https://github.com/ningshuliang/PICTURE
Official code for paper "PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns"
https://github.com/ningshuliang/PICTURE
Last synced: 8 months ago
JSON representation
Official code for paper "PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns"
- Host: GitHub
- URL: https://github.com/ningshuliang/PICTURE
- Owner: ningshuliang
- License: mit
- Created: 2023-12-06T18:39:41.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-10-14T04:47:02.000Z (about 1 year ago)
- Last Synced: 2024-10-30T23:35:41.916Z (about 1 year ago)
- Language: Jupyter Notebook
- Size: 27 MB
- Stars: 51
- Watchers: 10
- Forks: 4
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-diffusion-categorized - [Code
README
# PICTURE
PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns
[Shuliang Ning*](https://ningshuliang.github.io/),
[Duomin Wang](https://dorniwang.github.io/),
[Yipeng Qin](https://profiles.cardiff.ac.uk/staff/qiny16),
[Zirong Jin](https://scholar.google.com/citations?user=6-ARg6AAAAAJ&hl=en),
[Baoyuan Wang](https://sites.google.com/site/zjuwby/),
[Xiaoguang Han](https://gaplab.cuhk.edu.cn/)
[](https://www.youtube.com/watch?v=nEqVbkl2yY0)
## Install
```
- System requirement: Ubuntu20.04
- Tested GPUs: A100 40G.
- Cuda 11.7
```
Install requirements using following scripts.
~~~
git clone https://github.com/ningshuliang/PICTURE.git
conda create -n picture
conda activate picture
pip install -r requirements.txt
~~~
Download the pretrained weights [baiduyun](https://pan.baidu.com/s/1J-KC9n8HGX7yXnI-jk8zZA?pwd=qpky) or [Hugging Face ](https://huggingface.co/Shuliang/PICTURE/tree/main/pretrain_models) and place it in the pretrain_models directory.
## Stage 1
~~~
cd Stage1_Text_to_Parsing
bash test.sh
~~~
## Stage 2
~~~
cd Stage2_Parsing_to_Image
bash test.sh
~~~
## Architecture
## Experiments
