Qoboty/magic-animate

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

Zhongcong Xu · Jianfeng Zhang · Jun Hao Liew · Hanshu Yan · Jia-Wei Liu · Chenxu Zhang · Jiashi Feng · Mike Zheng Shou


National University of Singapore   |   ByteDance

📢 News

• [2023.12.4] Release inference code and gradio demo. We are working to improve MagicAnimate, stay tuned!
• [2023.11.23] Release MagicAnimate paper and project page.

🏃‍♂️ Getting Started

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

Download our MagicAnimate checkpoints.

Place them 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
    |----...
  |----stable-diffusion-v1-5
    |----...
|----...

⚒️ 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 graio 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}
}