This repository is the official implementation of Magic Clothing
Magic Clothing is a branch version of OOTDiffusion, focusing on controllable garment-driven image synthesis
Magic Clothing: Controllable Garment-Driven Image Synthesis [arXiv paper]
Weifeng Chen*, Tao Gu*, Yuhao Xu*+, Chengcai Chen
* Equal contribution + Corresponding author
Xiao-i Research
๐ข๐ข We are continuing to improve this project. Please check earlyAccess branch for new features and updates : )
๐ฅ [2024/4/16] Our paper is available now!
๐ฅ [2024/3/8] We release the model weights trained on the 768 resolution. The strength of clothing and text prompts can be independently adjusted.
๐ค Hugging Face link
๐ฅ [2024/2/28] We support IP-Adapter-FaceID with ControlNet-Openpose now! A portrait and a reference pose image can be used as additional conditions.
Have fun with gradio_ipadapter_openpose.py
๐ฅ [2024/2/23] We support IP-Adapter-FaceID now! A portrait image can be used as an additional condition.
Have fun with gradio_ipadapter_faceid.py
- Clone the repository
git clone https://github.com/ShineChen1024/MagicClothing.git
- Create a conda environment and install the required packages
conda create -n magicloth python==3.10
conda activate magicloth
pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2
pip install -r requirements.txt
- Python demo
512 weights
python inference.py --cloth_path [your cloth path] --model_path [your model checkpoints path]
768 weights
python inference.py --cloth_path [your cloth path] --model_path [your model checkpoints path] --enable_cloth_guidance
- Gradio demo
512 weights
python gradio_generate.py --model_path [your model checkpoints path]
768 weights
python gradio_generate.py --model_path [your model checkpoints path] --enable_cloth_guidance
@article{chen2024magic,
title={Magic Clothing: Controllable Garment-Driven Image Synthesis},
author={Chen, Weifeng and Gu, Tao and Xu, Yuhao and Chen, Chengcai},
journal={arXiv preprint arXiv:2404.09512},
year={2024}
}
- Paper
- Gradio demo
- Inference code
- Model weights
- Training code