
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +55 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ane asr audio automatic-speech-recognition avfoundation coreml

microsoft/foundry-local

No description

Category
multimodal media
Stars
2,497
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +15 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-sdk chat-completions foundry-local gpu-acceleration local-ai microsoft

iamsrikanthnani/pluely

The Open Source Alternative to Cluely - A lightning-fast, privacy-first AI assistant that works seamlessly during meetings, interviews, and conversations without anyone knowing. Built with Tauri for n

Category
multimodal media
Stars
2,377
Readiness
ready (74/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +21 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-assistant claude cluely-alternative desktop-app gemini grok

handy-computer/transcribe.cpp

ggml speech-to-text inference for 16+ model families

Category
multimodal media
Stars
1,712
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +58 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr ggml gguf speech-to-text

TypeWhisper/typewhisper-mac

Local speech-to-text for macOS on-device AI, fully private, optional cloud

Category
multimodal media
Stars
1,675
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +21 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

apple-silicon dictation macos on-device privacy speech-to-text

mkiol/dsnote

Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.

Category
multimodal media
Stars
1,557
Readiness
needs review (71/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr flatpak-applications linux-desktop machine-translation nmt offline

AlekPet/ComfyUI_Custom_Nodes_AlekPet

Custom nodes that extend the capabilities of Comfyui

Category
multimodal media
Stars
1,520
Readiness
ready (84/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

glm ide painter pose-detection speech-recognition speech-synthesis

goodroot/hyprwhspr

Native speech-to-text for Linux - Fast, accurate, private, and hackable system-wide dictation

Category
multimodal media
Stars
1,136
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +14 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai archlinux cachyos cohere-ai debian dictation

peteonrails/voxtype

Voice-to-text with push-to-talk for Wayland compositors

Category
multimodal media
Stars
1,050
Readiness
ready (89/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +20 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

accessibility dictation gnome hyprland kde linux

PatterAI/Patter

Open-source voice-AI SDK. The Vapi/Retell alternative for builders who want to own the stack. Give your AI agent a phone number in 4 lines — Python and TypeScript, MIT licensed, Twilio, Telnyx, and Pl

Category
multimodal media
Stars
1,026
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-agent ai-phone-agent hermes-agent llm mastra open-source

TensorSpeech/TensorFlowASR

:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords

Category
multimodal media
Stars
1,010
Readiness
ready (97/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

automatic-speech-recognition conformer contextnet ctc deepspeech2 end2end

voquill/voquill

Open source voice dictation technology

Category
multimodal media
Stars
998
Readiness
ready (80/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

agent agentic-ai dictation free local-ai open-source

Kieirra/murmure

Fully local, private and cross platform Speech-to-Text with LLM Post-processing

Category
multimodal media
Stars
990
Readiness
ready (82/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +9 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr asr-model debian-packages linux macos privacy

sandrohanea/whisper.net

Whisper.net. Speech to text made simple using Whisper Models

Category
multimodal media
Stars
940
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

cross-platform dotnet dotnetcore speech-recognition speech-to-text translation

VladislavAntonyuk/MauiSamples

.NET MAUI Samples

Category
multimodal media
Stars
915
Readiness
ready (85/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

azure blazor dotnet dotnet-maui dotnet-maui-blazor hacktoberfest

backmeupplz/voicy

@voicybot Telegram bot main repository

Category
multimodal media
Stars
906
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

bot speech-to-text telegam telegram-bot

techjarves/Uncensored-Local-Studio

Uncensored local AI studio for Windows, Linux, and macOS. Zero-setup GUI for Image Generation, GGUF LLMs, Text to Speech & Speech to Text

Category
multimodal media
Stars
835
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +69 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

image-generation speech-to-text text-generation text-to-speech

dimastatz/whisper-flow

Whisper-Flow is a framework designed to enable real-time transcription of audio content using OpenAI’s Whisper model. Rather than processing entire files after upload (“batch mode”), Whisper-Flow acce

Category
multimodal media
Stars
822
Readiness
ready (93/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

pypi-package python speech-to-text transcription whisper

corvo007/MioSub

一站式全自动字幕生成软件，下载、转录、翻译、压制全流程覆盖，无需人工介入 / One-stop automated subtitle generator. Handles downloading, transcription, translation, and hardcoding—zero human intervention required.

Category
multimodal media
Stars
791
Readiness
needs review (69/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +20 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

alignment ass-subtitles captions diarization ffmpeg forced-alignment

Blaizzy/mlx-audio-swift

A modular Swift SDK for audio processing with MLX on Apple Silicon

Category
multimodal media
Stars
749
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

mlx mlx-audio mlx-audio-swift mlx-swift-audio speech-to-speech speech-to-text

EmulationAI/awesome-large-audio-models

Collection of resources on the applications of Large Language Models (LLMs) in Audio AI.

Category
multimodal media
Stars
735
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

audio-ai audio-processing automatic-speech-recognition foundational-models large-audio-models large-language-model-speech

BryceWG/BiBi-Keyboard

说点啥（BiBi Keyboard）:一个基于 Kotlin 的 Android 平台的 LLM 与 ASR 语音输入法键盘应用 An LLM ASR voice input method keyboard application for the Android platform based on Kotlin

Category
multimodal media
Stars
731
Readiness
ready (90/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

android-app asr doubao elevenlabs keyboard kotlin

VocaHQ/vocalinux

Free, open-source, 100% offline voice dictation for Linux. Speak and type anywhere via whisper.cpp, Whisper & VOSK engines, GPU-accelerated, works on X11 + Wayland!

Category
multimodal media
Stars
722
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

accessibility dictation gpu-acceleration linux offline-first privacy-first

zh-plus/openlrc

Transcribe and translate voice into LRC file using Whisper and LLMs (GPT, Claude, et,al). 使用whisper和LLM(GPT，Claude等)来转录、翻译你的音频为字幕文件。

Category
multimodal media
Stars
672
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

auto-subtitle faster-whisper lyrics lyrics-generator openai-api openlrc

Picovoice/cheetah

On-device streaming speech-to-text engine powered by deep learning

Category
multimodal media
Stars
670
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr automatic-speech-recognition online-speech-recognition speech-recognition speech-to-text streaming-speech-to-text

jamsch/expo-speech-recognition

Speech Recognition for React Native Expo projects

Category
multimodal media
Stars
666
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +8 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

expo react-native speech-recognition speech-to-text voice-recognition

watzon/pindrop

A native macOS menu bar dictation app using local speech-to-text with WhisperKit

Category
multimodal media
Stars
584
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

apple-silicon dictation macos menu-bar open-source privacy

Xewdy444/Playwright-reCAPTCHA

A Python library for solving reCAPTCHA v2 and v3 with Playwright

Category
multimodal media
Stars
562
Readiness
ready (91/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asyncio library playwright recaptcha solver speech-to-text

VolcanicArts/VRCOSC

A modular node-programming language, program creator, animation system, toolkit, router, and debugger made for VRChat

Category
multimodal media
Stars
558
Readiness
ready (83/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

chatbox haptics heartrate media node-programing osc

moona3k/macparakeet

Fast, private, local-first voice app for Apple Silicon Macs — dictation, file/media transcription, meeting recording, Transforms, and a public automation CLI. Free and open-source.

Category
multimodal media
Stars
545
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +17 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

apple-silicon dictation local-first macos meeting-recording neural-engine

CrispStrobe/CrispASR

C++ ggml runtime hub for multilingual ASR and TTS models: Cohere Transcribe, Parakeet TDT, Voxtral, Canary 1B v2, etc, plus universal forced alignment, and more

Category
multimodal media
Stars
519
Readiness
ready (95/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +23 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

cohere-transcribe cohere-transcribe-03-2026 ggml parakeet speech-recognition speech-to-text

bugbakery/transcribee

open source audio and video transcription software

Category
multimodal media
Stars
509
Readiness
ready (72/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

collaborative speech-to-text transcription

Picovoice/leopard

On-device speech-to-text engine powered by deep learning

Category
multimodal media
Stars
482
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
0/100 · high confidence

Why: 12 lifetime contributors

Why it may be a gem: open issue backlog is stable or shrinking

Strongest signals: push recency, contributor breadth, issue load. Risks: None identified. Missing inputs: None.

asr automatic-speech-recognition on-device speech-recognition speech-to-text stt

deepgram/deepgram-python-sdk

Official Python SDK for Deepgram.

Category
multimodal media
Stars
456
Readiness
ready (81/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
8/100 · high confidence

Why: +3 stars in 7 days; 45 lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, contributor breadth, issue load. Risks: no pull-request review responses in 30 days. Missing inputs: None.

asr automated-speech-recognition deepgram python speech-recognition speech-to-text

jim60105/docker-whisperX

Dockerfile for WhisperX: Automatic Speech Recognition with Word-Level Timestamps and Speaker Diarization (Dockerfile, CI image build and test)

Category
multimodal media
Stars
454
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
medium
Maintainer health
healthy
Maintenance risk
18/100 · high confidence

Why: 6 lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: issue load, documentation, license. Risks: recent commit cadence is 1/4.2 of its monthly baseline. Missing inputs: release recency.

asr docker-image dockerfile speech speech-recognition speech-to-text

echogarden-project/echogarden

Cross-platform speech toolset, used from the command-line or as a Node.js library. Includes a variety of engines for speech synthesis, speech recognition, forced alignment, speech translation, voice i

Category
multimodal media
Stars
447
Readiness
needs review (60/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
8/100 · high confidence

Why: +2 stars in 7 days; 12 commits in 30 days

Why it may be a gem: open issue backlog is stable or shrinking

Strongest signals: push recency, issue load, documentation. Risks: no pull-request review responses in 30 days. Missing inputs: None.

command-line forced-alignment language-detection language-identification node-js source-separation

tover0314-w/opentypeless

Open-source AI voice typing for macOS, Windows, and Linux. Press a hotkey, speak naturally, get polished text in any app.

Category
multimodal media
Stars
438
Readiness
ready (78/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
healthy
Maintenance risk
8/100 · high confidence

Why: +27 stars in 7 days; 48 commits in 30 days

Why it may be a gem: healthy maintenance and project fundamentals; consistent human and community activity

Strongest signals: push recency, commit activity, issue load. Risks: no pull-request review responses in 30 days. Missing inputs: None.

ai ai-tools byok cross-platform desktop-app dictation

misyaguziya/VRCT

VRCT(VRChat Chatbox Translator & Transcription)

Category
multimodal media
Stars
417
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

osc speech-recognition speech-to-text vrchat

agan-j/xiaoniu

小牛视频翻译 是一款支持本地视频翻译、字幕翻译和 YouTube 视频翻译下载的 AI 工具，集成自动语音识别与多语言翻译功能，助力创作者高效完成视频翻译，应用于视频本地化与视频出海场景。

Category
multimodal media
Stars
392
Readiness
ready (76/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-subtitles asr multilingual speech-recognition speech-to-text subtitle-translation

altunenes/parakeet-rs

very fast speech-to-text, diarization, streaming (even in CPU) with NVIDIA Parakeet in Rust

Category
multimodal media
Stars
381
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr automatic-speech-recognition onnx parakeet speaker-diarization speaker-identification

kstonekuan/tambourine-voice

Your personal voice interface for any app. Speak naturally and your words appear wherever your cursor is, with fully customizable AI voice dictation. Open source alternative to Wispr Flow.

Category
multimodal media
Stars
374
Readiness
ready (74/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

accessibility cross-platform macos pipecat python rust

istupakov/onnx-asr

A lightweight Python package for Automatic Speech Recognition using ONNX models

Category
multimodal media
Stars
358
Readiness
ready (88/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr lightweight onnx parakeet python speech-recognition

PunithVT/ai-avatar-system

🎭 AI Avatar / digital human platform — upload a photo, clone a voice, talk to any face in real time with lip-sync video. Open-source, self-hosted. Claude · Whisper · Chatterbox · MuseTalk.

Category
multimodal media
Stars
355
Readiness
ready (92/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, fork interest. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-avatar avatar-ai chatterbox-tts claude-ai digital-human fastapi

mozilla/DeepSpeech

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

Category
multimodal media
Stars
26,771
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
risky
Maintenance risk
100/100 · high confidence

Why: 100+ lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: contributor breadth, issue load, documentation. Risks: repository is archived, no push in 414 days, latest release is 2057 days old, 151 open issues with no maintainer issue responses in 30 days, no pull-request review responses in 30 days, no maintainer response activity in 30 days. Missing inputs: None.

Capped lower bounds: lifetime contributors.

deep-learning deepspeech embedded machine-learning neural-networks offline

SYSTRAN/faster-whisper

Faster Whisper transcription with CTranslate2

Category
multimodal media
Stars
24,804
Readiness
needs review (46/100 heuristic points; not a probability)
Data confidence
high
Maintainer health
risky
Maintenance risk
38/100 · high confidence

Why: +139 stars in 7 days; 46 lifetime contributors

Why it may be a gem: healthy maintenance and project fundamentals; open issue backlog is stable or shrinking

Strongest signals: contributor breadth, issue load, documentation. Risks: no push in 261 days, no pull-request review responses in 30 days. Missing inputs: None.

deep-learning inference openai quantization speech-recognition speech-to-text

kaldi-asr/kaldi

kaldi-asr/kaldi is the official location of the Kaldi project.

Category
multimodal media
Stars
15,450
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 319 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

c-plus-plus cuda kaldi shell speaker-id speaker-verification

alphacep/vosk-api

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

Category
multimodal media
Stars
15,030
Readiness
needs review (70/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +11 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

android asr deep-learning deep-neural-networks deepspeech google-speech-to-text

KoljaB/RealtimeSTT

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

Category
multimodal media
Stars
10,042
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +19 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

python realtime speech-to-text

nl8590687/ASRT_SpeechRecognition

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

Category
multimodal media
Stars
8,380
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
20/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 119 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asrt chinese-speech-recognition cnn ctc keras python

MahmoudAshraf97/whisper-diarization

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

Category
multimodal media
Stars
5,616
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
27/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 165 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr speaker-diarization speech speech-recognition speech-to-text whisper

jianchang512/stt

Voice Recognition to Text Tool / 一个离线运行的本地音视频转字幕工具，输出json、srt字幕、纯文字格式

Category
multimodal media
Stars
4,730
Readiness
high risk (43/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +15 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 197 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

speech speech-recognition speech-to-text stt

sanchit-gandhi/whisper-jax

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

Category
multimodal media
Stars
4,683
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 856 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

deep-learning jax speech-recognition speech-to-text whisper

gradio-app/fastrtc

The python library for real-time communication

Category
multimodal media
Stars
4,620
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 207 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence hacktoberfest hacktoberfest2025 llm python real-time

ahmetoner/whisper-asr-webservice

OpenAI Whisper ASR Webservice API

Category
multimodal media
Stars
3,315
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 257 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr automatic-speech-recognition docker openai-whisper speech speech-recognition

BayLing-Models/BayLing-Speech

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

Category
multimodal media
Stars
3,145
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 445 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

large-language-models multimodal-large-language-models speech-interaction speech-language-model speech-to-speech speech-to-text

Purfview/whisper-standalone-win

Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python.

Category
multimodal media
Stars
3,141
Readiness
high risk (40/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 273 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr ctranslate2 diarization faster-whisper openai speaker-diarization

tensorflow/lingvo

Lingvo

Category
multimodal media
Stars
2,862
Readiness
needs review (65/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr distributed gpu-computing language-model lm machine-translation

coqui-ai/STT

🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

Category
multimodal media
Stars
2,602
Readiness
needs review (46/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 879 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr automatic-speech-recognition deep-learning speech-recognition speech-recognition-api speech-recognizer

sindresorhus/awesome-whisper

🔊 Awesome list for Whisper — an open-source AI-powered speech recognition system developed by OpenAI

Category
multimodal media
Stars
2,367
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai artificial-intelligence awesome awesome-list gpt openai

yan5xu/ququ

开源免费的 Wispr Flow 替代方案 | 集成FunASR本地模型和可配置大语言模型的下一代中文桌面语音工作流

Category
multimodal media
Stars
2,256
Readiness
needs review (46/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 303 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-text-processing chinese-speech-recognition electron-app funasr local-processing open-source

pannous/tensorflow-speech-recognition

🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks

Category
multimodal media
Stars
2,173
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 933 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

deep-learning neural-network speech-recognition speech-to-text stt tensorflow

jarikomppa/soloud

Free, easy, portable audio engine for games

Category
multimodal media
Stars
2,143
Readiness
needs review (48/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: issue load, documentation. Risks: no push in 724 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

audio blitzmax c cpp engine flac

meizhong986/WhisperJAV

ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV

Category
multimodal media
Stars
2,089
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +20 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

aitranslate hallucination japanese llm modelscope qwen3

ricky0123/vad

Voice activity detector (VAD) for the browser with a simple API

Category
multimodal media
Stars
2,034
Readiness
needs review (47/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +9 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 189 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

onnxruntime silero-vad speech-to-text typescript voice-activity-detection web

bugbakery/audapolis

an editor for spoken-word audio with automatic transcription

Category
multimodal media
Stars
1,881
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

audio-editing speech-to-text transcription video-editing

mesolitica/NLP-Models-Tensorflow

Gathers machine learning and Tensorflow deep learning models for NLP problems, 1.13 < Tensorflow < 2.0

Category
multimodal media
Stars
1,781
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
100/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: repository is archived, no push in 2209 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

attention chatbot deep-learning dnc-seq2seq embedded language-detection

kalliope-project/kalliope

Kalliope is a framework that will help you to create your own personal assistant.

Category
multimodal media
Stars
1,768
Readiness
needs review (47/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 1132 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

bot bot-creation home-automation jarvis linux personal-assistant

Olcmyk/HuChenFeng

收集户晨风的所有内容

Category
multimodal media
Stars
1,637
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
29/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 171 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

archiving content-analysis datasets internet-culture livestream social-media

royshil/obs-localvocal

OBS plugin for local speech recognition and captioning using AI

Category
multimodal media
Stars
1,569
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +7 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai live-streaming livestream obs obs-studio obs-studio-plugin

NVIDIA/OpenSeq2Seq

Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP

Category
multimodal media
Stars
1,558
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
100/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: repository is archived, no push in 1914 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

deep-learning float16 language-model mixed-precision multi-gpu multi-node

DragonComputer/Dragonfire

the open-source virtual assistant for Ubuntu based Linux distributions

Category
multimodal media
Stars
1,407
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1355 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

artificial-intelligence chatbot kaldi linux machine-learning nlp

R3gm/SoniTranslate

Synchronized Translation for Videos. Video dubbing

Category
multimodal media
Stars
1,403
Readiness
needs review (60/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
17/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 102 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr audio-processing automatic-dubbing diarization document-translator dubbing

coqui-ai/open-speech-corpora

💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies

Category
multimodal media
Stars
1,398
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 792 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

speech-emotion-recognition speech-processing speech-recognition speech-separation speech-synthesis speech-to-text

Softcatala/whisper-ctranslate2

Whisper command line client compatible with original OpenAI client based on CTranslate2.

Category
multimodal media
Stars
1,336
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
29/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 174 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

openai- openai-whisper speech-recognition speech-to-text whisper

ictnlp/StreamSpeech

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

Category
multimodal media
Stars
1,280
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 404 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

all-in-one asr audio-processing machine-translation non-autoregressive seamless

sdkcarlos/artyom.js

A voice control - voice commands - speech recognition and speech synthesis javascript library. Create your own siri,google now or cortana with Google Chrome within your website.

Category
multimodal media
Stars
1,269
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 1291 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

recognition speech-recognition speech-synthesis speech-to-text voice-commands

modal-labs/quillman

A voice chat app

Category
multimodal media
Stars
1,213
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai language-model python serverless speech-recognition speech-to-text

Kyubyong/dc_tts

A TensorFlow Implementation of DC-TTS: yet another text-to-speech model

Category
multimodal media
Stars
1,156
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, license. Risks: no push in 1211 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

speech speech-to-text tts

ardha27/AI-Waifu-Vtuber

AI Vtuber for Streaming on Youtube/Twitch

Category
multimodal media
Stars
1,109
Readiness
needs review (45/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +4 stars in 7 days

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-vtuber ai-waifu deepl openai speech-recognition speech-synthesis

Saik0s/Whisperboard

The open-source iOS app that's making quality voice transcription more accessible on mobile devices.

Category
multimodal media
Stars
1,089
Readiness
needs review (46/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 232 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

audio-to-text composable-architecture ios openai speech-recognition speech-to-text

savbell/whisper-writer

💬📝 A small dictation app using OpenAI's Whisper speech recognition model.

Category
multimodal media
Stars
1,089
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 713 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

dictation faster-whisper openai openai-api openai-whisper speech-recognition

alesaccoia/VoiceStreamAI

Near-Realtime audio transcription using self-hosted Whisper and WebSocket in Python/JS

Category
multimodal media
Stars
960
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 674 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai speech-recognition speech-to-text websocket

codeforequity-at/botium-speech-processing

Botium Speech Processing

Category
multimodal media
Stars
943
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

botium speech-to-text text-to-speech

jitsi/jiwer

Evaluate your speech-to-text system with similarity measures such as word error rate (WER)

Category
multimodal media
Stars
922
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
19/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 113 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

automatic-speech-recognition evaluation-metrics python3 speech-to-text wer word-error-rate

mikeyy/nonoCAPTCHA

An asynchronized Python library to automate solving ReCAPTCHA v2 using audio

Category
multimodal media
Stars
894
Readiness
needs review (49/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 1156 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asyncio python recaptcha speech-to-text

marswaveai/TypeNo

A free, open source, privacy-first voice input app for macOS.

Category
multimodal media
Stars
886
Readiness
needs review (45/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: +6 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

accessibility dictation local-first macos menu-bar-app open-source

yeyupiaoling/PPASR

基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型

Category
multimodal media
Stars
872
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 233 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr chinese conformer deep-learning deepspeech2 paddlepaddle

JamesBrill/react-speech-recognition

💬Speech recognition for your React app

Category
multimodal media
Stars
842
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, license. Risks: no push in 427 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

react speech-recognition speech-to-text

saharmor/whisper-playground

Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/

Category
multimodal media
Stars
834
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 329 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

machine-learning openai speech-recognition speech-to-text whisper

srvk/eesen

The official repository of the Eesen project

Category
multimodal media
Stars
834
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 2633 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr ctc ctc-loss kaldi speech-recognition speech-to-text

snakers4/open_stt

Open STT

Category
multimodal media
Stars
826
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
100/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: issue load, documentation. Risks: repository is archived, no push in 1610 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr automatic-speech-recognition dataset russian speech-to-text stt

deepgram/kur

Descriptive Deep Learning

Category
multimodal media
Stars
824
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 914 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

deep-learning deep-learning-tutorial deep-neural-networks image-recognition machine-learning neural-network

lobehub/lobe-tts

🎤 Lobe TTS - A high-quality & reliable TTS/STT library for Server and Browser

Category
multimodal media
Stars
800
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
26/100 · low confidence

Why: +2 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 158 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

auzre bun edge lobehub microsoft-speech-api nodejs

SlapBot/stephanie-va

Stephanie is an open-source platform built specifically for voice-controlled applications as well as to automate daily tasks imitating much of an virtual assistant's work.

Category
multimodal media
Stars
797
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 2756 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

intent-prediction personal-assistant python speech-recognition speech-to-text stephanie

VRCWizard/TTS-Voice-Wizard

Speech to Text to Speech. Song now playing. Sends text as OSC messages to VRChat to display on avatar. (STTTS) (Speech to TTS) (VRC STT System) (VTuber TTS)

Category
multimodal media
Stars
795
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
watch
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

chatbox discord free heart-rate osc speech-recognition

mallorbc/whisper_mic

Project that allows one to use a microphone with OpenAI whisper.

Category
multimodal media
Stars
788
Readiness
needs review (60/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 764 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

microphone speech-recognition speech-to-text whisper whisper-ai whisper-api

mezbaul-h/june

Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit

Category
multimodal media
Stars
788
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 725 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai assistant-chat-bots chatbot chatbots cli-app command-line-tool

exPHAT/SwiftWhisper

🎤 The easiest way to transcribe audio in Swift

Category
multimodal media
Stars
784
Readiness
needs review (56/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 806 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ios macos openai speech-recognition speech-to-text swift

Notely-Voice/NotelyVoice

A 100% private AI voice transcription app that converts speech to text in 100+ languages. Built with Compose Multiplatform for Android & iOS using Whisper AI - no cloud uploads, all processing happens

Category
multimodal media
Stars
766
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +5 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

android audio-player compose-ios compose-multiplatform compose-multiplatform-sample ios

yeyupiaoling/PaddlePaddle-DeepSpeech

基于PaddlePaddle实现的语音识别，中文语音识别。项目完善，识别效果好。支持Windows，Linux下训练和预测，支持Nvidia Jetson开发板预测。

Category
multimodal media
Stars
762
Readiness
needs review (59/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 233 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr chinese deep-learning deepspeech deepspeech2 docker

Macoron/whisper.unity

Running speech to text model (whisper.cpp) in Unity3d on your local machine.

Category
multimodal media
Stars
750
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 477 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr openai speech-recognition speech-to-text stt unity3d

yeyupiaoling/MASR

Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。

Category
multimodal media
Stars
729
Readiness
ready (75/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr conformer deep-learning deepspeech pytorch speech

soupslurpr/Transcribro

Private and on-device speech recognition keyboard and service for Android.

Category
multimodal media
Stars
729
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 343 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

android jetpack-compose keyboard kotlin kotlin-android material-3

MycroftAI/adapt

Adapt Intent Parser

Category
multimodal media
Stars
718
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 747 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

intent-parser intents open-source opensource speech-recognition speech-to-text

mmpneo/curses

Speech to Text and KB input captions for OBS, VRChat, Twitch chat and Discord

Category
multimodal media
Stars
714
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 780 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

captions obs speech-recognition speech-to-text tauri text-to-speech

Baidu-AIP/speech-demo

语音api示例

Category
multimodal media
Stars
709
Readiness
needs review (47/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: limited evidence; inspect maintenance signals before adopting

Strongest signals: issue load, fork interest, documentation. Risks: no push in 743 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

baidu rest-api speech-recognition speech-to-text

googleapis/nodejs-speech

This repository is deprecated. All of its content and history has been moved to googleapis/google-cloud-node.

Category
multimodal media
Stars
682
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
100/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: repository is archived, no push in 1121 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

machine-learning nodejs speech speech-to-text

abhirooptalasila/AutoSub

A CLI script to generate subtitle files (SRT/VTT/TXT) for any video using either DeepSpeech or Coqui

Category
multimodal media
Stars
651
Readiness
high risk (0/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
100/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: repository is archived, no push in 957 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr autosub coqui-ai deepspeech ffmpeg mozilla-deepspeech

evancohen/sonus

:speech_balloon: /so.nus/ STT (speech to text) for Node with offline hotword detection

Category
multimodal media
Stars
638
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 766 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

alexa hotword-detection keyword-spotting node speech speech-recognition

vardanagarwal/Proctoring-AI

Creating a software for automatic monitoring in online proctoring

Category
multimodal media
Stars
631
Readiness
needs review (62/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 605 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

automation dlib eye-tracking face-detection face-spoofing hacktoberfest

reriiasu/speech-to-text

Real-time transcription using faster-whisper

Category
multimodal media
Stars
614
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 745 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

faster-whisper openai speech-recognition speech-to-text voice-recognition whisper

ElishaAz/Sayboard

An open-source on-device voice IME (keyboard) for Android using the Vosk library.

Category
multimodal media
Stars
578
Readiness
high risk (42/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 402 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

android input-method-editor keyboard speech-to-text speech-to-text-android vosk

shashikg/WhisperS2T

An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine

Category
multimodal media
Stars
577
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 710 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr deep-learning speech-recognition speech-to-text tensorrt tensorrt-llm

algolia/voice-overlay-ios

🗣 An overlay that gets your user’s voice permission and input as text in a customizable UI

Category
multimodal media
Stars
556
Readiness
needs review (64/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

chatbots conversation conversational-bots conversational-interface conversational-ui input

lkuza2/java-speech-api

The J.A.R.V.I.S. Speech API is designed to be simple and efficient, using the speech engines created by Google to provide functionality for parts of the API. Essentially, it is an API written in Java,

Category
multimodal media
Stars
542
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 2655 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

api google jarvis java recognition speech

rtzr/Awesome-Korean-Speech-Recognition

한국어 음성인식 STT API 리스트. 각 성능 벤치마크.

Category
multimodal media
Stars
540
Readiness
high risk (44/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
0/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

awesome korean speech-recognition speech-to-text speech-to-text-api whisper

YoavRamon/awesome-kaldi

This is a list of features, scripts, blogs and resources for better using Kaldi ( http://kaldi-asr.org/ )

Category
multimodal media
Stars
536
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1640 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

automatic-speech-recognition awesome-list kaldi kaldi-asr speech speech-recognition

ccoreilly/vosk-browser

A speech recognition library running in the browser thanks to a WebAssembly build of Vosk

Category
multimodal media
Stars
527
Readiness
needs review (57/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 243 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr kaldi speech-recognition speech-to-text stt typescript

AdolfVonKleist/Phonetisaurus

Phonetisaurus G2P

Category
multimodal media
Stars
518
Readiness
needs review (61/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 797 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

g2p lexicon openfst pronunciation-dictionary speech-recognition speech-to-text

Thiagohgl/ai-pronunciation-trainer

This tool uses AI to evaluate your pronunciation.

Category
multimodal media
Stars
512
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +3 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 356 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai language-learning pronunciation speech-recognition speech-to-text

toverainc/willow-inference-server

Open source, local, and self-hosted highly optimized language inference server supporting ASR/STT, TTS, and LLM across WebRTC, REST, and WS

Category
multimodal media
Stars
510
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
29/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 176 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

cuda deep-learning llama llm privacy speech-recognition

alphacep/vosk

VOSK Speech Recognition Toolkit

Category
multimodal media
Stars
501
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1486 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

lifelong-learning multilingual python semi-supervised-learning speech-recognition speech-to-text

Kyubyong/css10

CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages

Category
multimodal media
Stars
491
Readiness
needs review (51/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, license. Risks: no push in 2345 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

dataset speech speech-to-text

Evil0ctal/Fast-Powerful-Whisper-AI-Services-API

⚡ 一款用于自动语音识别 (ASR)、翻译的高性能异步 API。不需要购买Whisper API，使用本地运行的Whisper模型进行推理，并支持多GPU并发，针对分布式部署进行设计。还内置了包括TikTok、抖音等社交媒体平台的爬虫，可实现来自多个社交平台的无缝媒体处理，为媒体内容数据自动化处理提供了强大且可扩展的解决方案。

Category
multimodal media
Stars
470
Readiness
needs review (55/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 416 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr crawler douyin-api fastapi faster-whisper openai-whisper

hackingbeauty/react-mic

Record audio from a user's microphone and display a cool visualization.

Category
multimodal media
Stars
470
Readiness
needs review (48/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, fork interest, documentation. Risks: no push in 621 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

audio-recorder audio-visualizer microphone mp3-audio reactjs record-audio

jonatasgrosman/huggingsound

HuggingSound: A toolkit for speech-related tasks based on Hugging Face's tools

Category
multimodal media
Stars
468
Readiness
needs review (53/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 1053 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr audio automatic-speech-recognition speech speech-recognition speech-to-text

double22a/speech_dataset

The dataset of Speech Recognition

Category
multimodal media
Stars
466
Readiness
needs review (58/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 215 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr audio automatic-speech-recognition dataset deep-learning deep-neural-networks

OpenNewsLabs/autoEdit_2

Fast text based video editing, node Electron Os X desktop app, with Backbone front end.

Category
multimodal media
Stars
455
Readiness
needs review (54/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 887 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

autoedit backbone backbonejs desktop dmg edl

modelscope/FunCodec

FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.

Category
multimodal media
Stars
446
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: +1 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 925 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

audio-generation audio-quantization codec encodec speech-synthesis speech-to-text

egorsmkv/speech-recognition-uk

🇺🇦 Speech Recognition & Synthesis for Ukrainian

Category
multimodal media
Stars
439
Readiness
high risk (39/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation. Risks: no push in 329 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

speech speech-recognition speech-synthesis speech-to-text text-to-speech tts

revdotcom/reverb

Open source inference code for Rev's model

Category
multimodal media
Stars
436
Readiness
needs review (52/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
risky
Maintenance risk
30/100 · low confidence

Why: High-signal multimodal media project

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: issue load, documentation, license. Risks: no push in 472 days. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

asr asr-model canary deeplearning diarization docker

backblaze-labs/genblaze

Genblaze is an open source Python SDK for orchestrating generative AI media pipelines across video, audio, and image providers with built in provenance for every output.

Category
multimodal media
Stars
564
Readiness
ready (86/100 heuristic points; not a probability)
Data confidence
low
Maintainer health
healthy
Maintenance risk
0/100 · low confidence

Why: +65 stars in 7 days

Why it may be a gem: healthy maintenance and project fundamentals

Strongest signals: push recency, issue load, documentation. Risks: None identified. Missing inputs: commit activity, contributor breadth, release recency, response activity, maintenance distribution.

ai-pipeline audio-generation b2-labs backblaze backblaze-b2 data-pipeline