Training-Free Style Consistent Image Synthesis with Condition and Mask Guidance in E-Commerce
This addresses style consistency for e-commerce image generation, but it is incremental as it builds on existing diffusion models.
The paper tackled the problem of generating style-consistent images in e-commerce without training by modifying attention maps in diffusion models, resulting in promising practical applications.
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.