---
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/ShineChen1024), and [Chengcai Chen](https://www.researchgate.net/profile/Chengcai-Chen)<br>
> Xiao-i Research

An early version of our paper is available now! [[arXiv](https://arxiv.org/abs/2403.01779)]

🥳🥳 Our model checkpoints trained on [VITON-HD](https://github.com/shadow2496/VITON-HD) (half-body) and [Dress Code](https://github.com/aimagelab/dress-code) (full-body) have been released!

* 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
* Please download [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) into ***checkpoints*** folder
* We've only tested our code and models on Linux (Ubuntu 22.04)

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