AnyDesign: Versatile Area Fashion Editing via Mask-Free Diffusion

TL;DR

AnyDesign introduces a versatile, mask-free diffusion-based approach for fashion image editing that handles diverse clothing types and complex backgrounds, using a new extended dataset and a novel guidance module.

Contribution

The paper presents a new dataset with diverse apparel and backgrounds, and a diffusion-based method with Fashion-Guidance Attention for flexible, mask-free fashion editing.

Findings

Outperforms existing text-guided fashion editing methods in quality.

Handles a wide range of apparel types and complex backgrounds.

Enables simple input of images and prompts for editing.

Abstract

Fashion image editing aims to modify a person's appearance based on a given instruction. Existing methods require auxiliary tools like segmenters and keypoint extractors, lacking a flexible and unified framework. Moreover, these methods are limited in the variety of clothing types they can handle, as most datasets focus on people in clean backgrounds and only include generic garments such as tops, pants, and dresses. These limitations restrict their applicability in real-world scenarios. In this paper, we first extend an existing dataset for human generation to include a wider range of apparel and more complex backgrounds. This extended dataset features people wearing diverse items such as tops, pants, dresses, skirts, headwear, scarves, shoes, socks, and bags. Additionally, we propose AnyDesign, a diffusion-based method that enables mask-free editing on versatile areas. Users can simply input a human image along with a corresponding prompt in either text or image format. Our approach incorporates Fashion DiT, equipped with a Fashion-Guidance Attention (FGA) module designed to fuse explicit apparel types and CLIP-encoded apparel features. Both Qualitative and quantitative experiments demonstrate that our method delivers high-quality fashion editing and outperforms contemporary text-guided fashion editing methods.