---
tags:
  - text-to-image
  - stable-diffusion
  - dress
  - try on
license: apache-2.0
language:
  - en
library_name: diffusers
---

# IMAGDressing: Interactive Modular Apparel Generation for Dressing

## IMAGDressing-v1: Customizable Virtual Dressing

<div align="center">

[**Project Page**](https://imagdressing.github.io/) **|** [**Paper**](https://arxiv.org/pdf/2407.12705) **|** [**Code**](https://github.com/muzishen/IMAGDressing)

</div>

---

## Introduction

To address the need for flexible and controllable customizations in virtual try-on systems, we propose IMAGDressing-v1. Specifically, we introduce a garment UNet that captures semantic features from CLIP and texture features from VAE. Our hybrid attention module includes a frozen self-attention and a trainable cross-attention, integrating these features into a frozen denoising UNet to ensure user-controlled editing. We will release a comprehensive dataset, IGv1, with over 200,000 pairs of clothing and dressed images, and establish a standard data assembly pipeline. Furthermore, IMAGDressing-v1 can be combined with extensions like ControlNet, IP-Adapter, T2I-Adapter, and AnimateDiff to enhance diversity and controllability. 

![framework](assets/pipeline.png)