{
 "Wan-Video/Wan2.2": {
  "stars": 18335,
  "forks": 2407,
  "license": "Apache-2.0",
  "desc": "Wan: Open and Advanced Large-Scale Video Generative Models",
  "url": "https://github.com/Wan-Video/Wan2.2",
  "homepage": "https://wan.video",
  "pushed": "2026-09-21T06:16:22Z",
  "created": "2025-07-28T08:17:01Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "aigc",
   "video-generation"
  ]
 },
 "Wan-Video/Wan2.1": {
  "stars": 17366,
  "forks": 3975,
  "license": "Apache-2.0",
  "desc": "Wan: Open and Advanced Large-Scale Video Generative Models",
  "url": "https://github.com/Wan-Video/Wan2.1",
  "homepage": "https://wan.video",
  "pushed": "2026-03-05T09:38:07Z",
  "created": "2025-02-25T11:49:33Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "aigc",
   "videogeneration"
  ]
 },
 "Tencent-Hunyuan/HunyuanVideo": {
  "stars": 12714,
  "forks": 1376,
  "license": "NOASSERTION",
  "desc": "HunyuanVideo: A Systematic Framework For Large Video Generation Model",
  "url": "https://github.com/Tencent-Hunyuan/HunyuanVideo",
  "homepage": "https://aivideo.hunyuan.tencent.com",
  "pushed": "2026-10-08T08:57:37Z",
  "created": "2024-11-28T08:38:31Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "diffusion-models",
   "diffusion-transformer",
   "video-generation"
  ]
 },
 "Tencent-Hunyuan/HunyuanVideo-1.5": {
  "stars": 4590,
  "forks": 238,
  "license": "NOASSERTION",
  "desc": "HunyuanVideo-1.5: A leading lightweight video generation model",
  "url": "https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5",
  "homepage": "https://hunyuan.tencent.com/video/zh?tabIndex=0",
  "pushed": "2026-04-10T06:14:59Z",
  "created": "2025-11-20T06:15:42Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "image-to-video",
   "text-to-video",
   "video-generation"
  ]
 },
 "Lightricks/LTX-Video": {
  "stars": 11286,
  "forks": 1216,
  "license": "Apache-2.0",
  "desc": "Official repository for LTX-Video",
  "url": "https://github.com/Lightricks/LTX-Video",
  "homepage": "https://ltx.io/model",
  "pushed": "2026-11-02T19:25:43Z",
  "created": "2024-11-20T20:06:28Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "diffusion-models",
   "dit",
   "image-to-video",
   "image-to-video-generation",
   "text-to-video",
   "text-to-video-generation"
  ]
 },
 "genmoai/mochi": {
  "stars": 3761,
  "forks": 497,
  "license": "Apache-2.0",
  "desc": "The best OSS video generation models, created by Genmo",
  "url": "https://github.com/genmoai/mochi",
  "homepage": "",
  "pushed": "2026-10-22T23:35:03Z",
  "created": "2024-09-11T02:55:33Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "zai-org/CogVideo": {
  "stars": 13175,
  "forks": 1385,
  "license": "Apache-2.0",
  "desc": "text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)",
  "url": "https://github.com/zai-org/CogVideo",
  "homepage": "",
  "pushed": "2025-11-04T11:19:04Z",
  "created": "2022-05-29T06:46:18Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "cogvideox",
   "image-to-video",
   "llm",
   "sora",
   "text-to-video",
   "video-generation"
  ]
 },
 "hpcaitech/Open-Sora": {
  "stars": 29902,
  "forks": 3092,
  "license": "Apache-2.0",
  "desc": "Open-Sora: Democratizing Efficient Video Production for All",
  "url": "https://github.com/hpcaitech/Open-Sora",
  "homepage": "https://hpcaitech.github.io/Open-Sora/",
  "pushed": "2026-04-09T01:52:40Z",
  "created": "2024-02-20T03:01:34Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "SandAI-org/MAGI-1": {
  "stars": 3798,
  "forks": 242,
  "license": "Apache-2.0",
  "desc": "MAGI-1: Autoregressive Video Generation at Scale",
  "url": "https://github.com/SandAI-org/MAGI-1",
  "homepage": "https://sand.ai",
  "pushed": "2026-06-17T07:06:35Z",
  "created": "2025-04-21T10:34:09Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "autoregressive",
   "diffusion-models",
   "video-generation"
  ]
 },
 "SkyworkAI/SkyReels-V2": {
  "stars": 7753,
  "forks": 1703,
  "license": "NOASSERTION",
  "desc": "SkyReels-V2: Infinite-length Film Generative model",
  "url": "https://github.com/SkyworkAI/SkyReels-V2",
  "homepage": "https://platform.skyreels.ai",
  "pushed": "2026-01-29T05:21:27Z",
  "created": "2025-04-15T10:16:25Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "stepfun-ai/Step-Video-T2V": {
  "stars": 3189,
  "forks": 335,
  "license": "MIT",
  "desc": "",
  "url": "https://github.com/stepfun-ai/Step-Video-T2V",
  "homepage": null,
  "pushed": "2025-03-17T03:26:54Z",
  "created": "2025-02-08T08:46:51Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "rhymes-ai/Allegro": {
  "stars": 1137,
  "forks": 68,
  "license": "Apache-2.0",
  "desc": "Allegro is a powerful text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input. ",
  "url": "https://github.com/rhymes-ai/Allegro",
  "homepage": "https://rhymes.ai/",
  "pushed": "2025-02-07T15:31:36Z",
  "created": "2024-10-16T04:04:15Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "guoyww/AnimateDiff": {
  "stars": 12283,
  "forks": 1106,
  "license": "Apache-2.0",
  "desc": "Official implementation of AnimateDiff.",
  "url": "https://github.com/guoyww/AnimateDiff",
  "homepage": "https://animatediff.github.io",
  "pushed": "2024-07-31T01:14:15Z",
  "created": "2023-06-17T11:14:28Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "lllyasviel/FramePack": {
  "stars": 17340,
  "forks": 1747,
  "license": "Apache-2.0",
  "desc": "Lets make video diffusion practical!",
  "url": "https://github.com/lllyasviel/FramePack",
  "homepage": "",
  "pushed": "2025-10-16T01:28:50Z",
  "created": "2025-04-12T14:45:22Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "ali-vilab/VGen": {
  "stars": 3153,
  "forks": 273,
  "license": null,
  "desc": "Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models",
  "url": "https://github.com/ali-vilab/VGen",
  "homepage": "https://i2vgen-xl.github.io",
  "pushed": "2025-01-10T09:09:13Z",
  "created": "2023-11-06T06:50:19Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "diffusion-models",
   "video-synthesis"
  ]
 },
 "modelscope/DiffSynth-Studio": {
  "stars": 13336,
  "forks": 1329,
  "license": "Apache-2.0",
  "desc": "Enjoy the magic of Diffusion models!",
  "url": "https://github.com/modelscope/DiffSynth-Studio",
  "homepage": "",
  "pushed": "2026-11-03T06:33:52Z",
  "created": "2023-12-07T16:52:15Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "Stability-AI/generative-models": {
  "stars": 27318,
  "forks": 3092,
  "license": "MIT",
  "desc": "Generative Models by Stability AI",
  "url": "https://github.com/Stability-AI/generative-models",
  "homepage": "",
  "pushed": "2025-12-16T08:36:18Z",
  "created": "2023-06-22T00:36:35Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "FoundationVision/Waver": {
  "stars": 955,
  "forks": 124,
  "license": null,
  "desc": "Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.",
  "url": "https://github.com/FoundationVision/Waver",
  "homepage": "",
  "pushed": "2025-08-27T18:50:42Z",
  "created": "2025-08-05T06:20:16Z",
  "lang": null,
  "archived": false,
  "topics": []
 },
 "PKU-YuanGroup/ConsisID": {
  "stars": 863,
  "forks": 48,
  "license": "Apache-2.0",
  "desc": "[CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition",
  "url": "https://github.com/PKU-YuanGroup/ConsisID",
  "homepage": "https://pku-yuangroup.github.io/ConsisID/",
  "pushed": "2026-04-14T03:25:24Z",
  "created": "2024-11-15T11:19:39Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "diffusion",
   "diffusion-models",
   "identity-preserving",
   "text-to-video",
   "video-generation",
   "video-generation-dataset",
   "video-generator",
   "videogeneration"
  ]
 },
 "ali-vilab/VACE": {
  "stars": 4046,
  "forks": 296,
  "license": "Apache-2.0",
  "desc": "[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing",
  "url": "https://github.com/ali-vilab/VACE",
  "homepage": "https://ali-vilab.github.io/VACE-Page/",
  "pushed": "2025-10-17T05:46:57Z",
  "created": "2025-03-08T07:58:12Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "video-editing",
   "video-generation"
  ]
 },
 "MeiGen-AI/InfiniteTalk": {
  "stars": 8285,
  "forks": 1421,
  "license": "Apache-2.0",
  "desc": "​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation",
  "url": "https://github.com/MeiGen-AI/InfiniteTalk",
  "homepage": null,
  "pushed": "2026-05-22T02:35:51Z",
  "created": "2025-08-14T01:04:53Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "MeiGen-AI/MultiTalk": {
  "stars": 3027,
  "forks": 503,
  "license": "Apache-2.0",
  "desc": "[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation",
  "url": "https://github.com/MeiGen-AI/MultiTalk",
  "homepage": "https://meigen-ai.github.io/multi-talk/",
  "pushed": "2026-05-22T02:38:22Z",
  "created": "2025-05-28T13:21:40Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "OpenTalker/SadTalker": {
  "stars": 14174,
  "forks": 2702,
  "license": "NOASSERTION",
  "desc": "[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation",
  "url": "https://github.com/OpenTalker/SadTalker",
  "homepage": "https://sadtalker.github.io/",
  "pushed": "2024-06-26T12:51:53Z",
  "created": "2022-11-23T02:18:18Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "audio-driven-talking-face",
   "cvpr2023",
   "deep-fake",
   "deep-fakes",
   "image-animation",
   "talking-face",
   "talking-face-generation",
   "talking-head",
   "talking-heads"
  ]
 },
 "Rudrabha/Wav2Lip": {
  "stars": 13263,
  "forks": 2850,
  "license": null,
  "desc": "This repository contains the codes of \"A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild\", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs ",
  "url": "https://github.com/Rudrabha/Wav2Lip",
  "homepage": "https://sync.so",
  "pushed": "2025-06-22T02:41:21Z",
  "created": "2020-08-07T08:06:38Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "bytedance/LatentSync": {
  "stars": 6237,
  "forks": 1000,
  "license": "Apache-2.0",
  "desc": "Taming Stable Diffusion for Lip Sync!",
  "url": "https://github.com/bytedance/LatentSync",
  "homepage": "https://arxiv.org/abs/2412.09262",
  "pushed": "2025-06-20T07:36:58Z",
  "created": "2024-12-11T10:32:54Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "diffusion-models",
   "lipsync",
   "research",
   "video-gen",
   "virtual-avatars"
  ]
 },
 "antgroup/echomimic_v2": {
  "stars": 4675,
  "forks": 555,
  "license": "Apache-2.0",
  "desc": "[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation",
  "url": "https://github.com/antgroup/echomimic_v2",
  "homepage": "https://antgroup.github.io/ai/echomimic_v2/",
  "pushed": "2026-02-23T05:28:31Z",
  "created": "2024-11-20T08:35:35Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "audio-driven-body-animation",
   "audio-driven-portrait-animations",
   "audio-driven-talking-face",
   "cvpr2025",
   "human-animation",
   "talking-face-generation",
   "talking-head",
   "video-generation"
  ]
 },
 "duixcom/Duix-Avatar": {
  "stars": 16199,
  "forks": 2765,
  "license": "NOASSERTION",
  "desc": "🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.",
  "url": "https://github.com/duixcom/Duix-Avatar",
  "homepage": "https://www.duix.com/",
  "pushed": "2026-04-21T07:06:36Z",
  "created": "2024-12-24T03:00:26Z",
  "lang": "C",
  "archived": false,
  "topics": [
   "ai-avatar",
   "ai-avatars",
   "cloning",
   "cloning-tool",
   "digital-human",
   "multimodal-ai",
   "video-generation",
   "video-synthesis"
  ]
 },
 "fudan-generative-vision/hallo3": {
  "stars": 1420,
  "forks": 188,
  "license": "MIT",
  "desc": "[CVPR 2025] Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer",
  "url": "https://github.com/fudan-generative-vision/hallo3",
  "homepage": "",
  "pushed": "2025-03-13T08:34:43Z",
  "created": "2024-11-27T02:35:10Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "OpenTalker/video-retalking": {
  "stars": 7299,
  "forks": 1047,
  "license": "Apache-2.0",
  "desc": "[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild",
  "url": "https://github.com/OpenTalker/video-retalking",
  "homepage": "https://opentalker.github.io/video-retalking/",
  "pushed": "2024-08-05T05:59:59Z",
  "created": "2022-09-14T04:24:49Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "lip-synchronization",
   "siggraph-asia-2022",
   "talking-head-videos",
   "video-editing"
  ]
 },
 "KwaiVGI/LivePortrait": {
  "stars": 19379,
  "forks": 2016,
  "license": "NOASSERTION",
  "desc": "Bring portraits to life!",
  "url": "https://github.com/KlingAIResearch/LivePortrait",
  "homepage": "https://liveportrait.github.io",
  "pushed": "2026-06-01T17:25:09Z",
  "created": "2024-07-03T16:15:03Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "face-animation",
   "image-animation",
   "video-editing",
   "video-generation"
  ]
 },
 "deepbrainai-research/float": {
  "stars": 497,
  "forks": 66,
  "license": "NOASSERTION",
  "desc": "[ICCV 2025] Official Pytorch Implementation of FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait.",
  "url": "https://github.com/deepbrainai-research/float",
  "homepage": "https://deepbrainai-research.github.io/float/",
  "pushed": "2025-11-10T14:12:57Z",
  "created": "2024-11-27T04:30:13Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "audio-driven-portrait-animations",
   "lip-sync",
   "video-generation"
  ]
 },
 "comfyanonymous/ComfyUI": {
  "stars": 144745,
  "forks": 17254,
  "license": "GPL-3.0",
  "desc": "The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.",
  "url": "https://github.com/Comfy-Org/ComfyUI",
  "homepage": "https://www.comfy.org/",
  "pushed": "2026-11-03T08:10:31Z",
  "created": "2023-01-17T03:15:56Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "ai",
   "comfy",
   "comfyui",
   "python",
   "pytorch",
   "stable-diffusion"
  ]
 },
 "HBAI-Ltd/Toonflow-app": {
  "stars": 20297,
  "forks": 3645,
  "license": "MIT",
  "desc": "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 Agent 与可视化工作流，支持本地部署、自选模型、跨平台客户端、MCP 与插件扩展。Open-source AI short drama and motion comic creation tool with an infinite canvas, AI agents, storyboarding, image and video generation. Self-hosted and extensible, with a canvas-based approach similar to LibTV and TapNow.",
  "url": "https://github.com/HBAI-Ltd/Toonflow-app",
  "homepage": "https://toonflow.net",
  "pushed": "2026-11-02T13:04:28Z",
  "created": "2026-01-29T10:25:45Z",
  "lang": "Vue",
  "archived": false,
  "topics": [
   "ai-agents",
   "ai-comic",
   "ai-content-creation",
   "ai-filmmaking",
   "ai-short-drama",
   "generative-ai",
   "image-generation",
   "image-to-video",
   "infinite-canvas",
   "libtv",
   "motion-comics",
   "node-based-editor",
   "open-source",
   "short-drama",
   "storyboarding",
   "tapnow",
   "text-to-image",
   "text-to-video",
   "video-generation",
   "workflow-automation"
  ]
 },
 "Forget-C/Jellyfish": {
  "stars": 7113,
  "forks": 1221,
  "license": "Apache-2.0",
  "desc": "An end-to-end production workspace for AI-generated short dramas. From script input to structured storyboarding, consistency management, shot preparation, video generation, and export.",
  "url": "https://github.com/Forget-C/Jellyfish",
  "homepage": "https://forget-c.github.io/Jellyfish",
  "pushed": "2026-07-30T02:19:18Z",
  "created": "2026-03-06T09:20:08Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "ai",
   "short-drama"
  ]
 },
 "YILS-LIN/short-video-factory": {
  "stars": 6035,
  "forks": 829,
  "license": "AGPL-3.0",
  "desc": "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 marketing and general content short videos, AI batch automatic cliping, beautiful cross platform desktop tool",
  "url": "https://github.com/YILS-LIN/short-video-factory",
  "homepage": "https://short-video-factory.yils.blog",
  "pushed": "2026-11-02T03:30:50Z",
  "created": "2025-07-09T05:55:44Z",
  "lang": "TypeScript",
  "archived": false,
  "topics": [
   "ai",
   "automatic",
   "automation",
   "clipping",
   "cross-platform",
   "desktop",
   "linux",
   "mac",
   "marketing",
   "pc",
   "product",
   "shortvideo",
   "tiktok",
   "windows"
  ]
 },
 "harry0703/MoneyPrinterTurbo": {
  "stars": 137776,
  "forks": 21995,
  "license": "MIT",
  "desc": "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.",
  "url": "https://github.com/harry0703/MoneyPrinterTurbo",
  "homepage": "",
  "pushed": "2026-11-02T23:29:07Z",
  "created": "2024-03-11T02:57:34Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "ai-video-generator",
   "content-creation",
   "ffmpeg",
   "instagram-reels",
   "llm",
   "python",
   "short-video",
   "subtitles",
   "text-to-speech",
   "tiktok",
   "video-automation",
   "video-workflow",
   "workflow-automation",
   "youtube-shorts"
  ]
 },
 "modelscope/FunClip": {
  "stars": 6489,
  "forks": 771,
  "license": "MIT",
  "desc": "FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.",
  "url": "https://github.com/modelscope/FunClip",
  "homepage": "https://huggingface.co/spaces/FunAudioLLM/FunClip",
  "pushed": "2026-11-01T14:52:34Z",
  "created": "2023-05-17T07:23:44Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "ai-tools",
   "ai-video-editing",
   "asr",
   "auto-subtitles",
   "chinese",
   "content-creation",
   "funasr",
   "funclip",
   "gradio",
   "llm",
   "paraformer",
   "speech-recognition",
   "speech-to-text",
   "subtitles-generator",
   "transcription",
   "video-editing",
   "video-processing",
   "video-subtitles",
   "video-transcription",
   "whisper-alternative"
  ]
 },
 "buxuku/SmartSub": {
  "stars": 5928,
  "forks": 480,
  "license": "MIT",
  "desc": "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，批量处理 + 全平台 GPU 加速，跨 Windows / macOS / Linux。Free, open-source desktop app to generate, translate, dub & burn video subtitles — local Whisper speech-to-text, AI dubbing & voice cloning, offline, GPU-accelerated.",
  "url": "https://github.com/buxuku/SmartSub",
  "homepage": "https://smartsub.linxiaodong.com/",
  "pushed": "2026-11-02T10:04:00Z",
  "created": "2024-05-21T09:33:49Z",
  "lang": "TypeScript",
  "archived": false,
  "topics": [
   "deepseek",
   "faster-whisper",
   "fireredasr",
   "funasr",
   "ollama",
   "openai",
   "qwen3-asr",
   "sherpa-onnx",
   "subtitle",
   "translate",
   "whisper",
   "whisper-cpp"
  ]
 },
 "tin2tin/Pallaidium": {
  "stars": 1552,
  "forks": 162,
  "license": "GPL-3.0",
  "desc": "PALLAIDIUM — a generative AI movie studio, seamlessly integrated into the Blender Video Editor (VSE), enabling end-to-end production from script to screen and back.",
  "url": "https://github.com/tin2tin/Pallaidium",
  "homepage": "https://tin2tin.github.io/Pallaidium/",
  "pushed": "2026-10-29T20:17:52Z",
  "created": "2023-03-20T18:40:16Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "ai",
   "aicinema",
   "blender",
   "chatterbox",
   "diffusion",
   "flux",
   "generative",
   "ltx",
   "movie",
   "qwen",
   "studio",
   "text2audio",
   "text2image",
   "text2speech",
   "text2video",
   "turbo",
   "wan",
   "z-image"
  ]
 },
 "HKUDS/ViMax": {
  "stars": 12845,
  "forks": 1939,
  "license": "MIT",
  "desc": "\"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)\"",
  "url": "https://github.com/HKUDS/ViMax",
  "homepage": "https://arxiv.org/abs/2606.07649",
  "pushed": "2026-09-30T14:35:08Z",
  "created": "2025-03-30T13:36:35Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "agentic-aigc",
   "video-generation"
  ]
 },
 "Anil-matcha/AI-Youtube-Shorts-Generator": {
  "stars": 5737,
  "forks": 1042,
  "license": "MIT",
  "desc": "Open-source alternative to Opus Clip, Vidyo.ai, Klap & SubMagic. Turn long-form YouTube videos into viral 9:16 shorts using LLM highlight detection, Whisper transcription, and auto vertical cropping — free, no watermarks, no per-clip credits.",
  "url": "https://github.com/Anil-matcha/AI-Youtube-Shorts-Generator",
  "homepage": "https://www.vadoo.tv/ai-youtube-shorts-generator",
  "pushed": "2026-10-24T17:01:38Z",
  "created": "2024-06-28T07:39:14Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "2short-ai-alternative",
   "ai-clip-generator",
   "ai-clipping",
   "auto-clip",
   "auto-crop",
   "highlight-detection",
   "klap-alternative",
   "llm",
   "open-source",
   "opus-clip-alternative",
   "reels",
   "shorts-maker",
   "submagic-alternative",
   "tiktok",
   "vertical-video",
   "video-editing",
   "vidyo-ai-alternative",
   "viral-clips",
   "whisper",
   "youtube-shorts"
  ]
 },
 "NJU-PCALab/STAR": {
  "stars": 1506,
  "forks": 87,
  "license": null,
  "desc": "[ICCV 2025] STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution",
  "url": "https://github.com/NJU-PCALab/STAR",
  "homepage": "",
  "pushed": "2025-07-02T08:32:10Z",
  "created": "2024-11-21T10:14:56Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "facefusion/facefusion": {
  "stars": 30519,
  "forks": 4999,
  "license": "NOASSERTION",
  "desc": "Industry leading face manipulation platform",
  "url": "https://github.com/facefusion/facefusion",
  "homepage": "https://facefusion.io",
  "pushed": "2026-11-03T08:19:54Z",
  "created": "2023-08-17T19:59:55Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "ai",
   "deep-fake",
   "deepfake",
   "face-swap",
   "faceswap",
   "lip-sync",
   "lipsync"
  ]
 },
 "xinntao/Real-ESRGAN": {
  "stars": 37335,
  "forks": 4517,
  "license": "BSD-3-Clause",
  "desc": "Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.",
  "url": "https://github.com/xinntao/Real-ESRGAN",
  "homepage": "",
  "pushed": "2024-08-06T13:15:18Z",
  "created": "2021-07-19T03:23:30Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "amine",
   "denoise",
   "esrgan",
   "image-restoration",
   "jpeg-compression",
   "pytorch",
   "real-esrgan",
   "super-resolution"
  ]
 },
 "sczhou/CodeFormer": {
  "stars": 18210,
  "forks": 3720,
  "license": "NOASSERTION",
  "desc": "[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer",
  "url": "https://github.com/sczhou/CodeFormer",
  "homepage": "",
  "pushed": "2025-11-18T12:03:30Z",
  "created": "2022-06-21T02:48:14Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "codebook",
   "codeformer",
   "face-enhancement",
   "face-restoration",
   "pytorch",
   "restoration",
   "super-resolution",
   "vqgan"
  ]
 },
 "williamyang1991/Rerender_A_Video": {
  "stars": 2997,
  "forks": 195,
  "license": "NOASSERTION",
  "desc": "[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation",
  "url": "https://github.com/williamyang1991/Rerender_A_Video",
  "homepage": "https://www.mmlab-ntu.com/project/rerender/",
  "pushed": "2024-03-09T12:34:21Z",
  "created": "2023-05-08T08:25:21Z",
  "lang": "Jupyter Notebook",
  "archived": false,
  "topics": [
   "controlnet",
   "diffusion",
   "video-processing"
  ]
 },
 "FunAudioLLM/CosyVoice": {
  "stars": 24257,
  "forks": 2771,
  "license": "Apache-2.0",
  "desc": "Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.",
  "url": "https://github.com/QwenAudio/CosyVoice",
  "homepage": "https://funaudiollm.github.io/cosyvoice3",
  "pushed": "2026-05-25T18:15:40Z",
  "created": "2024-07-03T02:59:22Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "audio-generation",
   "cantonese",
   "chatbot",
   "chatgpt",
   "chinese",
   "cosyvoice",
   "cross-lingual",
   "english",
   "fine-grained",
   "fine-tuning",
   "gpt-4o",
   "japanese",
   "korean",
   "multi-lingual",
   "natural-language-generation",
   "python",
   "text-to-speech",
   "tts",
   "voice-cloning"
  ]
 },
 "fishaudio/fish-speech": {
  "stars": 33551,
  "forks": 2917,
  "license": "NOASSERTION",
  "desc": "SOTA Open Source TTS",
  "url": "https://github.com/fishaudio/fish-speech",
  "homepage": "https://speech.fish.audio",
  "pushed": "2026-11-02T20:02:21Z",
  "created": "2023-10-10T03:16:51Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "llama",
   "transformer",
   "tts",
   "valle",
   "vits",
   "vqgan",
   "vqvae"
  ]
 },
 "index-tts/index-tts": {
  "stars": 24899,
  "forks": 2922,
  "license": "NOASSERTION",
  "desc": "An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System",
  "url": "https://github.com/index-tts/index-tts",
  "homepage": "",
  "pushed": "2026-09-29T16:06:53Z",
  "created": "2025-02-06T04:08:05Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "bigvgan",
   "cross-lingual",
   "indextts",
   "text-to-speech",
   "tts",
   "voice-clone",
   "zero-shot-tts"
  ]
 },
 "Tencent-Hunyuan/HunyuanVideo-I2V": {
  "stars": 1853,
  "forks": 199,
  "license": "NOASSERTION",
  "desc": "HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo",
  "url": "https://github.com/Tencent-Hunyuan/HunyuanVideo-I2V",
  "homepage": "https://video.hunyuan.tencent.com/",
  "pushed": "2026-04-07T06:13:09Z",
  "created": "2025-03-04T12:02:05Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "diffusion-models",
   "image-to-video",
   "image-to-video-generation",
   "videogeneration"
  ]
 },
 "Tencent-Hunyuan/HunyuanCustom": {
  "stars": 1232,
  "forks": 109,
  "license": "NOASSERTION",
  "desc": "HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation",
  "url": "https://github.com/Tencent-Hunyuan/HunyuanCustom",
  "homepage": "https://hunyuancustom.github.io/",
  "pushed": "2025-10-15T06:54:23Z",
  "created": "2025-05-07T07:48:42Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "audio-driven",
   "diffusion-models",
   "image-to-video",
   "image-to-video-generation",
   "video-editing",
   "video-generation"
  ]
 },
 "Tencent-Hunyuan/HunyuanVideo-Foley": {
  "stars": 1087,
  "forks": 109,
  "license": "NOASSERTION",
  "desc": "HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.",
  "url": "https://github.com/Tencent-Hunyuan/HunyuanVideo-Foley",
  "homepage": "https://hunyuan.tencent.com/video/zh?tabIndex=0",
  "pushed": "2025-09-28T17:48:49Z",
  "created": "2025-08-15T06:44:09Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "aigc-audio",
   "foley-art",
   "foley-sound-synthesis",
   "text-to-audio",
   "text-to-video",
   "text-video-to-audio",
   "tta",
   "video-to-audio"
  ]
 },
 "ai-forever/Kandinsky-5": {
  "stars": 844,
  "forks": 76,
  "license": "MIT",
  "desc": "Kandinsky 5.0: A family of diffusion models for Video & Image generation",
  "url": "https://github.com/kandinskylab/kandinsky-5",
  "homepage": "https://kandinskylab.ai",
  "pushed": "2026-08-07T14:33:47Z",
  "created": "2025-08-11T13:47:07Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "diffusion",
   "distillation",
   "kandinsky",
   "text-to-video",
   "video",
   "video-generation"
  ]
 },
 "PKU-YuanGroup/Open-Sora-Plan": {
  "stars": 12203,
  "forks": 1070,
  "license": "MIT",
  "desc": "This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.",
  "url": "https://github.com/PKU-YuanGroup/Open-Sora-Plan",
  "homepage": "",
  "pushed": "2026-03-08T12:48:46Z",
  "created": "2024-02-20T14:01:03Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "Vchitect/Vchitect-2.0": {
  "stars": 921,
  "forks": 22,
  "license": "Apache-2.0",
  "desc": "Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models",
  "url": "https://github.com/Vchitect/Vchitect-2.0",
  "homepage": "https://vchitect.intern-ai.org.cn/",
  "pushed": "2025-03-17T14:18:12Z",
  "created": "2024-09-09T12:18:28Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "ali-vilab/i2vgen-xl": {
  "stars": 9,
  "forks": 0,
  "license": null,
  "desc": "",
  "url": "https://github.com/ali-vilab/i2vgen-xl",
  "homepage": null,
  "pushed": "2024-03-06T08:16:48Z",
  "created": "2024-03-05T08:56:53Z",
  "lang": null,
  "archived": false,
  "topics": []
 },
 "aigc-apps/EasyAnimate": {
  "stars": 2266,
  "forks": 186,
  "license": "Apache-2.0",
  "desc": "📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion",
  "url": "https://github.com/aigc-apps/EasyAnimate",
  "homepage": "",
  "pushed": "2025-03-06T11:41:28Z",
  "created": "2024-04-11T08:52:50Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "SkyworkAI/SkyReels-V1": {
  "stars": 2702,
  "forks": 311,
  "license": "NOASSERTION",
  "desc": "SkyReels V1: The first and most advanced open-source human-centric video foundation model",
  "url": "https://github.com/SkyworkAI/SkyReels-V1",
  "homepage": "https://www.skyreels.ai",
  "pushed": "2025-03-10T10:02:10Z",
  "created": "2025-02-12T11:15:46Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "i2v",
   "t2v",
   "video-diffusion-transformers"
  ]
 },
 "bytedance/Video-As-Prompt": {
  "stars": 462,
  "forks": 34,
  "license": "Apache-2.0",
  "desc": "[ICLR 2026] Official repo for paper \"Video-As-Prompt: Unified Semantic Control for Video Generation\"",
  "url": "https://github.com/bytedance/Video-As-Prompt",
  "homepage": "https://bytedance.github.io/Video-As-Prompt/",
  "pushed": "2026-02-08T01:59:06Z",
  "created": "2025-10-22T01:06:23Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "controllable-video-generation",
   "in-context-generation",
   "video",
   "video-dataset",
   "video-generation"
  ]
 },
 "SkyworkAI/SkyReels-A2": {
  "stars": 713,
  "forks": 67,
  "license": "NOASSERTION",
  "desc": "SkyReels-A2: Compose anything in video diffusion transformers",
  "url": "https://github.com/SkyworkAI/SkyReels-A2",
  "homepage": "https://www.skyreels.ai/home/tools/to-video?refer=home",
  "pushed": "2025-06-03T06:15:58Z",
  "created": "2025-03-24T06:09:34Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "controllable-generation",
   "image2video",
   "video-diffusion-transformers"
  ]
 },
 "xdit-project/xDiT": {
  "stars": 2748,
  "forks": 356,
  "license": "Apache-2.0",
  "desc": "xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism",
  "url": "https://github.com/xdit-project/xDiT",
  "homepage": "",
  "pushed": "2026-11-03T12:45:58Z",
  "created": "2024-03-19T06:19:55Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "mit-han-lab/nunchaku": {
  "stars": 3963,
  "forks": 288,
  "license": "Apache-2.0",
  "desc": "[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models",
  "url": "https://github.com/nunchux-ai/nunchaku",
  "homepage": "nunchux.ai",
  "pushed": "2026-09-06T23:07:26Z",
  "created": "2024-11-06T07:24:40Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "comfyui",
   "diffusion-models",
   "flux",
   "genai",
   "iclr",
   "iclr2025",
   "lora",
   "mlsys",
   "quantization"
  ]
 },
 "thu-ml/SageAttention": {
  "stars": 3988,
  "forks": 545,
  "license": "Apache-2.0",
  "desc": "[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.",
  "url": "https://github.com/thu-ml/SageAttention",
  "homepage": "https://arxiv.org/abs/2410.02367",
  "pushed": "2026-01-17T17:43:28Z",
  "created": "2024-10-03T09:33:18Z",
  "lang": "Cuda",
  "archived": false,
  "topics": [
   "attention",
   "cuda",
   "efficient-attention",
   "inference-acceleration",
   "llm",
   "llm-infra",
   "mlsys",
   "quantization",
   "triton",
   "video-generate",
   "video-generation",
   "vit"
  ]
 },
 "ali-vilab/TeaCache": {
  "stars": 1387,
  "forks": 62,
  "license": "Apache-2.0",
  "desc": "Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model",
  "url": "https://github.com/ali-vilab/TeaCache",
  "homepage": "https://liewfeng.github.io/TeaCache/",
  "pushed": "2025-06-08T14:29:09Z",
  "created": "2024-11-27T09:34:58Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "cogvideox",
   "diffusion-models",
   "hunyuan-video",
   "inference-acceleration",
   "latte",
   "open-sora",
   "open-sora-plan",
   "video-generation"
  ]
 },
 "hao-ai-lab/FastVideo": {
  "stars": 4777,
  "forks": 518,
  "license": "Apache-2.0",
  "desc": "A unified inference and post-training framework for accelerated video generation.",
  "url": "https://github.com/hao-ai-lab/FastVideo",
  "homepage": "https://hao-ai-lab.github.io/FastVideo",
  "pushed": "2026-11-03T20:36:58Z",
  "created": "2024-10-24T02:11:32Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "diffusers",
   "diffusion-models",
   "distillation",
   "inference",
   "post-training",
   "video-generation"
  ]
 },
 "chengzeyi/ParaAttention": {
  "stars": 436,
  "forks": 48,
  "license": "NOASSERTION",
  "desc": "https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching",
  "url": "https://github.com/chengzeyi/ParaAttention",
  "homepage": "",
  "pushed": "2025-07-05T11:21:04Z",
  "created": "2024-10-28T11:01:12Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "attention",
   "diffusers",
   "flux",
   "hunyuan-video",
   "inference",
   "inference-engine",
   "parallel-computing",
   "transformers"
  ]
 },
 "kijai/ComfyUI-WanVideoWrapper": {
  "stars": 6806,
  "forks": 710,
  "license": "Apache-2.0",
  "desc": "",
  "url": "https://github.com/kijai/ComfyUI-WanVideoWrapper",
  "homepage": null,
  "pushed": "2026-05-24T13:07:20Z",
  "created": "2025-02-25T18:03:11Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "kijai/ComfyUI-HunyuanVideoWrapper": {
  "stars": 2592,
  "forks": 204,
  "license": null,
  "desc": "",
  "url": "https://github.com/kijai/ComfyUI-HunyuanVideoWrapper",
  "homepage": null,
  "pushed": "2025-08-20T08:38:14Z",
  "created": "2024-12-03T17:09:58Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "Kosinkadink/ComfyUI-VideoHelperSuite": {
  "stars": 1909,
  "forks": 393,
  "license": "GPL-3.0",
  "desc": "Nodes related to video workflows",
  "url": "https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite",
  "homepage": null,
  "pushed": "2026-09-02T06:48:06Z",
  "created": "2023-09-23T23:57:29Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "Comfy-Org/ComfyUI-Manager": {
  "stars": 16711,
  "forks": 2585,
  "license": "GPL-3.0",
  "desc": "ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. Furthermore, this extension provides a hub feature and convenience functions to access a wide range of information within ComfyUI.",
  "url": "https://github.com/Comfy-Org/ComfyUI-Manager",
  "homepage": "",
  "pushed": "2026-11-02T16:10:12Z",
  "created": "2023-04-23T14:36:09Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "mcmonkeyprojects/SwarmUI": {
  "stars": 4741,
  "forks": 483,
  "license": "MIT",
  "desc": "SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.",
  "url": "https://github.com/mcmonkeyprojects/SwarmUI",
  "homepage": "",
  "pushed": "2026-11-03T17:18:01Z",
  "created": "2024-06-21T06:24:53Z",
  "lang": "C#",
  "archived": false,
  "topics": [
   "ai",
   "comfyui",
   "csharp",
   "image-generation",
   "javascript",
   "machine-learning",
   "ml",
   "python",
   "stable-diffusion"
  ]
 },
 "Fannovel16/ComfyUI-Frame-Interpolation": {
  "stars": 1093,
  "forks": 141,
  "license": "MIT",
  "desc": "A custom node set for Video Frame Interpolation in ComfyUI.",
  "url": "https://github.com/Fannovel16/ComfyUI-Frame-Interpolation",
  "homepage": "",
  "pushed": "2026-03-29T02:54:30Z",
  "created": "2023-07-31T15:04:30Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "comfyanonymous/ComfyUI_bitsandbytes_NF4": {
  "stars": 424,
  "forks": 48,
  "license": "AGPL-3.0",
  "desc": "",
  "url": "https://github.com/comfyanonymous/ComfyUI_bitsandbytes_NF4",
  "homepage": null,
  "pushed": "2026-09-29T01:17:00Z",
  "created": "2024-08-11T12:53:29Z",
  "lang": "Python",
  "archived": true,
  "topics": []
 },
 "Tencent-Hunyuan/HunyuanVideo-Avatar": {
  "stars": 2204,
  "forks": 351,
  "license": "NOASSERTION",
  "desc": "",
  "url": "https://github.com/Tencent-Hunyuan/HunyuanVideo-Avatar",
  "homepage": null,
  "pushed": "2025-12-16T12:32:46Z",
  "created": "2025-05-26T11:24:20Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "Francis-Rings/StableAvatar": {
  "stars": 1273,
  "forks": 113,
  "license": "MIT",
  "desc": "[NeurIPS2026] We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a reference image and audio.",
  "url": "https://github.com/Francis-Rings/StableAvatar",
  "homepage": "",
  "pushed": "2026-09-25T01:37:42Z",
  "created": "2025-08-11T11:48:35Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "aigc",
   "avatar-generator",
   "video-generation"
  ]
 },
 "jixiaozhong/Sonic": {
  "stars": 3276,
  "forks": 292,
  "license": "NOASSERTION",
  "desc": "Official implementation of \"Sonic: Shifting Focus to Global Audio Perception in Portrait Animation\"",
  "url": "https://github.com/jixiaozhong/Sonic",
  "homepage": null,
  "pushed": "2026-01-08T11:32:14Z",
  "created": "2024-11-26T03:05:34Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "TMElyralab/MuseTalk": {
  "stars": 6867,
  "forks": 1000,
  "license": "NOASSERTION",
  "desc": "MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting",
  "url": "https://github.com/TMElyralab/MuseTalk",
  "homepage": "",
  "pushed": "2025-09-26T05:44:17Z",
  "created": "2024-03-26T04:14:37Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "lip-sync",
   "virtualhumans"
  ]
 },
 "fudan-generative-vision/hallo2": {
  "stars": 3755,
  "forks": 542,
  "license": "MIT",
  "desc": "[ICLR 2025] Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation",
  "url": "https://github.com/fudan-generative-vision/hallo2",
  "homepage": "https://fudan-generative-vision.github.io/hallo2",
  "pushed": "2025-02-27T03:24:55Z",
  "created": "2024-10-16T09:10:54Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "jdh-algo/JoyVASA": {
  "stars": 884,
  "forks": 90,
  "license": "MIT",
  "desc": "Diffusion-based Portrait and Animal Animation",
  "url": "https://github.com/jdh-algo/JoyVASA",
  "homepage": "https://jdh-algo.github.io/JoyVASA/",
  "pushed": "2026-04-16T08:47:31Z",
  "created": "2024-11-14T12:23:27Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "audio-driven-talking-face",
   "generative-ai",
   "image-animation",
   "lip-sync",
   "portrait-anination",
   "talking-head"
  ]
 },
 "antgroup/ditto-talkinghead": {
  "stars": 929,
  "forks": 168,
  "license": "Apache-2.0",
  "desc": "[ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis",
  "url": "https://github.com/antgroup/ditto-talkinghead",
  "homepage": "https://digital-avatar.github.io/ai/Ditto/",
  "pushed": "2025-11-12T13:58:52Z",
  "created": "2025-01-10T06:28:14Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "audio-driven-portrait-animations",
   "ditto",
   "generative-model",
   "human-animation",
   "talking-face-generation",
   "talking-head",
   "video-generation"
  ]
 },
 "anliyuan/Ultralight-Digital-Human": {
  "stars": 2666,
  "forks": 384,
  "license": null,
  "desc": "一个超轻量级、可以在移动端实时运行的数字人模型",
  "url": "https://github.com/anliyuan/Ultralight-Digital-Human",
  "homepage": null,
  "pushed": "2026-07-22T12:29:48Z",
  "created": "2024-10-10T03:34:47Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "Kedreamix/Linly-Talker": {
  "stars": 3478,
  "forks": 546,
  "license": "MIT",
  "desc": "Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction method. 🤝🤖 It integrates various technologies like Whisper, Linly, Microsoft Speech Services, and SadTalker talking head generation system. 🌟🔬",
  "url": "https://github.com/Kedreamix/Linly-Talker",
  "homepage": "https://kedreamix.github.io/",
  "pushed": "2026-02-10T05:17:05Z",
  "created": "2023-10-17T06:18:27Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "Tencent-Hunyuan/HunyuanPortrait": {
  "stars": 361,
  "forks": 36,
  "license": "NOASSERTION",
  "desc": "[CVPR-2025] The code of HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation",
  "url": "https://github.com/Tencent-Hunyuan/HunyuanPortrait",
  "homepage": "",
  "pushed": "2025-12-07T17:27:14Z",
  "created": "2025-05-27T03:18:41Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "diffusion-models",
   "generative-ai",
   "image-to-video",
   "portrait-animation",
   "talking-head",
   "video-generation"
  ]
 },
 "Huanshere/VideoLingo": {
  "stars": 19055,
  "forks": 2097,
  "license": "Apache-2.0",
  "desc": "Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组",
  "url": "https://github.com/Huanshere/VideoLingo",
  "homepage": "https://docs.videolingo.io",
  "pushed": "2026-09-30T17:03:30Z",
  "created": "2024-08-09T11:19:52Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "ai-translation",
   "dubbing",
   "localization",
   "video-translation",
   "voice-cloning"
  ]
 },
 "krillinai/KrillinAI": {
  "stars": 14131,
  "forks": 1573,
  "license": "Apache-2.0",
  "desc": "Formerly KrillinAI, VideoTranslation and Dubbing Tool for 120+ Languages. Open-source AI workspace for creators, powered by Codex. Video downloader, video translation, create videos, images, audios, and edits with Agents in one place. For your Social Media like YouTube, TikTok, Instagram, etc.",
  "url": "https://github.com/krillinai/OpenCreator",
  "homepage": "https://www.open-creator.ai",
  "pushed": "2026-11-03T14:12:07Z",
  "created": "2024-12-17T01:59:22Z",
  "lang": "TypeScript",
  "archived": false,
  "topics": [
   "agent-skills",
   "codex-cli",
   "deskop-app",
   "dubbing",
   "image-generation",
   "localization",
   "skills",
   "tts",
   "video-editing",
   "video-generation",
   "video-transcription",
   "video-translation"
  ]
 },
 "jianchang512/pyvideotrans": {
  "stars": 19631,
  "forks": 2429,
  "license": "GPL-3.0",
  "desc": "Translate the video from one language to another and embed dubbing & subtitles.",
  "url": "https://github.com/jianchang512/pyvideotrans",
  "homepage": "https://pyvideotrans.com",
  "pushed": "2026-11-03T23:55:01Z",
  "created": "2023-10-02T16:13:19Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "speech-to-text",
   "stt",
   "subtitle-translation",
   "text-to-speech",
   "tts",
   "video-transition"
  ]
 },
 "jianchang512/stt": {
  "stars": 4842,
  "forks": 511,
  "license": "GPL-3.0",
  "desc": "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",
  "url": "https://github.com/jianchang512/stt",
  "homepage": "https://pyvideotrans.com",
  "pushed": "2026-01-22T08:38:53Z",
  "created": "2023-12-28T16:02:55Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "speech",
   "speech-recognition",
   "speech-to-text",
   "stt"
  ]
 },
 "RayVentura/ShortGPT": {
  "stars": 8103,
  "forks": 1174,
  "license": "MIT",
  "desc": "🚀🎬 ShortGPT - Experimental AI framework for youtube shorts / tiktok channel automation",
  "url": "https://github.com/RayVentura/ShortGPT",
  "homepage": "https://short-gpt-dcs.vercel.app",
  "pushed": "2025-02-10T19:33:18Z",
  "created": "2023-06-27T19:25:33Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "ai",
   "artificial-intelligence",
   "automation",
   "autonomous-agents",
   "content",
   "gpt-4",
   "openai",
   "python",
   "video",
   "video-editing"
  ]
 },
 "FujiwaraChoki/MoneyPrinter": {
  "stars": 14144,
  "forks": 1840,
  "license": "MIT",
  "desc": "Automate Creation of YouTube Shorts using MoviePy.",
  "url": "https://github.com/FujiwaraChoki/MoneyPrinter",
  "homepage": "",
  "pushed": "2026-03-26T22:17:17Z",
  "created": "2024-01-31T18:53:24Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "automation",
   "chatgpt",
   "moviepy",
   "python"
  ]
 },
 "wide-trace/open-higgsfield": {
  "stars": 5303,
  "forks": 1147,
  "license": null,
  "desc": "A studio for image and video generation — one prompt bar, each model’s own settings, and every finished run in one gallery.",
  "url": "https://github.com/wide-trace/open-higgsfield",
  "homepage": "https://openhiggsfield.ai",
  "pushed": "2026-09-17T01:53:26Z",
  "created": "2026-08-26T06:09:58Z",
  "lang": "TypeScript",
  "archived": false,
  "topics": []
 },
 "SubtitleEdit/SubtitleEdit": {
  "stars": 14841,
  "forks": 1361,
  "license": "MIT",
  "desc": "the subtitle editor :)",
  "url": "https://github.com/SubtitleEdit/subtitleedit",
  "homepage": "http://www.nikse.dk/SubtitleEdit/Help",
  "pushed": "2026-11-03T19:04:57Z",
  "created": "2014-02-03T08:17:41Z",
  "lang": "C#",
  "archived": false,
  "topics": []
 },
 "ThioJoe/Auto-Synced-Translated-Dubs": {
  "stars": 1751,
  "forks": 168,
  "license": "AGPL-3.0",
  "desc": "Automatically translates the text of a video based on a subtitle file, and then uses AI voice services to create a new dubbed & translated audio track where the speech is synced using the subtitle's timings.",
  "url": "https://github.com/ThioJoe/Auto-Synced-Translated-Dubs",
  "homepage": "",
  "pushed": "2026-05-11T05:50:13Z",
  "created": "2022-12-08T02:40:07Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "ai",
   "dubbing",
   "subtitles",
   "text-to-speech",
   "translation",
   "tts"
  ]
 },
 "k4yt3x/video2x": {
  "stars": 22551,
  "forks": 1967,
  "license": "AGPL-3.0",
  "desc": "A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.",
  "url": "https://github.com/k4yt3x/video2x",
  "homepage": "https://docs.video2x.org",
  "pushed": "2026-03-07T15:39:42Z",
  "created": "2018-02-24T16:34:41Z",
  "lang": "C++",
  "archived": false,
  "topics": [
   "anime4k",
   "frame-interpolation",
   "machine-learning",
   "neural-networks",
   "realcugan",
   "realesrgan",
   "rife",
   "super-resoluion",
   "upscale-video",
   "vulkan"
  ]
 },
 "hzwer/Practical-RIFE": {
  "stars": 1035,
  "forks": 132,
  "license": "MIT",
  "desc": "More practical frame interpolation approach.",
  "url": "https://github.com/hzwer/Practical-RIFE",
  "homepage": "",
  "pushed": "2026-08-27T08:13:43Z",
  "created": "2021-06-16T05:22:06Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "Sanster/IOPaint": {
  "stars": 23297,
  "forks": 2558,
  "license": "Apache-2.0",
  "desc": "Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.",
  "url": "https://github.com/Sanster/IOPaint",
  "homepage": "https://www.iopaint.com/",
  "pushed": "2025-04-29T02:13:17Z",
  "created": "2021-11-15T14:16:40Z",
  "lang": "Python",
  "archived": true,
  "topics": [
   "inpainting",
   "lama",
   "latent-diffusion",
   "mat",
   "pytorch",
   "stable-diffusion",
   "zits"
  ]
 },
 "sczhou/ProPainter": {
  "stars": 7033,
  "forks": 819,
  "license": "NOASSERTION",
  "desc": "[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting",
  "url": "https://github.com/sczhou/ProPainter",
  "homepage": "https://shangchenzhou.com/projects/ProPainter/",
  "pushed": "2026-10-27T04:05:04Z",
  "created": "2023-09-01T13:11:57Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "object-removal",
   "video-completion",
   "video-inpainting",
   "video-outpainting",
   "watermark-removal"
  ]
 },
 "PeterL1n/RobustVideoMatting": {
  "stars": 9586,
  "forks": 1194,
  "license": "GPL-3.0",
  "desc": "Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!",
  "url": "https://github.com/PeterL1n/RobustVideoMatting",
  "homepage": "https://peterl1n.github.io/RobustVideoMatting/",
  "pushed": "2024-04-02T16:26:48Z",
  "created": "2021-08-30T20:57:44Z",
  "lang": "Python",
  "archived": false,
  "topics": [
   "ai",
   "computer-vision",
   "deep-learning",
   "machine-learning",
   "matting"
  ]
 },
 "chaiNNer-org/chaiNNer": {
  "stars": 6133,
  "forks": 381,
  "license": "GPL-3.0",
  "desc": "A node-based image processing GUI aimed at making chaining image processing tasks easy and customizable. Born as an AI upscaling application, chaiNNer has grown into an extremely flexible and powerful programmatic image processing application.",
  "url": "https://github.com/chaiNNer-org/chaiNNer",
  "homepage": "https://chaiNNer.app",
  "pushed": "2026-11-02T21:16:42Z",
  "created": "2021-09-07T22:58:14Z",
  "lang": "Python",
  "archived": false,
  "topics": []
 },
 "upscayl/upscayl": {
  "stars": 51698,
  "forks": 2700,
  "license": "AGPL-3.0",
  "desc": "🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.",
  "url": "https://github.com/upscayl/upscayl",
  "homepage": "https://upscayl.org",
  "pushed": "2026-10-05T19:13:12Z",
  "created": "2022-07-30T17:19:20Z",
  "lang": "TypeScript",
  "archived": false,
  "topics": [
   "ai",
   "electron",
   "esrgan",
   "gigapixel",
   "gigapixel-images",
   "image",
   "image-upscaling",
   "topaz",
   "upscale",
   "upscalerimage",
   "upscayl"
  ]
 },
 "XPixelGroup/BasicSR": {
  "url": "https://github.com/XPixelGroup/BasicSR",
  "stars": 8405,
  "forks": 1412,
  "license": "Apache-2.0",
  "desc": "Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDN",
  "pushed": "2024-05-17T07:34:46Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "TencentARC/GFPGAN": {
  "url": "https://github.com/TencentARC/GFPGAN",
  "stars": 37702,
  "forks": 6278,
  "license": "NOASSERTION",
  "desc": "GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration. - TencentARC/GFPGAN",
  "pushed": "2024-04-02T16:39:30Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "RVC-Project/Retrieval-based-Voice-Conversion-WebUI": {
  "url": "https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI",
  "stars": 39036,
  "forks": 5344,
  "license": "MIT",
  "desc": "Easily train a good VC model with voice data <= 10 mins! - RVC-Project/Retrieval-based-Voice-Conversion-WebUI",
  "pushed": "2026-08-04T07:47:05Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "svc-develop-team/so-vits-svc": {
  "url": "https://github.com/svc-develop-team/so-vits-svc",
  "stars": 28067,
  "forks": 5015,
  "license": "AGPL-3.0",
  "desc": "SoftVC VITS Singing Voice Conversion. Contribute to svc-develop-team/so-vits-svc development by creating an account on GitHub.",
  "pushed": "2023-10-03T15:54:19Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "yl4579/StyleTTS2": {
  "url": "https://github.com/yl4579/StyleTTS2",
  "stars": 6382,
  "forks": 715,
  "license": "MIT",
  "desc": "StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models - yl4579/StyleTTS2",
  "pushed": "2024-03-07T04:49:30Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "SWivid/F5-TTS": {
  "url": "https://github.com/SWivid/F5-TTS",
  "stars": 15507,
  "forks": 2261,
  "license": "MIT",
  "desc": "Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching" - SWivid/F5-TTS",
  "pushed": "2026-11-03T15:05:09Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "SparkAudio/Spark-TTS": {
  "url": "https://github.com/SparkAudio/Spark-TTS",
  "stars": 10993,
  "forks": 1149,
  "license": "Apache-2.0",
  "desc": "Spark-TTS Inference Code. Contribute to SparkAudio/Spark-TTS development by creating an account on GitHub.",
  "pushed": "2025-04-09T10:17:58Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "myshell-ai/OpenVoice": {
  "url": "https://github.com/myshell-ai/OpenVoice",
  "stars": 38134,
  "forks": 4284,
  "license": "MIT",
  "desc": "Instant voice cloning by MIT and MyShell. Audio foundation model. - myshell-ai/OpenVoice",
  "pushed": "2025-04-19T15:59:59Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "2noise/ChatTTS": {
  "url": "https://github.com/2noise/ChatTTS",
  "stars": 39975,
  "forks": 4246,
  "license": "AGPL-3.0",
  "desc": "A generative speech model for daily dialogue. Contribute to 2noise/ChatTTS development by creating an account on GitHub.",
  "pushed": "2026-04-10T16:31:18Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "Plachtaa/VALL-E-X": {
  "url": "https://github.com/Plachtaa/VALL-E-X",
  "stars": 7907,
  "forks": 772,
  "license": "MIT",
  "desc": "An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/ - Plachtaa/VALL-E-X",
  "pushed": "2023-11-03T11:01:10Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "fishaudio/Bert-VITS2": {
  "url": "https://github.com/fishaudio/Bert-VITS2",
  "stars": 8806,
  "forks": 1311,
  "license": "AGPL-3.0",
  "desc": "vits2 backbone with multilingual-bert. Contribute to fishaudio/Bert-VITS2 development by creating an account on GitHub.",
  "pushed": "2026-05-29T05:46:46Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "ace-step/ACE-Step": {
  "url": "https://github.com/ace-step/ACE-Step",
  "stars": 5024,
  "forks": 655,
  "license": "Apache-2.0",
  "desc": "ACE-Step: A Step Towards Music Generation Foundation Model - ace-step/ACE-Step",
  "pushed": "2026-02-15T04:57:54Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "ASLP-lab/DiffRhythm": {
  "url": "https://github.com/ASLP-lab/DiffRhythm",
  "stars": 2358,
  "forks": 281,
  "license": "Apache-2.0",
  "desc": "Di♪♪Rhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion - ASLP-lab/DiffRhythm",
  "pushed": "2025-11-27T13:30:11Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "facebookresearch/audiocraft": {
  "url": "https://github.com/facebookresearch/audiocraft",
  "stars": 23816,
  "forks": 2715,
  "license": "MIT",
  "desc": "Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM wi",
  "pushed": "2025-03-13T16:01:11Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "haoheliu/AudioLDM2": {
  "url": "https://github.com/haoheliu/AudioLDM2",
  "stars": 2644,
  "forks": 209,
  "license": "NOASSERTION",
  "desc": "Text-to-Audio/Music Generation. Contribute to haoheliu/AudioLDM2 development by creating an account on GitHub.",
  "pushed": "2024-09-29T15:05:21Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "adefossez/demucs": {
  "url": "https://github.com/adefossez/demucs",
  "stars": 3496,
  "forks": 329,
  "license": "MIT",
  "desc": "Code for the paper Hybrid Spectrogram and Waveform Source Separation - adefossez/demucs",
  "pushed": "2026-10-26T11:50:46Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "Anjok07/ultimatevocalremovergui": {
  "url": "https://github.com/Anjok07/ultimatevocalremovergui",
  "stars": 26941,
  "forks": 2059,
  "license": "MIT",
  "desc": " GUI for a Vocal Remover that uses Deep Neural Networks. - Anjok07/ultimatevocalremovergui",
  "pushed": "2026-10-06T22:39:25Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "hkchengrex/MMAudio": {
  "url": "https://github.com/hkchengrex/MMAudio",
  "stars": 2303,
  "forks": 270,
  "license": "MIT",
  "desc": "[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis - hkchengrex/MMAudio",
  "pushed": "2026-02-23T06:09:17Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "multimodal-art-projection/YuE": {
  "url": "https://github.com/multimodal-art-projection/YuE",
  "stars": 13054,
  "forks": 1506,
  "license": "Apache-2.0",
  "desc": "YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing. - multimodal-art-projection/YuE",
  "pushed": "2026-11-01T05:46:34Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 },
 "GuijiAI/HeyGem.ai": {
  "url": "https://github.com/GuijiAI/HeyGem.ai",
  "stars": 16211,
  "forks": 2764,
  "license": "NOASSERTION",
  "desc": "🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning. - duixcom/Duix-Avatar",
  "pushed": "2026-04-21T07:06:08Z",
  "archived": false,
  "homepage": null,
  "topics": [],
  "lang": null,
  "created": null
 }
}