Awesome
PICTURE
PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns
Shuliang Ning*, Duomin Wang, Yipeng Qin, Zirong Jin, Baoyuan Wang, Xiaoguang Han
<a href='https://ningshuliang.github.io/2023/Arxiv/index.html'><img src='https://img.shields.io/badge/Project-Page-Green'></a> <a href='https://arxiv.org/abs/2312.04534'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a>
<img src=".\figs\teaser_GAP.jpg" alt="richdreamer" style="zoom:200%;" /> <!-- ## TODO :triangular_flag_on_post: - [ ] Provide the generation trial on [ModelScope's 3D Object Generation](https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC/summary) - [ ] Text to ND Diffusion Model - [ ] Multiview-ND and Multiview-Albedo Diffusion Models - [ ] Release code (The code will be public around the end of Dec.2023.) -->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 or Google Drive 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