---
title: IDM-VTON
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/IDM-VTON"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/IDM-VTON.md"
repository: AI-ModelScope/IDM-VTON
last_updated: 2024-05-16
license: cc-by-nc-sa-4.0
pipeline_tag: image-to-image
tasks:
  - image-to-image
parameters: 4.1B
tensor_type:
  - F32
  - I64
library_name:
  - safetensors
  - diffusers
  - onnx
  - pytorch
frameworks:
  - pytorch
downloads: 4731
stars: 13
tags:
  - stable-diffusion-xl
  - inpainting
  - "virtual try-on"
---

# IDM-VTON

> IDM-VTON - AI-ModelScope 在 ModelScope 开源的模型。Check out more codes on our github repository!

AI-ModelScope/IDM-VTON 是 ModelScope 魔搭社区上的 4.1B 参数image-to-image模型，采用 cc-by-nc-sa-4.0 许可。

- **Repository**: AI-ModelScope/IDM-VTON
- **License**: cc-by-nc-sa-4.0
- **Tasks**: image-to-image
- **Parameters**: 4.1B
- **Tags**: stable-diffusion-xl, inpainting, virtual try-on
- **Downloads**: 4731
- **Stars**: 13
- **Last updated**: 2024-05-16

Source: https://www.modelscope.cn/models/AI-ModelScope/IDM-VTON

---

# Check out more codes on our [github repository](https://github.com/yisol/IDM-VTON)!

# 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](https://arxiv.org/abs/2403.05139) 
- [project page](https://idm-vton.github.io/) 

🤗 Try our huggingface [Demo](https://huggingface.co/spaces/yisol/IDM-VTON)

![teaser](assets/teaser.png) 
![teaser2](assets/teaser2.png) 


## TODO LIST


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




## Acknowledgements

For the demo, GPUs are supported from [zerogpu](https://huggingface.co/zero-gpu-explorers), and auto masking generation codes are based on [OOTDiffusion](https://github.com/levihsu/OOTDiffusion) and [DCI-VTON](https://github.com/bcmi/DCI-VTON-Virtual-Try-On).  
Parts of the code are based on [IP-Adapter](https://github.com/tencent-ailab/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](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).