Skip to yearly menu bar Skip to main content


Oral

Style Aligned Image Generation via Shared Attention

Amir Hertz · Andrey Voynov · Shlomi Fruchter · Daniel Cohen-Or

Summit Ballroom Oral #5
[ ] [ Visit Orals 2A Image & Video Synthesis ]
Wed 19 Jun 2:12 p.m. — 2:30 p.m. PDT

Abstract:

Large-scale Text-to-Image (T2I) models have rapidly gained prominence across creative fields, generating visually compelling outputs from textual prompts. However, controlling these models to ensure consistent style remains challenging, with existing methods necessitating fine-tuning and manual intervention to disentangle content and style. In this paper, we introduce StyleAligned, a novel technique designed to establish style alignment among a series of generated images. By employing minimal `attention sharing' during the diffusion process, our method maintains style consistency across images within T2I models. This approach allows for the creation of style-consistent images using a reference style through a straightforward inversion operation. Our method's evaluation across diverse styles and text prompts demonstrates high-quality synthesis and fidelity, underscoring its efficacy in achieving consistent style across various inputs.

Chat is not available.