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
Project Page | Paper | Code| Data
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.
