## 🚀 Overview
**Refaçade** is a unified image–video retexturing model built upon the Wan2.1-based VACE framework. It edits the surface material of specified objects in a video using user-provided reference textures, while preserving the original geometry and background. We use **Jigsaw Permutation** to decouple structural information in the reference image and a **Texture Remover** to disentangle the original object’s appearance. This functionality enables users to explore diverse possibilities effectively.
---
## 🛠️ Installation
Our project is built upon [Wan2.1-based VACE](https://github.com/ali-vilab/VACE).
```bash
pip install -r requirements.txt
pip install wan@git+https://github.com/Wan-Video/Wan2.1
```
---
## 🏃♂️ Gradio Demo
You can use this gradio demo to retexture objects. Note that you don't need to compile the SAM2.
```bash
python app.py
```
---
## 📂 Download
First, download our checkpoints:
```shell
huggingface-cli download --resume-download fishze/Refacade --local-dir models
```
Next, download SAM2 [sam2_hiera_large.pt](https://huggingface.co/facebook/sam2-hiera-large) and place it at:
```shell
sam2/SAM2-Video-Predictor/checkpoints/
```
We recommend to organize local directories as:
```angular2html
Refacade
├── ...
├── examples
├── models
│ ├── refacade
│ │ └── ...
│ ├── texture_remover
│ │ └── ...
│ └── vae
│ └── ...
├── sam2
└── ...
```
---
