CatVTON / README.md
abubakar123456's picture
Upload 4 files
5eaa703 verified
|
raw
history blame
9.22 kB
---
license: cc-by-nc-sa-4.0
---
# 🐈 CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models
<div style="display: flex; justify-content: center; align-items: center;">
<a href="http://arxiv.org/abs/2407.15886" style="margin: 0 2px;">
<img src='https://img.shields.io/badge/arXiv-2407.15886-red?style=flat&logo=arXiv&logoColor=red' alt='arxiv'>
</a>
<a href='https://huggingface.co/zhengchong/CatVTON' style="margin: 0 2px;">
<img src='https://img.shields.io/badge/Hugging Face-ckpts-orange?style=flat&logo=HuggingFace&logoColor=orange' alt='huggingface'>
</a>
<a href="https://github.com/Zheng-Chong/CatVTON" style="margin: 0 2px;">
<img src='https://img.shields.io/badge/GitHub-Repo-blue?style=flat&logo=GitHub' alt='GitHub'>
</a>
<a href="http://120.76.142.206:8888" style="margin: 0 2px;">
<img src='https://img.shields.io/badge/Demo-Gradio-gold?style=flat&logo=Gradio&logoColor=red' alt='Demo'>
</a>
<a href="https://huggingface.co/spaces/zhengchong/CatVTON" style="margin: 0 2px;">
<img src='https://img.shields.io/badge/Space-ZeroGPU-orange?style=flat&logo=Gradio&logoColor=red' alt='Demo'>
</a>
<a href='https://zheng-chong.github.io/CatVTON/' style="margin: 0 2px;">
<img src='https://img.shields.io/badge/Webpage-Project-silver?style=flat&logo=&logoColor=orange' alt='webpage'>
</a>
<a href="https://github.com/Zheng-Chong/CatVTON/LICENCE" style="margin: 0 2px;">
<img src='https://img.shields.io/badge/License-CC BY--NC--SA--4.0-lightgreen?style=flat&logo=Lisence' alt='License'>
</a>
</div>
**CatVTON** is a simple and efficient virtual try-on diffusion model with ***1) Lightweight Network (899.06M parameters totally)***, ***2) Parameter-Efficient Training (49.57M parameters trainable)*** and ***3) Simplified Inference (< 8G VRAM for 1024X768 resolution)***.
## Updates
- **`2024/08/10`**: Our πŸ€— [**HuggingFace Space**](https://huggingface.co/spaces/zhengchong/CatVTON) is available now! Thanks for the grant from [**ZeroGPU**](https://huggingface.co/zero-gpu-explorers)!
- **`2024/08/09`**: [**Evaluation code**](https://github.com/Zheng-Chong/CatVTON?tab=readme-ov-file#3-calculate-metrics) is provided to calculate metrics πŸ“š.
- **`2024/07/27`**: We provide code and workflow for deploying CatVTON on [**ComfyUI**](https://github.com/Zheng-Chong/CatVTON?tab=readme-ov-file#comfyui-workflow) πŸ’₯.
- **`2024/07/24`**: Our [**Paper on ArXiv**](http://arxiv.org/abs/2407.15886) is available πŸ₯³!
- **`2024/07/22`**: Our [**App Code**](https://github.com/Zheng-Chong/CatVTON/blob/main/app.py) is released, deploy and enjoy CatVTON on your mechine πŸŽ‰!
- **`2024/07/21`**: Our [**Inference Code**](https://github.com/Zheng-Chong/CatVTON/blob/main/inference.py) and [**Weights** πŸ€—](https://huggingface.co/zhengchong/CatVTON) are released.
- **`2024/07/11`**: Our [**Online Demo**](http://120.76.142.206:8888) is released 😁.
## Installation
An [Installation Guide](https://github.com/Zheng-Chong/CatVTON/blob/main/INSTALL.md) is provided to help build the conda environment for CatVTON. When deploying the app, you will need Detectron2 & DensePose, which are not required for inference on datasets. Install the packages according to your needs.
## Deployment
### ComfyUI Workflow
We have modified the main code to enable easy deployment of CatVTON on [ComfyUI](https://github.com/comfyanonymous/ComfyUI). Due to the incompatibility of the code structure, we have released this part in the [Releases](https://github.com/Zheng-Chong/CatVTON/releases/tag/ComfyUI), which includes the code placed under `custom_nodes` of ComfyUI and our workflow JSON files.
To deploy CatVTON to your ComfyUI, follow these steps:
1. Install all the requirements for both CatVTON and ComfyUI, refer to [Installation Guide for CatVTON](https://github.com/Zheng-Chong/CatVTON/blob/main/INSTALL.md) and [Installation Guide for ComfyUI](https://github.com/comfyanonymous/ComfyUI?tab=readme-ov-file#installing).
2. Download [`ComfyUI-CatVTON.zip`](https://github.com/Zheng-Chong/CatVTON/releases/download/ComfyUI/ComfyUI-CatVTON.zip) and unzip it in the `custom_nodes` folder under your ComfyUI project (clone from [ComfyUI](https://github.com/comfyanonymous/ComfyUI)).
3. Run the ComfyUI.
4. Download [`catvton_workflow.json`](https://github.com/Zheng-Chong/CatVTON/releases/download/ComfyUI/catvton_workflow.json) and drag it into you ComfyUI webpage and enjoy πŸ˜†!
> Problems under Windows OS, please refer to [issue#8](https://github.com/Zheng-Chong/CatVTON/issues/8).
>
When you run the CatVTON workflow for the first time, the weight files will be automatically downloaded, usually taking dozens of minutes.
<!-- <div align="center">
<img src="resource/img/comfyui.png" width="100%" height="100%"/>
</div> -->
### Gradio App
To deploy the Gradio App for CatVTON on your machine, run the following command, and checkpoints will be automatically downloaded from HuggingFace.
```PowerShell
CUDA_VISIBLE_DEVICES=0 python app.py \
--output_dir="resource/demo/output" \
--mixed_precision="bf16" \
--allow_tf32
```
When using `bf16` precision, generating results with a resolution of `1024x768` only requires about `8G` VRAM.
## Inference
### 1. Data Preparation
Before inference, you need to download the [VITON-HD](https://github.com/shadow2496/VITON-HD) or [DressCode](https://github.com/aimagelab/dress-code) dataset.
Once the datasets are downloaded, the folder structures should look like these:
```
β”œβ”€β”€ VITON-HD
| β”œβ”€β”€ test_pairs_unpaired.txt
β”‚ β”œβ”€β”€ test
| | β”œβ”€β”€ image
β”‚ β”‚ β”‚ β”œβ”€β”€ [000006_00.jpg | 000008_00.jpg | ...]
β”‚ β”‚ β”œβ”€β”€ cloth
β”‚ β”‚ β”‚ β”œβ”€β”€ [000006_00.jpg | 000008_00.jpg | ...]
β”‚ β”‚ β”œβ”€β”€ agnostic-mask
β”‚ β”‚ β”‚ β”œβ”€β”€ [000006_00_mask.png | 000008_00.png | ...]
...
```
For the DressCode dataset, we provide [our preprocessed agnostic masks](https://drive.google.com/drive/folders/1uT88nYQl0n5qHz6zngb9WxGlX4ArAbVX?usp=share_link), download and place in `agnostic_masks` folders under each category.
```
β”œβ”€β”€ DressCode
| β”œβ”€β”€ test_pairs_paired.txt
| β”œβ”€β”€ test_pairs_unpaired.txt
β”‚ β”œβ”€β”€ [dresses | lower_body | upper_body]
| | β”œβ”€β”€ test_pairs_paired.txt
| | β”œβ”€β”€ test_pairs_unpaired.txt
β”‚ β”‚ β”œβ”€β”€ images
β”‚ β”‚ β”‚ β”œβ”€β”€ [013563_0.jpg | 013563_1.jpg | 013564_0.jpg | 013564_1.jpg | ...]
β”‚ β”‚ β”œβ”€β”€ agnostic_masks
β”‚ β”‚ β”‚ β”œβ”€β”€ [013563_0.png| 013564_0.png | ...]
...
```
### 2. Inference on VTIONHD/DressCode
To run the inference on the DressCode or VITON-HD dataset, run the following command, checkpoints will be automatically downloaded from HuggingFace.
```PowerShell
CUDA_VISIBLE_DEVICES=0 python inference.py \
--dataset [dresscode | vitonhd] \
--data_root_path <path> \
--output_dir <path>
--dataloader_num_workers 8 \
--batch_size 8 \
--seed 555 \
--mixed_precision [no | fp16 | bf16] \
--allow_tf32 \
--repaint \
--eval_pair
```
### 3. Calculate Metrics
After obtaining the inference results, calculate the metrics using the following command:
```PowerShell
CUDA_VISIBLE_DEVICES=0 python eval.py \
--gt_folder <your_path_to_gt_image_folder> \
--pred_folder <your_path_to_predicted_image_folder> \
--paired \
--batch_size=16 \
--num_workers=16
```
- `--gt_folder` and `--pred_folder` should be folders that contain **only images**.
- To evaluate the results in a paired setting, use `--paired`; for an unpaired setting, simply omit it.
- `--batch_size` and `--num_workers` should be adjusted based on your machine.
## Acknowledgement
Our code is modified based on [Diffusers](https://github.com/huggingface/diffusers). We adopt [Stable Diffusion v1.5 inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting) as the base model. We use [SCHP](https://github.com/GoGoDuck912/Self-Correction-Human-Parsing/tree/master) and [DensePose](https://github.com/facebookresearch/DensePose) to automatically generate masks in our [Gradio](https://github.com/gradio-app/gradio) App and [ComfyUI](https://github.com/comfyanonymous/ComfyUI) workflow. Thanks to all the contributors!
## License
All the materials, including code, checkpoints, and demo, are made available under the [Creative Commons BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license. You are free to copy, redistribute, remix, transform, and build upon the project for non-commercial purposes, as long as you give appropriate credit and distribute your contributions under the same license.
## Citation
```bibtex
@misc{chong2024catvtonconcatenationneedvirtual,
title={CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models},
author={Zheng Chong and Xiao Dong and Haoxiang Li and Shiyue Zhang and Wenqing Zhang and Xujie Zhang and Hanqing Zhao and Xiaodan Liang},
year={2024},
eprint={2407.15886},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2407.15886},
}
```