IMAGDressing-v1: Customizable Virtual Dressing

TL;DR

IMAGDressing-v1 introduces a flexible virtual dressing system that allows customizable, controllable human image generation with a new dataset and advanced attention mechanisms, improving virtual try-on experiences.

Contribution

The paper presents IMAGDressing-v1, a novel model for editable human image synthesis with flexible garment control, and releases a large dataset for garment pairing.

Findings

Achieves state-of-the-art performance in controlled human image synthesis.

Enables flexible scene and garment control via text and plugins.

Provides a large garment pairing dataset for training and evaluation.

Abstract

Latest advances have achieved realistic virtual try-on (VTON) through localized garment inpainting using latent diffusion models, significantly enhancing consumers' online shopping experience. However, existing VTON technologies neglect the need for merchants to showcase garments comprehensively, including flexible control over garments, optional faces, poses, and scenes. To address this issue, we define a virtual dressing (VD) task focused on generating freely editable human images with fixed garments and optional conditions. Meanwhile, we design a comprehensive affinity metric index (CAMI) to evaluate the consistency between generated images and reference garments. Then, we propose IMAGDressing-v1, which incorporates a garment UNet that captures semantic features from CLIP and texture features from VAE. We present a hybrid attention module, including a frozen self-attention and a trainable cross-attention, to integrate garment features from the garment UNet into a frozen denoising UNet, ensuring users can control different scenes through text. IMAGDressing-v1 can be combined with other extension plugins, such as ControlNet and IP-Adapter, to enhance the diversity and controllability of generated images. Furthermore, to address the lack of data, we release the interactive garment pairing (IGPair) dataset, containing over 300,000 pairs of clothing and dressed images, and establish a standard pipeline for data assembly. Extensive experiments demonstrate that our IMAGDressing-v1 achieves state-of-the-art human image synthesis performance under various controlled conditions. The code and model will be available at https://github.com/muzishen/IMAGDressing.