---
license: cc-by-nc-sa-4.0
---

# OOTDiffusion
[Our OOTDiffusion GitHub repository](https://github.com/levihsu/OOTDiffusion)

[Try our OOTDiffusion](https://ootd.ibot.cn/)

Please give me a star if you find it interesting!


> **OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on**<br>
> [Yuhao Xu](https://scholar.google.com/citations?user=FF7JVLsAAAAJ&hl=zh-CN), [Tao Gu](https://github.com/T-Gu), [Weifeng Chen](https://github.com/chenshine1), Chengcai Chen<br>
> Xiao-i Research

Our paper is coming soon!

> We use checkpoints of [humanparsing](https://github.com/GoGoDuck912/Self-Correction-Human-Parsing) and [openpose](https://huggingface.co/lllyasviel/ControlNet/tree/main/annotator/ckpts) in preprocess. Please refer to their guidance if you encounter relevant environmental issues<br>
> Please download [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) into ***checkpoints*** folder

![demo](images/demo.png)&nbsp;
![workflow](images/workflow.png)&nbsp;