---
license: creativeml-openrail-m
language:
- en
---
# MusePose ComfyUI installation script

MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation. Zhengyan Tong,
Chao Li,
Zhaokang Chen,
Bin Wu<sup>†</sup>,
Wenjiang Zhou
(<sup>†</sup>Corresponding Author, benbinwu@tencent.com)

**[github](https://github.com/TMElyralab/MusePose)**    **[huggingface](https://huggingface.co/TMElyralab/MusePose)**    **space (comming soon)**    **Project (comming soon)**    **Technical report (comming soon)**

# This is a script to quickly install MusePose ComfyUI node

## Installation script

Save the code to a script file like `install_musepose.sh` under the ComfyUI directory, and execute it (`source install_musepose.sh`) to install the node.
```
#!/bin/bash
cd custom_nodes/
rm -rf Comfyui-MusePose
git clone https://github.com/TMElyralab/Comfyui-MusePose.git
cd Comfyui-MusePose
apt update
apt install ffmpeg
pip install -r requirements.txt
pip install openmim
mim install mmengine "mmcv>=2.0.1"  "mmdet>=3.1.0"  "mmpose>=1.1.0"

# Download weights
huggingface-cli download --local-dir /tmp/download hoveyc/musepose
rm -rf pretrained_weights
mv /tmp/download/pretrained_weights .
```

If no errors occur, restart the ComfyUI and it should work.