[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-70976":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":24,"readmeContent":25,"aiSummary":26,"trendingCount":16,"starSnapshotCount":16,"syncStatus":17,"lastSyncTime":27,"discoverSource":28},70976,"magic-animate","magic-research\u002Fmagic-animate","magic-research","[CVPR 2024] Official repository for \"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model\"","https:\u002F\u002Fshowlab.github.io\u002Fmagicanimate\u002F",null,"Python",10908,1088,103,95,0,2,6,44.11,"BSD 3-Clause \"New\" or \"Revised\" License",false,"main",[],"2026-06-12 02:02:46","\u003C!-- # magic-edit.github.io -->\n\n\u003Cp align=\"center\">\n\n  \u003Ch2 align=\"center\">MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model\u003C\u002Fh2>\n  \u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fscholar.google.com\u002Fcitations?user=-4iADzMAAAAJ&hl=en\">\u003Cstrong>Zhongcong Xu\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"http:\u002F\u002Fjeff95.me\u002F\">\u003Cstrong>Jianfeng Zhang\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fscholar.google.com.sg\u002Fcitations?user=8gm-CYYAAAAJ&hl=en\">\u003Cstrong>Jun Hao Liew\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fhanshuyan.github.io\u002F\">\u003Cstrong>Hanshu Yan\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fscholar.google.com\u002Fcitations?user=stQQf7wAAAAJ&hl=en\">\u003Cstrong>Jia-Wei Liu\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fzhangchenxu528.github.io\u002F\">\u003Cstrong>Chenxu Zhang\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fsites.google.com\u002Fsite\u002Fjshfeng\u002Fhome\">\u003Cstrong>Jiashi Feng\u003C\u002Fstrong>\u003C\u002Fa>\n    ·\n    \u003Ca href=\"https:\u002F\u002Fsites.google.com\u002Fview\u002Fshowlab\">\u003Cstrong>Mike Zheng Shou\u003C\u002Fstrong>\u003C\u002Fa>\n    \u003Cbr>\n    \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2311.16498\">\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FarXiv-MagicAnimate-red' alt='Paper PDF'>\u003C\u002Fa>\n        \u003Ca href='https:\u002F\u002Fshowlab.github.io\u002Fmagicanimate'>\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FProject_Page-MagicAnimate-green' alt='Project Page'>\u003C\u002Fa>\n        \u003Ca href='https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fzcxu-eric\u002Fmagicanimate'>\u003Cimg src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%F0%9F%A4%97%20Hugging%20Face-Spaces-blue'>\u003C\u002Fa>\n    \u003Cbr>\n    \u003Cb>National University of Singapore   |    ByteDance\u003C\u002Fb>\n  \u003C\u002Fp>\n  \n  \u003Ctable align=\"center\">\n    \u003Ctr>\n    \u003Ctd>\n      \u003Cimg src=\"assets\u002Fteaser\u002Ft4.gif\">\n    \u003C\u002Ftd>\n    \u003Ctd>\n      \u003Cimg src=\"assets\u002Fteaser\u002Ft2.gif\">\n    \u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftable>\n\n## 📢 News\n* **[2023.12.4]** Release inference code and gradio demo. We are working to improve MagicAnimate, stay tuned!\n* **[2023.11.23]** Release MagicAnimate paper and project page.\n\n## 🏃‍♂️ Getting Started\nDownload the pretrained base models for [StableDiffusion V1.5](https:\u002F\u002Fhuggingface.co\u002Frunwayml\u002Fstable-diffusion-v1-5) and [MSE-finetuned VAE](https:\u002F\u002Fhuggingface.co\u002Fstabilityai\u002Fsd-vae-ft-mse).\n\nDownload our MagicAnimate [checkpoints](https:\u002F\u002Fhuggingface.co\u002Fzcxu-eric\u002FMagicAnimate).\n\nPlease follow the huggingface download instructions to download the above models and checkpoints, `git lfs` is recommended.\n\nPlace the based models and checkpoints as follows:\n```bash\nmagic-animate\n|----pretrained_models\n  |----MagicAnimate\n    |----appearance_encoder\n      |----diffusion_pytorch_model.safetensors\n      |----config.json\n    |----densepose_controlnet\n      |----diffusion_pytorch_model.safetensors\n      |----config.json\n    |----temporal_attention\n      |----temporal_attention.ckpt\n  |----sd-vae-ft-mse\n    |----config.json\n    |----diffusion_pytorch_model.safetensors\n  |----stable-diffusion-v1-5\n    |----scheduler\n       |----scheduler_config.json\n    |----text_encoder\n       |----config.json\n       |----pytorch_model.bin\n    |----tokenizer (all)\n    |----unet\n       |----diffusion_pytorch_model.bin\n       |----config.json\n    |----v1-5-pruned-emaonly.safetensors\n|----...\n```\n\n## ⚒️ Installation\nprerequisites: `python>=3.8`, `CUDA>=11.3`, and `ffmpeg`.\n\nInstall with `conda`: \n```bash\nconda env create -f environment.yaml\nconda activate manimate\n```\nor `pip`:\n```bash\npip3 install -r requirements.txt\n```\n\n## 💃 Inference\nRun inference on single GPU:\n```bash\nbash scripts\u002Fanimate.sh\n```\nRun inference with multiple GPUs:\n```bash\nbash scripts\u002Fanimate_dist.sh\n```\n\n## 🎨 Gradio Demo \n\n#### Online Gradio Demo:\nTry our [online gradio demo](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002Fzcxu-eric\u002Fmagicanimate) quickly.\n\n#### Local Gradio Demo:\nLaunch local gradio demo on single GPU:\n```bash\npython3 -m demo.gradio_animate\n```\nLaunch local gradio demo if you have multiple GPUs:\n```bash\npython3 -m demo.gradio_animate_dist\n```\nThen open gradio demo in local browser.\n\n## 🙏 Acknowledgements\nWe would like to thank [AK(@_akhaliq)](https:\u002F\u002Ftwitter.com\u002F_akhaliq?lang=en) and huggingface team for the help of setting up oneline gradio demo.\n\n## 🎓 Citation\nIf you find this codebase useful for your research, please use the following entry.\n```BibTeX\n@inproceedings{xu2023magicanimate,\n    author    = {Xu, Zhongcong and Zhang, Jianfeng and Liew, Jun Hao and Yan, Hanshu and Liu, Jia-Wei and Zhang, Chenxu and Feng, Jiashi and Shou, Mike Zheng},\n    title     = {MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model},\n    booktitle = {arXiv},\n    year      = {2023}\n}\n```\n\n","MagicAnimate 是一个利用扩散模型实现时间一致的人体图像动画生成的项目。该项目通过先进的深度学习技术，特别是扩散模型和时空注意力机制，能够根据给定的输入生成流畅自然的人体动作序列。它支持从单张或多张静态图片中创建动态视频内容，且在保持原始人物外观特征的同时，确保动作连贯性。适用于需要高质量人体动画的应用场景，如虚拟角色制作、游戏开发以及影视特效等领域。","2026-06-11 03:35:15","high_star"]