Voost jointly handles virtual try-on and try-off within a single transformer, achieving high-quality results while remaining robust to various human poses, garment categories, backgrounds, lighting conditions, and image compositions.

• [2025-08-08] 📄 Voost is now on arXiv. Visit the project page for more details and results.

🚧 A public demo (try-on & try-off) will be released soon. Stay tuned!

@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}
}

This project is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

For commercial use, please visit NXN Labs.

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.