---
license: cc-by-nc-4.0
base_model:
- stabilityai/stable-diffusion-3-medium-diffusers
pipeline_tag: image-to-image
tags:
- image-generation
- image-to-image
- virtual-try-on
- virtual-try-off
- diffusion
- dit
- stable-diffusion-3
- multimodal
- fashion
- pytorch
language: en
datasets:
- dresscode
- viton-hd
---

<div align="center">
<h1 align="center">TEMU-VTOFF</h1>
<h3 align="center">Text-Enhanced MUlti-category Virtual Try-Off</h3>
</div>

<div align="center">
<picture>
<source srcset="/davidelobba/TEMU-VTOFF/resolve/main/teaser.png" media="(prefers-color-scheme: dark)">
<img src="/davidelobba/TEMU-VTOFF/resolve/main/teaser.png" width="75%" alt="TEMU-VTOFF Teaser">
</source>
</picture>
</div>

<div align="center">

**Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals**
[Davide Lobba](https://scholar.google.com/citations?user=WEMoLPEAAAAJ&hl=en&oi=ao)<sup>1,2,\*</sup>, [Fulvio Sanguigni](https://scholar.google.com/citations?user=tSpzMUEAAAAJ&hl=en)<sup>2,3,\*</sup>, [Bin Ren](https://scholar.google.com/citations?user=Md9maLYAAAAJ&hl=en)<sup>1,2</sup>, [Marcella Cornia](https://scholar.google.com/citations?user=DzgmSJEAAAAJ&hl=en)<sup>3</sup>, [Rita Cucchiara](https://scholar.google.com/citations?user=OM3sZEoAAAAJ&hl=en)<sup>3</sup>, [Nicu Sebe](https://scholar.google.com/citations?user=stFCYOAAAAAJ&hl=en)<sup>1</sup>
<sup>1</sup>University of Trento, <sup>2</sup>University of Pisa, <sup>3</sup>University of Modena and Reggio Emilia
<sup>*</sup> Equal contribution
</div>

<div align="center">
<a href="https://arxiv.org/abs/2505.21062" style="margin: 0 2px;">
<img src="https://img.shields.io/badge/Paper-Arxiv_2505.21062-darkred.svg" alt="Paper">
</a>
<a href="https://temu-vtoff-page.github.io/" style="margin: 0 2px;">
<img src='https://img.shields.io/badge/Webpage-Project-silver?style=flat&logo=&logoColor=orange' alt='Project Webpage'>
</a>
<a href="https://github.com/davidelobba/TEMU-VTOFF" style="margin: 0 2px;">
<img src="https://img.shields.io/badge/GitHub-Repo-blue.svg?logo=github" alt="GitHub Repository">
</a>
<!-- The Hugging Face model badge will be automatically displayed on the model page -->
</div>

## 💡 Model Description

**TEMU-VTOFF** is a novel dual-DiT (Diffusion Transformer) architecture designed for the Virtual Try-Off task: generating in-shop images of garments worn by a person. By combining a pretrained feature extractor with a text-enhanced generation module, our method can handle occlusions, multiple garment categories, and ambiguous appearances. It further refines generation fidelity via a feature alignment module based on DINOv2.

This model is based on `stabilityai/stable-diffusion-3-medium-diffusers`. The uploaded weights correspond to the finetuned feature extractor and the VTOFF DiT module.

## ✨ Key Features
Our contribution can be summarized as follows:
- **🎯 Multi-Category Try-Off**. We present a unified framework capable of handling multiple garment types (upper-body, lower-body, and full-body clothes) without requiring category-specific pipelines.
- **🔗 Multimodal Hybrid Attention**. We introduce a novel attention mechanism that integrates garment textual descriptions into the generative process by linking them with person-specific features. This helps the model synthesize occluded or ambiguous garment regions more accurately.
- **⚡ Garment Aligner Module**. We design a lightweight aligner that conditions generation on clean garment images, replacing conventional denoising objectives. This leads to better alignment consistency on the overall dataset and preserves more precise visual retention.
- **📊 Extensive experiments**. Experiments on the Dress Code and VITON-HD datasets demonstrate that TEMU-VTOFF outperforms prior methods in both the quality of generated images and alignment with the target garment, highlighting its strong generalization capabilities.