head.mp4
- System requirement: Ubuntu20.04
- Tested GPUs: A100, RTX3090
Create conda environment:
conda create -n champ python=3.10
conda activate champInstall packages with pip:
pip install git+https://github.com/painebenjamin/champ.gitTo inference, simply instantiate the pipeline and pass your arguments.
from champ import CHAMPPipeline
pipeline = CHAMPPipeline.from_pretrained(
"benjamin-paine/champ",
torch_dtype=torch.float16,
variant="fp16",
device="cuda"
).to("cuda", dtype=torch.float16)
result = pipeline(
reference: PIL.Image.Image,
guidance: Dict[str, List[PIL.Image.Image]],
width: int,
height: int,
video_length: int,
num_inference_steps: int,
guidance_scale: float
).videos
# Result is a list of PIL ImagesOne small set of example data is provided in this repository, with a script to execute. Here is the command for inference:
python inference.pyAnimation results will be saved as output.mp4.
We thank the authors of MagicAnimate, Animate Anyone, and AnimateDiff for their excellent work. Our project is built upon Moore-AnimateAnyone, and we are grateful for their open-source contributions.
If you find our work useful for your research, please consider citing the paper:
@misc{zhu2024champ,
title={Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance},
author={Shenhao Zhu and Junming Leo Chen and Zuozhuo Dai and Yinghui Xu and Xun Cao and Yao Yao and Hao Zhu and Siyu Zhu},
year={2024},
eprint={2403.14781},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
Multiple research positions are open at the Generative Vision Lab, Fudan University! Include:
- Research assistant
- Postdoctoral researcher
- PhD candidate
- Master students
Interested individuals are encouraged to contact us at siyuzhu@fudan.edu.cn for further information.