Spaces:
Runtime error
Runtime error
VictorFS82
commited on
Commit
β’
969535f
1
Parent(s):
e2b5e38
Delete README.md
Browse files
README.md
DELETED
@@ -1,71 +0,0 @@
|
|
1 |
-
# OOTDiffusion
|
2 |
-
This repository is the official implementation of OOTDiffusion
|
3 |
-
|
4 |
-
π€ [Try out OOTDiffusion](https://huggingface.co/spaces/levihsu/OOTDiffusion) (Thanks to [ZeroGPU](https://huggingface.co/zero-gpu-explorers) for providing A100 GPUs)
|
5 |
-
|
6 |
-
Or [try our own demo](https://ootd.ibot.cn/) on RTX 4090 GPUs
|
7 |
-
|
8 |
-
> **OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on** [[arXiv paper](https://arxiv.org/abs/2403.01779)]<br>
|
9 |
-
> [Yuhao Xu](http://levihsu.github.io/), [Tao Gu](https://github.com/T-Gu), [Weifeng Chen](https://github.com/ShineChen1024), [Chengcai Chen](https://www.researchgate.net/profile/Chengcai-Chen)<br>
|
10 |
-
> Xiao-i Research
|
11 |
-
|
12 |
-
|
13 |
-
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
|
14 |
-
|
15 |
-
* π€ [Hugging Face link](https://huggingface.co/levihsu/OOTDiffusion)
|
16 |
-
* π’π’ We support ONNX for [humanparsing](https://github.com/GoGoDuck912/Self-Correction-Human-Parsing) now. Most environmental issues should have been addressed : )
|
17 |
-
* Please download [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) into ***checkpoints*** folder
|
18 |
-
* We've only tested our code and models on Linux (Ubuntu 22.04)
|
19 |
-
|
20 |
-
![demo](images/demo.png)
|
21 |
-
![workflow](images/workflow.png)
|
22 |
-
|
23 |
-
## Installation
|
24 |
-
1. Clone the repository
|
25 |
-
|
26 |
-
```sh
|
27 |
-
git clone https://github.com/levihsu/OOTDiffusion
|
28 |
-
```
|
29 |
-
|
30 |
-
2. Create a conda environment and install the required packages
|
31 |
-
|
32 |
-
```sh
|
33 |
-
conda create -n ootd python==3.10
|
34 |
-
conda activate ootd
|
35 |
-
pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2
|
36 |
-
pip install -r requirements.txt
|
37 |
-
```
|
38 |
-
|
39 |
-
## Inference
|
40 |
-
1. Half-body model
|
41 |
-
|
42 |
-
```sh
|
43 |
-
cd OOTDiffusion/run
|
44 |
-
python run_ootd.py --model_path <model-image-path> --cloth_path <cloth-image-path> --scale 2.0 --sample 4
|
45 |
-
```
|
46 |
-
|
47 |
-
2. Full-body model
|
48 |
-
|
49 |
-
> Garment category must be paired: 0 = upperbody; 1 = lowerbody; 2 = dress
|
50 |
-
|
51 |
-
```sh
|
52 |
-
cd OOTDiffusion/run
|
53 |
-
python run_ootd.py --model_path <model-image-path> --cloth_path <cloth-image-path> --model_type dc --category 2 --scale 2.0 --sample 4
|
54 |
-
```
|
55 |
-
|
56 |
-
## Citation
|
57 |
-
```
|
58 |
-
@article{xu2024ootdiffusion,
|
59 |
-
title={OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on},
|
60 |
-
author={Xu, Yuhao and Gu, Tao and Chen, Weifeng and Chen, Chengcai},
|
61 |
-
journal={arXiv preprint arXiv:2403.01779},
|
62 |
-
year={2024}
|
63 |
-
}
|
64 |
-
```
|
65 |
-
|
66 |
-
## TODO List
|
67 |
-
- [x] Paper
|
68 |
-
- [x] Gradio demo
|
69 |
-
- [x] Inference code
|
70 |
-
- [x] Model weights
|
71 |
-
- [ ] Training code
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|