Home

Awesome

<!-- # magic-edit.github.io --> <p align="center"> <h2 align="center">MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model</h2> <p align="center"> <a href="https://scholar.google.com/citations?user=-4iADzMAAAAJ&hl=en"><strong>Zhongcong Xu</strong></a> · <a href="http://jeff95.me/"><strong>Jianfeng Zhang</strong></a> · <a href="https://scholar.google.com.sg/citations?user=8gm-CYYAAAAJ&hl=en"><strong>Jun Hao Liew</strong></a> · <a href="https://hanshuyan.github.io/"><strong>Hanshu Yan</strong></a> · <a href="https://scholar.google.com/citations?user=stQQf7wAAAAJ&hl=en"><strong>Jia-Wei Liu</strong></a> · <a href="https://zhangchenxu528.github.io/"><strong>Chenxu Zhang</strong></a> · <a href="https://sites.google.com/site/jshfeng/home"><strong>Jiashi Feng</strong></a> · <a href="https://sites.google.com/view/showlab"><strong>Mike Zheng Shou</strong></a> <br> <br> <a href="https://arxiv.org/abs/2311.16498"><img src='https://img.shields.io/badge/arXiv-MagicAnimate-red' alt='Paper PDF'></a> <a href='https://showlab.github.io/magicanimate'><img src='https://img.shields.io/badge/Project_Page-MagicAnimate-green' alt='Project Page'></a> <a href='https://huggingface.co/spaces/zcxu-eric/magicanimate'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue'></a> <br> <b>National University of Singapore &nbsp; | &nbsp; ByteDance</b> </p> <table align="center"> <tr> <td> <img src="assets/teaser/t4.gif"> </td> <td> <img src="assets/teaser/t2.gif"> </td> </tr> </table>

📢 News

🏃‍♂️ Getting Started

Download the pretrained base models for StableDiffusion V1.5 and MSE-finetuned VAE.

Download our MagicAnimate checkpoints.

Please follow the huggingface download instructions to download the above models and checkpoints, git lfs is recommended.

Place the based models and checkpoints as follows:

magic-animate
|----pretrained_models
  |----MagicAnimate
    |----appearance_encoder
      |----diffusion_pytorch_model.safetensors
      |----config.json
    |----densepose_controlnet
      |----diffusion_pytorch_model.safetensors
      |----config.json
    |----temporal_attention
      |----temporal_attention.ckpt
  |----sd-vae-ft-mse
    |----config.json
    |----diffusion_pytorch_model.safetensors
  |----stable-diffusion-v1-5
    |----scheduler
       |----scheduler_config.json
    |----text_encoder
       |----config.json
       |----pytorch_model.bin
    |----tokenizer (all)
    |----unet
       |----diffusion_pytorch_model.bin
       |----config.json
    |----v1-5-pruned-emaonly.safetensors
|----...

⚒️ Installation

prerequisites: python>=3.8, CUDA>=11.3, and ffmpeg.

Install with conda:

conda env create -f environment.yaml
conda activate manimate

or pip:

pip3 install -r requirements.txt

💃 Inference

Run inference on single GPU:

bash scripts/animate.sh

Run inference with multiple GPUs:

bash scripts/animate_dist.sh

🎨 Gradio Demo

Online Gradio Demo:

Try our online gradio demo quickly.

Local Gradio Demo:

Launch local gradio demo on single GPU:

python3 -m demo.gradio_animate

Launch local gradio demo if you have multiple GPUs:

python3 -m demo.gradio_animate_dist

Then open gradio demo in local browser.

🙏 Acknowledgements

We would like to thank AK(@_akhaliq) and huggingface team for the help of setting up oneline gradio demo.

🎓 Citation

If you find this codebase useful for your research, please use the following entry.

@inproceedings{xu2023magicanimate,
    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},
    title     = {MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model},
    booktitle = {arXiv},
    year      = {2023}
}