Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,23 @@ base_model:
|
|
| 8 |
- stabilityai/stable-diffusion-3.5-large
|
| 9 |
- Qwen/Qwen2.5-VL-7B-Instruct
|
| 10 |
pipeline_tag: image-to-image
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
## Features
|
|
|
|
| 8 |
- stabilityai/stable-diffusion-3.5-large
|
| 9 |
- Qwen/Qwen2.5-VL-7B-Instruct
|
| 10 |
pipeline_tag: image-to-image
|
| 11 |
+
---
|
| 12 |
+
# TEMU-VTOFF: Virtual Try-Off & Fashion Understanding Toolkit
|
| 13 |
+
TEMU-VTOFF is a state-of-the-art toolkit for virtual try-off and fashion image understanding. It leverages advanced diffusion models, vision-language models, and semantic segmentation to enable garment transfer, attribute captioning, and mask generation for fashion images.
|
| 14 |
+
<img src="./assets/teaser.png" alt="example">
|
| 15 |
+
## Table of Contents
|
| 16 |
+
|
| 17 |
+
- [Features](#features)
|
| 18 |
+
- [Installation](#installation)
|
| 19 |
+
- [Quick Start](#quick-start)
|
| 20 |
+
- [Core Components](#core-components)
|
| 21 |
+
- [1. Inference Pipeline (`inference.py`)](#1-inference-pipeline-inferencepy)
|
| 22 |
+
- [2. Visual Attribute Captioning (`precompute_utils/captioning_qwen.py`)](#2-visual-attribute-captioning-precompute_utilscaptioning_qwenpy)
|
| 23 |
+
- [3. Clothing Segmentation (`SegCloth.py`)](#3-clothing-segmentation-segclothpy)
|
| 24 |
+
- [Examples](#examples)
|
| 25 |
+
- [Citation](#citation)
|
| 26 |
+
- [License](#license)
|
| 27 |
+
|
| 28 |
---
|
| 29 |
|
| 30 |
## Features
|