Training-Free Style Consistent Image Synthesis with Condition and Mask Guidance in E-Commerce

TL;DR

This paper presents a train-free, style-consistent image synthesis method for e-commerce that leverages attention map modifications and mask guidance to produce high-quality images without additional training.

Contribution

It introduces a novel train-free approach using condition and mask guidance in attention maps to generate style-consistent images in e-commerce.

Findings

Effective style consistency in generated images

No additional training required for the method

Promising results in practical e-commerce applications

Abstract

Generating style-consistent images is a common task in the e-commerce field, and current methods are largely based on diffusion models, which have achieved excellent results. This paper introduces the concept of the QKV (query/key/value) level, referring to modifications in the attention maps (self-attention and cross-attention) when integrating UNet with image conditions. Without disrupting the product's main composition in e-commerce images, we aim to use a train-free method guided by pre-set conditions. This involves using shared KV to enhance similarity in cross-attention and generating mask guidance from the attention map to cleverly direct the generation of style-consistent images. Our method has shown promising results in practical applications.