[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-71188":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":19,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":21,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":27,"readmeContent":28,"aiSummary":29,"trendingCount":16,"starSnapshotCount":16,"syncStatus":30,"lastSyncTime":31,"discoverSource":32},71188,"VideoCrafter","AILab-CVC\u002FVideoCrafter","AILab-CVC","VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","https:\u002F\u002Failab-cvc.github.io\u002Fvideocrafter2\u002F",null,"Python",5062,411,65,71,0,1,9,65.24,"Other",false,"main",[24,25,26],"image-to-video","text-to-video","video-generation","2026-06-12 04:00:59","\n## ___***VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models***___\n\n\u003Ca href='https:\u002F\u002Failab-cvc.github.io\u002Fvideocrafter2\u002F'>\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FProject-Page-green'>\u003C\u002Fa> \n\u003Ca href='https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.09047'>\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FTechnique-Report-red'>\u003C\u002Fa> \n[![Discord](https:\u002F\u002Fdcbadge.vercel.app\u002Fapi\u002Fserver\u002FrrayYqZ4tf?style=flat)](https:\u002F\u002Fdiscord.gg\u002FrrayYqZ4tf)\n\u003Ca href='https:\u002F\u002Fhuggingface.co\u002Fspaces\u002FVideoCrafter\u002FVideoCrafter'>\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%F0%9F%A4%97%20Hugging%20Face-Model-blue'>\u003C\u002Fa>\n[![GitHub](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FVideoCrafter\u002FVideoCrafter?style=social)](https:\u002F\u002Fgithub.com\u002FVideoCrafter\u002FVideoCrafter)\n\n### 🔥🔥 Our dedicated high-resolution I2V model is released at: :point_right:[DynamiCrafter](https:\u002F\u002Fgithub.com\u002FDoubiiu\u002FDynamiCrafter)!!!\n\n[![](https:\u002F\u002Fimg.youtube.com\u002Fvi\u002F0NfmIsNAg-g\u002F0.jpg)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=0NfmIsNAg-g)\n\n### 🔥The VideoCrafter2 Large improvements over VideoCrafter1 with limited data. Better Motion, Better Concept Combination!!!\n\nPlease Join us and create your own film on [Discord\u002FFloor33](https:\u002F\u002Fdiscord.gg\u002FrrayYqZ4tf).\n\n##### 🎥 Exquisite film, produced by VideoCrafter2, directed by Human\n [![IMAGE ALT TEXT HERE](https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FTUsFkW0tK-s\u002F0.jpg)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=TUsFkW0tK-s)\n \n## 🔆 Introduction\n\n🤗🤗🤗 VideoCrafter is an open-source video generation and editing toolbox for crafting video content.   \nIt currently includes the Text2Video and Image2Video models:\n\n### 1. Generic Text-to-video Generation\nClick the GIF to access the high-resolution video.\n\n\u003Ctable class=\"center\">\n  \u003Ctd>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAILab-CVC\u002FVideoCrafter\u002Fassets\u002F18735168\u002Fd20ee09d-fc32-44a8-9e9a-f12f44b30411\">\u003Cimg src=assets\u002Ft2v\u002Ftom.gif width=\"320\">\u003C\u002Ftd>\n  \u003Ctd>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAILab-CVC\u002FVideoCrafter\u002Fassets\u002F18735168\u002Ff1d9f434-28e8-44f6-a9b8-cffd67e4574d\">\u003Cimg src=assets\u002Ft2v\u002Fchild.gif width=\"320\">\u003C\u002Ftd>\n  \u003Ctd>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAILab-CVC\u002FVideoCrafter\u002Fassets\u002F18735168\u002Fbbcfef0e-d8fb-4850-adc0-d8f937c2fa36\">\u003Cimg src=assets\u002Ft2v\u002Fwoman.gif width=\"320\">\u003C\u002Ftd>\n  \u003Ctr>\n  \u003Ctd style=\"text-align:center;\" width=\"320\">\"Tom Cruise's face reflects focus, his eyes filled with purpose and drive.\"\u003C\u002Ftd>\n  \u003Ctd style=\"text-align:center;\" width=\"320\">\"A child excitedly swings on a rusty swing set, laughter filling the air.\"\u003C\u002Ftd>\n  \u003Ctd style=\"text-align:center;\" width=\"320\">\"A young woman with glasses is jogging in the park wearing a pink headband.\"\u003C\u002Ftd>\n  \u003Ctr>\n\u003C\u002Ftable >\n\n\u003Ctable class=\"center\">\n  \u003Ctd>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAILab-CVC\u002FVideoCrafter\u002Fassets\u002F18735168\u002F7edafc5a-750e-45f3-a46e-b593751a4b12\">\u003Cimg src=assets\u002Ft2v\u002Fcouple.gif width=\"320\">\u003C\u002Ftd>\n  \u003Ctd>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAILab-CVC\u002FVideoCrafter\u002Fassets\u002F18735168\u002F37fe41c8-31fb-4e77-bcf9-fa159baa6d86\">\u003Cimg src=assets\u002Ft2v\u002Frabbit.gif width=\"320\">\u003C\u002Ftd>\n  \u003Ctd>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAILab-CVC\u002FVideoCrafter\u002Fassets\u002F18735168\u002F09791a46-a243-41b8-a6bb-892cdd3a83a2\">\u003Cimg src=assets\u002Ft2v\u002Fduck.gif width=\"320\">\u003C\u002Ftd>\n  \u003Ctr>\n  \u003Ctd style=\"text-align:center;\" width=\"320\">\"With the style of van gogh, A young couple dances under the moonlight by the lake.\"\u003C\u002Ftd>\n  \u003Ctd style=\"text-align:center;\" width=\"320\">\"A rabbit, low-poly game art style\"\u003C\u002Ftd>\n  \u003Ctd style=\"text-align:center;\" width=\"320\">\"Impressionist style, a yellow rubber duck floating on the wave on the sunset\"\u003C\u002Ftd>\n  \u003Ctr>\n\u003C\u002Ftable >\n\n### 2. Generic Image-to-video Generation\n\n\u003Ctable class=\"center\">\n  \u003Ctd>\u003Cimg src=assets\u002Fi2v\u002Finput\u002Fblackswan.png width=\"170\">\u003C\u002Ftd>\n  \u003Ctd>\u003Cimg src=assets\u002Fi2v\u002Finput\u002Fhorse.png width=\"170\">\u003C\u002Ftd>\n  \u003Ctd>\u003Cimg src=assets\u002Fi2v\u002Finput\u002Fchair.png width=\"170\">\u003C\u002Ftd>\n  \u003Ctd>\u003Cimg src=assets\u002Fi2v\u002Finput\u002Fsunset.png width=\"170\">\u003C\u002Ftd>\n  \u003Ctr>\n  \u003Ctd>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAILab-CVC\u002FVideoCrafter\u002Fassets\u002F18735168\u002F1a57edd9-3fd2-4ce9-8313-89aca95b6ec7\">\u003Cimg src=assets\u002Fi2v\u002Fblackswan.gif width=\"170\">\u003C\u002Ftd>\n  \u003Ctd>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAILab-CVC\u002FVideoCrafter\u002Fassets\u002F18735168\u002Fd671419d-ae49-4889-807e-b841aef60e8a\">\u003Cimg src=assets\u002Fi2v\u002Fhorse.gif width=\"170\">\u003C\u002Ftd>\n  \u003Ctd>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAILab-CVC\u002FVideoCrafter\u002Fassets\u002F18735168\u002F39d730d9-7b47-4132-bdae-4d18f3e651ee\">\u003Cimg src=assets\u002Fi2v\u002Fchair.gif width=\"170\">\u003C\u002Ftd>\n  \u003Ctd>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAILab-CVC\u002FVideoCrafter\u002Fassets\u002F18735168\u002Fdc8dd0d5-a80d-4f31-94db-f9ea0b13172b\">\u003Cimg src=assets\u002Fi2v\u002Fsunset.gif width=\"170\">\u003C\u002Ftd>\n  \u003Ctr>\n  \u003Ctd style=\"text-align:center;\" width=\"170\">\"a black swan swims on the pond\"\u003C\u002Ftd>\n  \u003Ctd style=\"text-align:center;\" width=\"170\">\"a girl is riding a horse fast on grassland\"\u003C\u002Ftd>\n  \u003Ctd style=\"text-align:center;\" width=\"170\">\"a boy sits on a chair facing the sea\"\u003C\u002Ftd>\n  \u003Ctd style=\"text-align:center;\" width=\"170\">\"two galleons moving in the wind at sunset\"\u003C\u002Ftd>\n\n\u003C\u002Ftable >\n\n:boom: **You are highly recommended to try our dedicated I2V model [DynamiCrafter](https:\u002F\u002Fgithub.com\u002FDoubiiu\u002FDynamiCrafter): Higher resolution, Better Dynamics, More Coherence!!!**\n\n---\n\n## 📝 Changelog\n- __[2024.02.05]__: 🔥🔥 Release new I2V model with the resolution of 640x1024 of VideoCrafter1\u002FDynamiCrafter. \n\n- __[2024.01.26]__: Release the 512x320 checkpoint of VideoCrafter2. \n\n- __[2024.01.18]__: Release the [VideoCrafter2](https:\u002F\u002Failab-cvc.github.io\u002Fvideocrafter2\u002F) and [Tech Report](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.09047)!\n\n- __[2023.10.30]__: Release [VideoCrafter1](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.19512) Technical Report!\n\n- __[2023.10.13]__: Release the VideoCrafter1, High Quality Video Generation!\n\n- __[2023.08.14]__: Release a new version of VideoCrafter on [Discord\u002FFloor33](https:\u002F\u002Fdiscord.gg\u002FuHaQuThT). Please join us to create your own film!\n\n- __[2023.04.18]__: Release a VideoControl model with most of the watermarks removed!\n\n- __[2023.04.05]__: Release pretrained Text-to-Video models, VideoLora models, and inference code.\n\u003Cbr>\n\n\n## ⏳ Models\n\n|T2V-Models|Resolution|Checkpoints|\n|:---------|:---------|:--------|\n|VideoCrafter2|320x512|[Hugging Face](https:\u002F\u002Fhuggingface.co\u002FVideoCrafter\u002FVideoCrafter2\u002Fblob\u002Fmain\u002Fmodel.ckpt)\n|VideoCrafter1|576x1024|[Hugging Face](https:\u002F\u002Fhuggingface.co\u002FVideoCrafter\u002FText2Video-1024\u002Fblob\u002Fmain\u002Fmodel.ckpt)\n|VideoCrafter1|320x512|[Hugging Face](https:\u002F\u002Fhuggingface.co\u002FVideoCrafter\u002FText2Video-512\u002Fblob\u002Fmain\u002Fmodel.ckpt)\n\n|I2V-Models|Resolution|Checkpoints|\n|:---------|:---------|:--------|\n|VideoCrafter1|640x1024|[Hugging Face](https:\u002F\u002Fhuggingface.co\u002FDoubiiu\u002FDynamiCrafter_1024\u002Fblob\u002Fmain\u002Fmodel.ckpt)\n|VideoCrafter1|320x512|[Hugging Face](https:\u002F\u002Fhuggingface.co\u002FVideoCrafter\u002FImage2Video-512\u002Fblob\u002Fmain\u002Fmodel.ckpt)\n\n\n\n## ⚙️ Setup\n\n### 1. Install Environment via Anaconda (Recommended)\n```bash\nconda create -n videocrafter python=3.8.5\nconda activate videocrafter\npip install -r requirements.txt\n```\n\n\n## 💫 Inference \n### 1. Text-to-Video\n\n1) Download pretrained T2V models via [Hugging Face](https:\u002F\u002Fhuggingface.co\u002FVideoCrafter\u002FVideoCrafter2\u002Fblob\u002Fmain\u002Fmodel.ckpt), and put the `model.ckpt` in `checkpoints\u002Fbase_512_v2\u002Fmodel.ckpt`.\n2) Input the following commands in terminal.\n```bash\n  sh scripts\u002Frun_text2video.sh\n```\n\n### 2. Image-to-Video\n\n1) Download pretrained I2V models via [Hugging Face](https:\u002F\u002Fhuggingface.co\u002FVideoCrafter\u002FImage2Video-512-v1.0\u002Fblob\u002Fmain\u002Fmodel.ckpt), and put the `model.ckpt` in `checkpoints\u002Fi2v_512_v1\u002Fmodel.ckpt`.\n2) Input the following commands in terminal.\n```bash\n  sh scripts\u002Frun_image2video.sh\n```\n\n### 3. Local Gradio demo\n\n1. Download the pretrained T2V and I2V models and put them in the corresponding directory according to the previous guidelines.\n2. Input the following commands in terminal.\n```bash\n  python gradio_app.py\n```\n\n---\n## 📋 Technical Report\n😉 VideoCrafter2 Tech report: [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https:\u002F\u002Farxiv.org\u002Fabs\u002F2401.09047)\n\n😉 VideoCrafter1 Tech report: [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https:\u002F\u002Farxiv.org\u002Fabs\u002F2310.19512)\n\u003Cbr>\n\n## 😉 Citation\nThe technical report is currently unavailable as it is still in preparation. You can cite the paper of our image-to-video model and related base model.\n```\n@misc{chen2024videocrafter2,\n      title={VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models}, \n      author={Haoxin Chen and Yong Zhang and Xiaodong Cun and Menghan Xia and Xintao Wang and Chao Weng and Ying Shan},\n      year={2024},\n      eprint={2401.09047},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV}\n}\n\n@misc{chen2023videocrafter1,\n      title={VideoCrafter1: Open Diffusion Models for High-Quality Video Generation}, \n      author={Haoxin Chen and Menghan Xia and Yingqing He and Yong Zhang and Xiaodong Cun and Shaoshu Yang and Jinbo Xing and Yaofang Liu and Qifeng Chen and Xintao Wang and Chao Weng and Ying Shan},\n      year={2023},\n      eprint={2310.19512},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV}\n}\n\n@article{xing2023dynamicrafter,\n      title={DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors}, \n      author={Jinbo Xing and Menghan Xia and Yong Zhang and Haoxin Chen and Xintao Wang and Tien-Tsin Wong and Ying Shan},\n      year={2023},\n      eprint={2310.12190},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV}\n}\n\n@article{he2022lvdm,\n      title={Latent Video Diffusion Models for High-Fidelity Long Video Generation}, \n      author={Yingqing He and Tianyu Yang and Yong Zhang and Ying Shan and Qifeng Chen},\n      year={2022},\n      eprint={2211.13221},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV}\n}\n```\n\n\n## 🤗 Acknowledgements\nOur codebase builds on [Stable Diffusion](https:\u002F\u002Fgithub.com\u002FStability-AI\u002Fstablediffusion). \nThanks the authors for sharing their awesome codebases! \n\n\n## 📢 Disclaimer\nWe develop this repository for RESEARCH purposes, so it can only be used for personal\u002Fresearch\u002Fnon-commercial purposes.\n****\n","VideoCrafter2 是一个用于生成高质量视频的开源工具箱，特别针对数据限制进行了优化。该项目主要提供文本到视频（Text-to-Video）和图像到视频（Image-to-Video）两种核心功能，能够根据输入的文字或图片自动生成相应的动态视频内容，显著提升了在有限数据条件下的视频质量和动作流畅度。它采用先进的扩散模型技术，在概念组合与运动表现上均有出色表现。适用于需要快速创建创意视频内容的各种场景，如广告制作、个人创作以及教育演示等。",2,"2026-06-11 03:36:28","high_star"]