# 11 · 完整项目清单（118 个）

> 数据快照：2026-11-03 · 来源 GitHub 仓库（API + 页面解析）

> ★ 为 star 数；协议中「自定义」= 非标准 OSI 许可，「未声明」= 仓库无 LICENSE 文件


## 基座模型（29）

*文生视频 / 图生视频 / 视频编辑*

| 项目 | ★ | 协议 | 最近提交 | 说明 |
|---|---:|---|---|---|
| [hpcaitech/Open-Sora](https://github.com/hpcaitech/Open-Sora) | 29902 | Apache-2.0 | 2026-04-09 | Open-Sora: Democratizing Efficient Video Production for All |
| [Stability-AI/generative-models](https://github.com/Stability-AI/generative-models) | 27318 | MIT | 2025-12-16 | Generative Models by Stability AI |
| [Wan-Video/Wan2.2](https://github.com/Wan-Video/Wan2.2) | 18335 | Apache-2.0 | 2026-09-21 | Wan: Open and Advanced Large-Scale Video Generative Models |
| [Wan-Video/Wan2.1](https://github.com/Wan-Video/Wan2.1) | 17366 | Apache-2.0 | 2026-03-05 | Wan: Open and Advanced Large-Scale Video Generative Models |
| [lllyasviel/FramePack](https://github.com/lllyasviel/FramePack) | 17340 | Apache-2.0 | 2025-10-16 | Lets make video diffusion practical! |
| [modelscope/DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) | 13336 | Apache-2.0 | 2026-11-03 | Enjoy the magic of Diffusion models! |
| [zai-org/CogVideo](https://github.com/zai-org/CogVideo) | 13175 | Apache-2.0 | 2025-11-04 | text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023) |
| [Tencent-Hunyuan/HunyuanVideo](https://github.com/Tencent-Hunyuan/HunyuanVideo) | 12714 | 自定义 | 2026-10-08 | HunyuanVideo: A Systematic Framework For Large Video Generation Model |
| [guoyww/AnimateDiff](https://github.com/guoyww/AnimateDiff) | 12283 | Apache-2.0 | 2024-07-31 | Official implementation of AnimateDiff. |
| [PKU-YuanGroup/Open-Sora-Plan](https://github.com/PKU-YuanGroup/Open-Sora-Plan) | 12203 | MIT | 2026-03-08 | This project aim to reproduce Sora (Open AI T2V model), we wish the open sou… |
| [Lightricks/LTX-Video](https://github.com/Lightricks/LTX-Video) | 11286 | Apache-2.0 | 2026-11-02 | Official repository for LTX-Video |
| [SkyworkAI/SkyReels-V2](https://github.com/SkyworkAI/SkyReels-V2) | 7753 | 自定义 | 2026-01-29 | SkyReels-V2: Infinite-length Film Generative model |
| [Tencent-Hunyuan/HunyuanVideo-1.5](https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5) | 4590 | 自定义 | 2026-04-10 | HunyuanVideo-1.5: A leading lightweight video generation model |
| [ali-vilab/VACE](https://github.com/ali-vilab/VACE) | 4046 | Apache-2.0 | 2025-10-17 | [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creat… |
| [SandAI-org/MAGI-1](https://github.com/SandAI-org/MAGI-1) | 3798 | Apache-2.0 | 2026-06-17 | MAGI-1: Autoregressive Video Generation at Scale |
| [genmoai/mochi](https://github.com/genmoai/mochi) | 3761 | Apache-2.0 | 2026-10-22 | The best OSS video generation models, created by Genmo |
| [stepfun-ai/Step-Video-T2V](https://github.com/stepfun-ai/Step-Video-T2V) | 3189 | MIT | 2025-03-17 |  |
| [ali-vilab/VGen](https://github.com/ali-vilab/VGen) | 3153 | 未声明 | 2025-01-10 | Official repo for VGen: a holistic video generation ecosystem for video gene… |
| [SkyworkAI/SkyReels-V1](https://github.com/SkyworkAI/SkyReels-V1) | 2702 | 自定义 | 2025-03-10 | SkyReels V1: The first and most advanced open-source human-centric video fou… |
| [aigc-apps/EasyAnimate](https://github.com/aigc-apps/EasyAnimate) | 2266 | Apache-2.0 | 2025-03-06 | 📺 An End-to-End Solution for High-Resolution and Long Video Generation Based… |
| [Tencent-Hunyuan/HunyuanVideo-I2V](https://github.com/Tencent-Hunyuan/HunyuanVideo-I2V) | 1853 | 自定义 | 2026-04-07 | HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo |
| [Tencent-Hunyuan/HunyuanCustom](https://github.com/Tencent-Hunyuan/HunyuanCustom) | 1232 | 自定义 | 2025-10-15 | HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generat… |
| [rhymes-ai/Allegro](https://github.com/rhymes-ai/Allegro) | 1137 | Apache-2.0 | 2025-02-07 | Allegro is a powerful text-to-video model that generates high-quality videos… |
| [FoundationVision/Waver](https://github.com/FoundationVision/Waver) | 955 | 未声明 | 2025-08-27 | Industry-level video foundation model for unified Text-to-Video (T2V) and Im… |
| [Vchitect/Vchitect-2.0](https://github.com/Vchitect/Vchitect-2.0) | 921 | Apache-2.0 | 2025-03-17 | Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models |
| [PKU-YuanGroup/ConsisID](https://github.com/PKU-YuanGroup/ConsisID) | 863 | Apache-2.0 | 2026-04-14 | [CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequ… |
| [kandinskylab/kandinsky-5](https://github.com/kandinskylab/kandinsky-5) | 844 | MIT | 2026-08-07 | Kandinsky 5.0: A family of diffusion models for Video & Image generation |
| [SkyworkAI/SkyReels-A2](https://github.com/SkyworkAI/SkyReels-A2) | 713 | 自定义 | 2025-06-03 | SkyReels-A2: Compose anything in video diffusion transformers |
| [bytedance/Video-As-Prompt](https://github.com/bytedance/Video-As-Prompt) | 462 | Apache-2.0 | 2026-02-08 | [ICLR 2026] Official repo for paper "Video-As-Prompt: Unified Semantic Contr… |

## 数字人 / 对口型（22）

*音频驱动说话视频、肖像动画*

| 项目 | ★ | 协议 | 最近提交 | 说明 |
|---|---:|---|---|---|
| [KlingAIResearch/LivePortrait](https://github.com/KlingAIResearch/LivePortrait) | 19379 | 自定义 | 2026-06-01 | Bring portraits to life! |
| [GuijiAI/HeyGem.ai](https://github.com/GuijiAI/HeyGem.ai) | 16211 | 自定义 | 2026-04-21 | 🚀 Truly open-source AI avatar(digital human) toolkit for offline video gener… |
| [duixcom/Duix-Avatar](https://github.com/duixcom/Duix-Avatar) | 16199 | 自定义 | 2026-04-21 | 🚀 Truly open-source AI avatar(digital human) toolkit for offline video gener… |
| [OpenTalker/SadTalker](https://github.com/OpenTalker/SadTalker) | 14174 | 自定义 | 2024-06-26 | [CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized… |
| [Rudrabha/Wav2Lip](https://github.com/Rudrabha/Wav2Lip) | 13263 | 未声明 | 2025-06-22 | This repository contains the codes of "A Lip Sync Expert Is All You Need for… |
| [MeiGen-AI/InfiniteTalk](https://github.com/MeiGen-AI/InfiniteTalk) | 8285 | Apache-2.0 | 2026-05-22 | ​​Unlimited-length talking video generation​​ that supports image-to-video a… |
| [OpenTalker/video-retalking](https://github.com/OpenTalker/video-retalking) | 7299 | Apache-2.0 | 2024-08-05 | [SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Tal… |
| [TMElyralab/MuseTalk](https://github.com/TMElyralab/MuseTalk) | 6867 | 自定义 | 2025-09-26 | MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpain… |
| [bytedance/LatentSync](https://github.com/bytedance/LatentSync) | 6237 | Apache-2.0 | 2025-06-20 | Taming Stable Diffusion for Lip Sync! |
| [antgroup/echomimic_v2](https://github.com/antgroup/echomimic_v2) | 4675 | Apache-2.0 | 2026-02-23 | [CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human A… |
| [fudan-generative-vision/hallo2](https://github.com/fudan-generative-vision/hallo2) | 3755 | MIT | 2025-02-27 | [ICLR 2025] Hallo2: Long-Duration and High-Resolution Audio-driven Portrait … |
| [Kedreamix/Linly-Talker](https://github.com/Kedreamix/Linly-Talker) | 3478 | MIT | 2026-02-10 | Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an i… |
| [jixiaozhong/Sonic](https://github.com/jixiaozhong/Sonic) | 3276 | 自定义 | 2026-01-08 | Official implementation of "Sonic: Shifting Focus to Global Audio Perception… |
| [MeiGen-AI/MultiTalk](https://github.com/MeiGen-AI/MultiTalk) | 3027 | Apache-2.0 | 2026-05-22 | [NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video… |
| [anliyuan/Ultralight-Digital-Human](https://github.com/anliyuan/Ultralight-Digital-Human) | 2666 | 未声明 | 2026-07-22 | 一个超轻量级、可以在移动端实时运行的数字人模型 |
| [Tencent-Hunyuan/HunyuanVideo-Avatar](https://github.com/Tencent-Hunyuan/HunyuanVideo-Avatar) | 2204 | 自定义 | 2025-12-16 |  |
| [fudan-generative-vision/hallo3](https://github.com/fudan-generative-vision/hallo3) | 1420 | MIT | 2025-03-13 | [CVPR 2025] Hallo3: Highly Dynamic and Realistic Portrait Image Animation wi… |
| [Francis-Rings/StableAvatar](https://github.com/Francis-Rings/StableAvatar) | 1273 | MIT | 2026-09-25 | [NeurIPS2026] We present StableAvatar, the first end-to-end video diffusion … |
| [antgroup/ditto-talkinghead](https://github.com/antgroup/ditto-talkinghead) | 929 | Apache-2.0 | 2025-11-12 | [ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talkin… |
| [jdh-algo/JoyVASA](https://github.com/jdh-algo/JoyVASA) | 884 | MIT | 2026-04-16 | Diffusion-based Portrait and Animal Animation |
| [deepbrainai-research/float](https://github.com/deepbrainai-research/float) | 497 | 自定义 | 2025-11-10 | [ICCV 2025] Official Pytorch Implementation of FLOAT: Generative Motion Late… |
| [Tencent-Hunyuan/HunyuanPortrait](https://github.com/Tencent-Hunyuan/HunyuanPortrait) | 361 | 自定义 | 2025-12-07 | [CVPR-2025] The code of HunyuanPortrait: Implicit Condition Control for Enha… |

## 一站式工作流 / 译制（18）

*剧本分镜、成片流水线、字幕翻配*

| 项目 | ★ | 协议 | 最近提交 | 说明 |
|---|---:|---|---|---|
| [harry0703/MoneyPrinterTurbo](https://github.com/harry0703/MoneyPrinterTurbo) | 137776 | MIT | 2026-11-02 | 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 … |
| [HBAI-Ltd/Toonflow-app](https://github.com/HBAI-Ltd/Toonflow-app) | 20297 | MIT | 2026-11-02 | 短剧、漫剧制作工具 Toonflow：开源 AI 视频创作平台，集成剧本创作、智能分镜、角色与场景资产管理、图像生成和视频生成。融合无限画布、AI Ag… |
| [jianchang512/pyvideotrans](https://github.com/jianchang512/pyvideotrans) | 19631 | GPL-3.0 | 2026-11-03 | Translate the video from one language to another and embed dubbing & subtitl… |
| [Huanshere/VideoLingo](https://github.com/Huanshere/VideoLingo) | 19055 | Apache-2.0 | 2026-09-30 | Netflix-level subtitle cutting, translation, alignment, and even dubbing - o… |
| [SubtitleEdit/subtitleedit](https://github.com/SubtitleEdit/subtitleedit) | 14841 | MIT | 2026-11-03 | the subtitle editor :) |
| [FujiwaraChoki/MoneyPrinter](https://github.com/FujiwaraChoki/MoneyPrinter) | 14144 | MIT | 2026-03-26 | Automate Creation of YouTube Shorts using MoviePy. |
| [krillinai/OpenCreator](https://github.com/krillinai/OpenCreator) | 14131 | Apache-2.0 | 2026-11-03 | Formerly KrillinAI, VideoTranslation and Dubbing Tool for 120+ Languages. Op… |
| [HKUDS/ViMax](https://github.com/HKUDS/ViMax) | 12845 | MIT | 2026-09-30 | "ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Vide… |
| [RayVentura/ShortGPT](https://github.com/RayVentura/ShortGPT) | 8103 | MIT | 2025-02-10 | 🚀🎬 ShortGPT - Experimental AI framework for youtube shorts / tiktok channel … |
| [Forget-C/Jellyfish](https://github.com/Forget-C/Jellyfish) | 7113 | Apache-2.0 | 2026-07-30 | An end-to-end production workspace for AI-generated short dramas. From scrip… |
| [modelscope/FunClip](https://github.com/modelscope/FunClip) | 6489 | MIT | 2026-11-01 | FunASR-powered video transcription, subtitle generation, and LLM-assisted cl… |
| [YILS-LIN/short-video-factory](https://github.com/YILS-LIN/short-video-factory) | 6035 | AGPL-3.0 | 2026-11-02 | 一键生成产品营销与泛内容短视频，AI批量自动剪辑，高颜值跨平台桌面端工具 One click generation of product marketi… |
| [buxuku/SmartSub](https://github.com/buxuku/SmartSub) | 5928 | MIT | 2026-11-02 | 视频转字幕、字幕翻译、AI 配音与声音克隆、字幕烧录——免费开源的一站式桌面工具。基于 Whisper / FunASR 等本地模型离线语音转文字，批量… |
| [Anil-matcha/AI-Youtube-Shorts-Generator](https://github.com/Anil-matcha/AI-Youtube-Shorts-Generator) | 5737 | MIT | 2026-10-24 | Open-source alternative to Opus Clip, Vidyo.ai, Klap & SubMagic. Turn long-f… |
| [wide-trace/open-higgsfield](https://github.com/wide-trace/open-higgsfield) | 5303 | 未声明 | 2026-09-17 | A studio for image and video generation — one prompt bar, each model’s own s… |
| [jianchang512/stt](https://github.com/jianchang512/stt) | 4842 | GPL-3.0 | 2026-01-22 | 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 |
| [ThioJoe/Auto-Synced-Translated-Dubs](https://github.com/ThioJoe/Auto-Synced-Translated-Dubs) | 1751 | AGPL-3.0 | 2026-05-11 | Automatically translates the text of a video based on a subtitle file, and t… |
| [tin2tin/Pallaidium](https://github.com/tin2tin/Pallaidium) | 1552 | GPL-3.0 | 2026-10-29 | PALLAIDIUM — a generative AI movie studio, seamlessly integrated into the Bl… |

## 后期与增强（14）

*超分、修脸、插帧、抠像、编辑*

| 项目 | ★ | 协议 | 最近提交 | 说明 |
|---|---:|---|---|---|
| [upscayl/upscayl](https://github.com/upscayl/upscayl) | 51698 | AGPL-3.0 | 2026-10-05 | 🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and W… |
| [TencentARC/GFPGAN](https://github.com/TencentARC/GFPGAN) | 37702 | 自定义 | 2024-04-02 | GFPGAN aims at developing Practical Algorithms for Real-world Face Restorati… |
| [xinntao/Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) | 37335 | BSD-3-Clause | 2024-08-06 | Real-ESRGAN aims at developing Practical Algorithms for General Image/Video … |
| [facefusion/facefusion](https://github.com/facefusion/facefusion) | 30519 | 自定义 | 2026-11-03 | Industry leading face manipulation platform |
| [Sanster/IOPaint](https://github.com/Sanster/IOPaint) | 23297 | Apache-2.0 | 2025-04-29 | Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, … |
| [k4yt3x/video2x](https://github.com/k4yt3x/video2x) | 22551 | AGPL-3.0 | 2026-03-07 | A machine learning-based video super resolution and frame interpolation fram… |
| [sczhou/CodeFormer](https://github.com/sczhou/CodeFormer) | 18210 | 自定义 | 2025-11-18 | [NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Tr… |
| [PeterL1n/RobustVideoMatting](https://github.com/PeterL1n/RobustVideoMatting) | 9586 | GPL-3.0 | 2024-04-02 | Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML! |
| [XPixelGroup/BasicSR](https://github.com/XPixelGroup/BasicSR) | 8405 | Apache-2.0 | 2024-05-17 | Open Source Image and Video Restoration Toolbox for Super-resolution, Denois… |
| [sczhou/ProPainter](https://github.com/sczhou/ProPainter) | 7033 | 自定义 | 2026-10-27 | [ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpa… |
| [chaiNNer-org/chaiNNer](https://github.com/chaiNNer-org/chaiNNer) | 6133 | GPL-3.0 | 2026-11-02 | A node-based image processing GUI aimed at making chaining image processing … |
| [williamyang1991/Rerender_A_Video](https://github.com/williamyang1991/Rerender_A_Video) | 2997 | 自定义 | 2024-03-09 | [SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video … |
| [NJU-PCALab/STAR](https://github.com/NJU-PCALab/STAR) | 1506 | 未声明 | 2025-07-02 | [ICCV 2025] STAR: Spatial-Temporal Augmentation with Text-to-Video Models fo… |
| [hzwer/Practical-RIFE](https://github.com/hzwer/Practical-RIFE) | 1035 | MIT | 2026-08-27 | More practical frame interpolation approach. |

## 语音合成与克隆（12）

*TTS、声音克隆、变声*

| 项目 | ★ | 协议 | 最近提交 | 说明 |
|---|---:|---|---|---|
| [2noise/ChatTTS](https://github.com/2noise/ChatTTS) | 39975 | AGPL-3.0 | 2026-04-10 | A generative speech model for daily dialogue. Contribute to 2noise/ChatTTS d… |
| [RVC-Project/Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) | 39036 | MIT | 2026-08-04 | Easily train a good VC model with voice data <= 10 mins! - RVC-Project/Re… |
| [myshell-ai/OpenVoice](https://github.com/myshell-ai/OpenVoice) | 38134 | MIT | 2025-04-19 | Instant voice cloning by MIT and MyShell. Audio foundation model. - myshell-… |
| [fishaudio/fish-speech](https://github.com/fishaudio/fish-speech) | 33551 | 自定义 | 2026-11-02 | SOTA Open Source TTS |
| [svc-develop-team/so-vits-svc](https://github.com/svc-develop-team/so-vits-svc) | 28067 | AGPL-3.0 | 2023-10-03 | SoftVC VITS Singing Voice Conversion. Contribute to svc-develop-team/so-vits… |
| [index-tts/index-tts](https://github.com/index-tts/index-tts) | 24899 | 自定义 | 2026-09-29 | An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System |
| [QwenAudio/CosyVoice](https://github.com/QwenAudio/CosyVoice) | 24257 | Apache-2.0 | 2026-05-25 | Multi-lingual large voice generation model, providing inference, training an… |
| [SWivid/F5-TTS](https://github.com/SWivid/F5-TTS) | 15507 | MIT | 2026-11-03 | Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful … |
| [SparkAudio/Spark-TTS](https://github.com/SparkAudio/Spark-TTS) | 10993 | Apache-2.0 | 2025-04-09 | Spark-TTS Inference Code. Contribute to SparkAudio/Spark-TTS development by … |
| [fishaudio/Bert-VITS2](https://github.com/fishaudio/Bert-VITS2) | 8806 | AGPL-3.0 | 2026-05-29 | vits2 backbone with multilingual-bert. Contribute to fishaudio/Bert-VITS2 de… |
| [Plachtaa/VALL-E-X](https://github.com/Plachtaa/VALL-E-X) | 7907 | MIT | 2023-11-03 | An open source implementation of Microsoft's VALL-E X zero-shot TTS mode… |
| [yl4579/StyleTTS2](https://github.com/yl4579/StyleTTS2) | 6382 | MIT | 2024-03-07 | StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and A… |

## 音乐、音效与分离（9）

*BGM 生成、视频拟音、人声分离*

| 项目 | ★ | 协议 | 最近提交 | 说明 |
|---|---:|---|---|---|
| [Anjok07/ultimatevocalremovergui](https://github.com/Anjok07/ultimatevocalremovergui) | 26941 | MIT | 2026-10-06 | GUI for a Vocal Remover that uses Deep Neural Networks. - Anjok07/ultimatevo… |
| [facebookresearch/audiocraft](https://github.com/facebookresearch/audiocraft) | 23816 | MIT | 2025-03-13 | Audiocraft is a library for audio processing and generation with deep learni… |
| [multimodal-art-projection/YuE](https://github.com/multimodal-art-projection/YuE) | 13054 | Apache-2.0 | 2026-11-01 | YuE2: frontier music generation with symbolic planning, zero-shot covers, an… |
| [ace-step/ACE-Step](https://github.com/ace-step/ACE-Step) | 5024 | Apache-2.0 | 2026-02-15 | ACE-Step: A Step Towards Music Generation Foundation Model - ace-step/ACE-Step |
| [adefossez/demucs](https://github.com/adefossez/demucs) | 3496 | MIT | 2026-10-26 | Code for the paper Hybrid Spectrogram and Waveform Source Separation - adefo… |
| [haoheliu/AudioLDM2](https://github.com/haoheliu/AudioLDM2) | 2644 | 自定义 | 2024-09-29 | Text-to-Audio/Music Generation. Contribute to haoheliu/AudioLDM2 development… |
| [ASLP-lab/DiffRhythm](https://github.com/ASLP-lab/DiffRhythm) | 2358 | Apache-2.0 | 2025-11-27 | Di♪♪Rhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length … |
| [hkchengrex/MMAudio](https://github.com/hkchengrex/MMAudio) | 2303 | MIT | 2026-02-23 | [CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video… |
| [Tencent-Hunyuan/HunyuanVideo-Foley](https://github.com/Tencent-Hunyuan/HunyuanVideo-Foley) | 1087 | 自定义 | 2025-09-28 | HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for H… |

## 加速与 ComfyUI 生态（14）

*量化、注意力加速、并行、节点*

| 项目 | ★ | 协议 | 最近提交 | 说明 |
|---|---:|---|---|---|
| [Comfy-Org/ComfyUI](https://github.com/Comfy-Org/ComfyUI) | 144745 | GPL-3.0 | 2026-11-03 | The most powerful and modular diffusion model GUI, api and backend with a gr… |
| [Comfy-Org/ComfyUI-Manager](https://github.com/Comfy-Org/ComfyUI-Manager) | 16711 | GPL-3.0 | 2026-11-02 | ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI… |
| [kijai/ComfyUI-WanVideoWrapper](https://github.com/kijai/ComfyUI-WanVideoWrapper) | 6806 | Apache-2.0 | 2026-05-24 |  |
| [hao-ai-lab/FastVideo](https://github.com/hao-ai-lab/FastVideo) | 4777 | Apache-2.0 | 2026-11-03 | A unified inference and post-training framework for accelerated video genera… |
| [mcmonkeyprojects/SwarmUI](https://github.com/mcmonkeyprojects/SwarmUI) | 4741 | MIT | 2026-11-03 | SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interf… |
| [thu-ml/SageAttention](https://github.com/thu-ml/SageAttention) | 3988 | Apache-2.0 | 2026-01-17 | [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves spe… |
| [nunchux-ai/nunchaku](https://github.com/nunchux-ai/nunchaku) | 3963 | Apache-2.0 | 2026-09-06 | [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for… |
| [xdit-project/xDiT](https://github.com/xdit-project/xDiT) | 2748 | Apache-2.0 | 2026-11-03 | xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Mas… |
| [kijai/ComfyUI-HunyuanVideoWrapper](https://github.com/kijai/ComfyUI-HunyuanVideoWrapper) | 2592 | 未声明 | 2025-08-20 |  |
| [Kosinkadink/ComfyUI-VideoHelperSuite](https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite) | 1909 | GPL-3.0 | 2026-09-02 | Nodes related to video workflows |
| [ali-vilab/TeaCache](https://github.com/ali-vilab/TeaCache) | 1387 | Apache-2.0 | 2025-06-08 | Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model |
| [Fannovel16/ComfyUI-Frame-Interpolation](https://github.com/Fannovel16/ComfyUI-Frame-Interpolation) | 1093 | MIT | 2026-03-29 | A custom node set for Video Frame Interpolation in ComfyUI. |
| [chengzeyi/ParaAttention](https://github.com/chengzeyi/ParaAttention) | 436 | 自定义 | 2025-07-05 | https://wavespeed.ai/ Context parallel attention that accelerates DiT model … |
| [comfyanonymous/ComfyUI_bitsandbytes_NF4](https://github.com/comfyanonymous/ComfyUI_bitsandbytes_NF4) | 424 | AGPL-3.0 | 2026-09-29 |  |

---

**合计 118 个仓库。** 未收录的：`ali-vilab/i2vgen-xl`（已迁移，仓库仅剩占位）、`GuijiAI/HeyGem.ai` 与 `duixcom/Duix-Avatar` 为同一项目的新旧名（两个都保留 star 数据，正文按 Duix-Avatar 介绍）。


数据文件：`data/repos.json`（含 forks、创建时间、语言、topics、homepage 等完整字段）