IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild
https://github.com/yisol/IDM-VTON
Step 1: Clone the repository
git clone https://github.com/yisol/IDM-VTON
Step 2: Navigate inside the cloned repository
cd IDM-VTON
Step 3: Create virtual environment
python -m venv venv
Step 4: Activate virtual environment
venv\scripts\activate
Step 5: Install requirements
pip install torch2.0.1+cu118 torchvision0.15.2+cu118 torchaudio2.0.2+cu118 -f https://download.pytorch.org/whl/torch_stable.html
pip install pytorch-triton
pip install accelerate0.25.0 torchmetrics1.2.1 tqdm4.66.1 transformers4.36.2 diffusers0.25.0 einops0.7.0 bitsandbytes0.39.0 scipy1.11.1 opencv-python gradio4.24.0 fvcore cloudpickle omegaconf pycocotools basicsr av onnxruntime==1.16.2
python.exe -m pip install --upgrade pip
Step 6: Download checkpoints
IDM-VTON\ckpt\densepose
https://huggingface.co/yisol/IDM-VTON/tree/main/denseposeIDM-VTON\ckpt\humanparsing (parsing_atr.onnx and parsing_lip.onnx)
https://huggingface.co/levihsu/OOTDiffusion/tree/main/checkpoints/humanparsingIDM-VTON\ckpt\openpose\ckpts
https://huggingface.co/lllyasviel/ControlNet/blob/main/annotator/ckpts/body_pose_model.pth
Step 7: Download models
mkdir yisol
cd yisol
git lfs install
git clone https://huggingface.co/yisol/IDM-VTON
Step 8: Launch the gradio UI
venv\scripts\activate
python gradio_demo/app.py
Try Hugging face demo
https://huggingface.co/spaces/yisol/IDM-VTON