WearCast

This repository is the official implementation of WearCast

🤗 Try out WearCast

WearCast: High-Fidelity Men's Half-Body Virtual Try-On Based on Latent Diffusion
A highly optimized pipeline tailored specifically for Men's half-body clothing outfitting.

Our model checkpoints trained on VITON-HD (half-body) have been released

• 🤗 Hugging Face link for checkpoints (wearcast, humanparsing, and openpose)
• 📢📢 We support ONNX for humanparsing now. Most environmental issues should have been addressed : )
• Please also download clip-vit-large-patch14 into checkpoints folder
• We've only tested our code and models on Linux (Ubuntu 22.04)

   

Installation

1. Clone the repository

git clone https://github.com/Abdokamal1532/WearCast_AI

2. Create a conda environment and install the required packages

conda create -n wearcast python==3.10
conda activate wearcast
pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2
pip install -r requirements.txt

Quick Start (Gradio UI)

To launch the interactive Men's Virtual Try-On interface locally:

cd run
python gradio_wearcast.py

Open http://localhost:7865 in your browser!

Command Line Inference

1. Men's Half-body model

cd run
python run_wearcast.py --model_path <model-image-path> --cloth_path <cloth-image-path> --scale 2.0 --sample 4

Citation

@article{xu2024wearcast,
  title={WearCast: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on},
  author={Xu, Yuhao and Gu, Tao and Chen, Weifeng and Chen, Chengcai},
  journal={arXiv preprint arXiv:2403.01779},
  year={2024}
}

Star History

TODO List

• Paper
• Gradio demo
• Inference code
• Model weights
• Training code