cuuupid / idm-vton

Best-in-class clothing virtual try on in the wild (non-commercial use only)

  • Public
  • 236.6K runs
  • GitHub
  • Paper
  • License

Input

Output

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 18 seconds.

Readme

Non-Commercial use only!

This is the current best-in-class virtual try-on model, created by the Korea Advanced Institute of Science & Technology (KAIST). It’s capable of virtual try-on “in the wild” which has notoriously been difficult for generative models to tackle, until now!

IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

This is an official implementation of paper ‘Improving Diffusion Models for Authentic Virtual Try-on in the Wild’ - paper - project page

teaser  teaser2 

TODO LIST

  • [x] demo model
  • [x] inference code
  • [ ] training code

Acknowledgements

For the demo, auto masking generation codes are based on OOTDiffusion and DCI-VTON.
Parts of the code are based on IP-Adapter.

Citation

@article{choi2024improving,
  title={Improving Diffusion Models for Virtual Try-on},
  author={Choi, Yisol and Kwak, Sangkyung and Lee, Kyungmin and Choi, Hyungwon and Shin, Jinwoo},
  journal={arXiv preprint arXiv:2403.05139},
  year={2024}
}

License

The codes and checkpoints in this repository are under the CC BY-NC-SA 4.0 license.