Views
No views yet
Jiazheng Xing, Chao Xu, Yijie Qian, Yang Liu, Guang Dai, Baigui Sun, Yong Liu, Jingdong Wang
1git clone https://github.com/jiazheng-xing/TryOn-Adapter.git
2cd TryOn-Adapter1conda env create -f environment.yaml
2conda activate tryon-adapter├── VITON-HD
| ├── test_pairs.txt
| ├── train_pairs.txt
│ ├── [train | test]
| | ├── image
│ │ │ ├── [000006_00.jpg | 000008_00.jpg | ...]
│ │ ├── cloth
│ │ │ ├── [000006_00.jpg | 000008_00.jpg | ...]
│ │ ├── cloth-mask
│ │ │ ├── [000006_00.jpg | 000008_00.jpg | ...]
│ │ ├── image-parse-v3
│ │ │ ├── [000006_00.png | 000008_00.png | ...]
│ │ ├── openpose_img
│ │ │ ├── [000006_00_rendered.png | 000008_00_rendered.png | ...]
│ │ ├── openpose_json
│ │ │ ├── [000006_00_keypoints.json | 000008_00_keypoints.json | ...]
│ │ ├── train_paired/test_(un)paired
│ │ │ ├── mask [000006_00.png | 000008_00.png | ...]
│ │ │ ├── seg_preds [000006_00.png | 000008_00.png | ...]
│ │ │ ├── warped [000006_00.png | 000008_00.png | ...]├── DressCode
| ├── test_pairs_paired.txt
| ├── test_pairs_unpaired.txt
| ├── train_pairs.txt
| ├── train_pairs.txt
│ ├── [test_paird | test_unpaird | train_paird]
│ │ ├── [dresses | lower_body | upper_body]
│ │ │ │ ├── mask [013563_1.png| 013564_1.png | ...]
│ │ │ │ ├── seg_preds [013563_1.png| 013564_1.png | ...]
│ │ │ │ ├── warped [013563_1.png| 013564_1.png | ...]
│ ├── [dresses | lower_body | upper_body]
| | ├── test_pairs_paired.txt
| | ├── test_pairs_unpaired.txt
| | ├── train_pairs.txt
│ │ ├── images
│ │ │ ├── [013563_0.jpg | 013563_1.jpg | 013564_0.jpg | 013564_1.jpg | ...]
│ │ ├── masks
│ │ │ ├── [013563_1.png| 013564_1.png | ...]
│ │ ├── keypoints
│ │ │ ├── [013563_2.json | 013564_2.json | ...]
│ │ ├── label_maps
│ │ │ ├── [013563_4.png | 013564_4.png | ...]
│ │ ├── skeletons
│ │ │ ├── [013563_5.jpg | 013564_5.jpg | ...]
│ │ ├── dense
│ │ │ ├── [013563_5.png | 013563_5_uv.npz | 013564_5.png | 013564_5_uv.npz | ...]1python test_viton.py/test_dresscode.py --plms --gpu_id 0 \
2--ddim_steps 100 \
3--outdir <path> \
4--config [configs/viton.yaml | configs/dresscode.yaml] \
5--dataroot <path> \
6--ckpt <path> \
7--ckpt_elbm_path <path> \
8--use_T_repaint [True | False] \
9--n_samples 1 \
10--seed 23 \
11--scale 1 \
12--H 512 \
13--W 512 \
14--unpaired1--ddim_steps <int> sampling steps
2--outdir <str> output direction path
3--config <str> config path of viton-hd/dresscode
4--ckpt <str> diffusion model checkpoint path
5--ckpt_elbm_path <str> elbm module checkpoint dirction path
6--use_T_repaint <bool> whether to use T-Repaint technique
7--n_samples <int> numbers of samples per inference
8--unpaired whether to use the unpaired setting1bash test_viton.sh
2bash test_dresscode.sh@article{xing2025tryon,
title={TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On},
author={Xing, Jiazheng and Xu, Chao and Qian, Yijie and Liu, Yang and Dai, Guang and Sun, Baigui and Liu, Yong and Wang, Jingdong},
journal={International Journal of Computer Vision},
pages={1--22},
year={2025},
publisher={Springer}
}