Instructions to use levihsu/OOTDiffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use levihsu/OOTDiffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("levihsu/OOTDiffusion", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
metadata
license: cc-by-nc-sa-4.0
OOTDiffusion
Our OOTDiffusion GitHub repository
Please give me a star if you find it interesting!
OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on
Yuhao Xu, Tao Gu, Weifeng Chen, and Chengcai Chen
Xiao-i Research
An early version of our paper is available now! [arXiv]
🥳🥳 Our model checkpoints trained on VITON-HD (half-body) and Dress Code (full-body) have been released!
- We use checkpoints of humanparsing and openpose in preprocess. Please refer to their guidance if you encounter relevant environmental issues
- Please download clip-vit-large-patch14 into checkpoints folder
- We've only tested our code and models on Linux (Ubuntu 22.04)

