Update README.md

README.md

@@ -1,19 +1,13 @@
-# TEMU-VTOFF: Virtual Try-Off & Fashion Understanding Toolkit
-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.
-<img src="./assets/teaser.png" alt="example">
-## Table of Contents
-
-- [Features](#features)
-- [Installation](#installation)
-- [Quick Start](#quick-start)
-- [Core Components](#core-components)
-  - [1. Inference Pipeline (`inference.py`)](#1-inference-pipeline-inferencepy)
-  - [2. Visual Attribute Captioning (`precompute_utils/captioning_qwen.py`)](#2-visual-attribute-captioning-precompute_utilscaptioning_qwenpy)
-  - [3. Clothing Segmentation (`SegCloth.py`)](#3-clothing-segmentation-segclothpy)
-- [Examples](#examples)
-- [Citation](#citation)
-- [License](#license)
-
+---
+license: apache-2.0
+datasets:
+- XiuAiMoon/VITON-HD
+- JianhaoZeng/Dresscode
+base_model:
+- davidelobba/TEMU-VTOFF
+- stabilityai/stable-diffusion-3.5-large
+- Qwen/Qwen2.5-VL-7B-Instruct
+pipeline_tag: image-to-image
 ---
 
 ## Features
@@ -163,4 +157,4 @@ If you use TEMU-VTOFF in your research or product, please cite this repository a
 
 ## License
 
-This project is licensed under the [LICENSE](LICENSE) provided in the repository. Please check individual model and dataset licenses for additional terms.
+This project is licensed under the [LICENSE](LICENSE) provided in the repository. Please check individual model and dataset licenses for additional terms.