# Voost

**Repository Path**: monkeycc/Voost

## Basic Information

- **Project Name**: Voost
- **Description**: No description available
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-12-03
- **Last Updated**: 2025-12-03

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

<div align="center">
<h2>[SIGGRAPH Asia'25] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off
</h2>

<a href="https://arxiv.org/abs/2508.04825"><img src='https://img.shields.io/badge/arXiv-2508.04825-red?style=flat&logo=arXiv&logoColor=red' alt='arxiv'></a>
<a href="https://nxnai.github.io/Voost/"><img src="https://img.shields.io/badge/Project_Page-green" alt="Project Page"></a>
<a href="https://github.com/nxnai/Voost/blob/main/LICENSE"><img src='https://img.shields.io/badge/License-CC BY--NC--SA--4.0-lightgreen?style=flat&logo=Lisence' alt='License'></a>
<a href='https://huggingface.co/spaces/NXN-Labs/Voost'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Demo-blue'></a>

[Seungyong Lee<sup>*</sup>](https://ryan-seungyong-lee.github.io/)&emsp;&emsp;
[Jeong-gi Kwak<sup>*</sup>](https://jgkwak95.github.io/)<br><sup>* Equal contribution</sup><br>
**[NXN LABS](https://nxn.ai/)**
</div>

<p align="center">
  <img src="docs/img/teaser.jpg" alt="Voost Teaser" width="80%" /><br>
  <i>Voost</i> jointly handles <b>v</b>irtual try-<b>o</b>n and try-<b>o</b>ff within a <b>s</b>ingle <b>t</b>ransformer, achieving high-quality results while
  remaining robust to various human poses, garment categories, backgrounds, lighting conditions, and image compositions.
</p>

## News
- [2025-10-13] 🎉 Voost has been accepted to SIGGRAPH Asia 2025!
- [2025-08-19] 🚀 A public demo of Voost is now available on [Hugging Face Spaces](https://huggingface.co/spaces/NXN-Labs/Voost). Try it out and don’t forget to leave a 🤍 _like_ to support us!
- [2025-08-08] 📄 Voost is now on [arXiv](https://arxiv.org/abs/2508.04825). Visit the [project page](https://nxnai.github.io/Voost/) for more details and results.

## Demo <a href="https://huggingface.co/spaces/NXN-Labs/Voost"><img src="docs/logo/huggingface_logo-noborder.svg" alt="Hugging Face Demo" height="24" style="vertical-align: middle;"/></a>

🚀 A **public demo (try-on & try-off)** is now available on [Hugging Face Spaces](https://huggingface.co/spaces/NXN-Labs/Voost).  
Try it out and don’t forget to leave a 🤍 like to support us!

<div align="center">
  <img src="docs/img/demo/demo_ui.png" alt="demo-ui" height="600">
</div><br>

### Examples
<div align="center">
  <img src="docs/img/demo/demo_samples/sample1.jpg" alt="demo 1" height="200">
  <img src="docs/img/demo/demo_samples/sample2.jpg" alt="demo 2" height="200">
  <img src="docs/img/demo/demo_samples/sample3.jpg" alt="demo 3" height="200">
  <img src="docs/img/demo/demo_samples/sample4.jpg" alt="demo 4" height="200">
  <img src="docs/img/demo/demo_samples/sample5.jpg" alt="demo 5" height="200">
</div><br>

## Citation

```bibtex
@article{lee2025voost,
  author  =   {Seungyong Lee and Jeong-gi Kwak},
  title   =   {Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off},
  journal =   {arXiv preprint arXiv:2508.04825},
  year    =   {2025}
}
```

## License

This project is licensed under the [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-nc-sa/4.0/).

For commercial use, please visit [NXN Labs](https://nxn.ai/).

## Acknowledgments

Most models and clothing images used are from internet and public datasets (VITON, DressCode). All images and brands are the property of their respective owners.