HieraFashDiff: Hierarchical Fashion Design with Multi-stage Diffusion Models

TL;DR

HieraFashDiff introduces a hierarchical diffusion framework that mimics the fashion design process, enabling generation and editing of fashion images with high fidelity and adherence to high-level concepts and low-level attributes.

Contribution

The paper presents a novel multi-stage diffusion model tailored for fashion design, along with a new hierarchical dataset for training and evaluation.

Findings

Outperforms prior methods in fidelity and prompt adherence

Supports integrated fashion design generation and editing

Demonstrates potential to augment practical fashion workflows

Abstract

Fashion design is a challenging and complex process.Recent works on fashion generation and editing are all agnostic of the actual fashion design process, which limits their usage in practice.In this paper, we propose a novel hierarchical diffusion-based framework tailored for fashion design, coined as HieraFashDiff. Our model is designed to mimic the practical fashion design workflow, by unraveling the denosing process into two successive stages: 1) an ideation stage that generates design proposals given high-level concepts and 2) an iteration stage that continuously refines the proposals using low-level attributes. Our model supports fashion design generation and fine-grained local editing in a single framework. To train our model, we contribute a new dataset of full-body fashion images annotated with hierarchical text descriptions. Extensive evaluations show that, as compared to prior approaches, our method can generate fashion designs and edited results with higher fidelity and better prompt adherence, showing its promising potential to augment the practical fashion design workflow. Code and Dataset are available at https://github.com/haoli-zbdbc/hierafashdiff.