StyleBlend: Enhancing Style‐Specific Content Creation in Text‐to‐Image Diffusion Models

Synthesizing visually impressive images that seamlessly align both text prompts and specific artistic styles remains a significant challenge in Text‐to‐Image (T2I) diffusion models. This paper introduces StyleBlend, a method designed to learn and apply style representations from a limited set of ref...

Full description

Saved in:
Bibliographic Details
Published in:Computer graphics forum Vol. 44; no. 2
Main Authors: Chen, Zichong, Wang, Shijin, Zhou, Yang
Format: Journal Article
Language:English
Published: Oxford Blackwell Publishing Ltd 01.05.2025
Subjects:
CCS Concepts
Computing methodologies → Image processing
Image representations
Misalignment
Representations
Synthesis
ISSN:0167-7055, 1467-8659
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Synthesizing visually impressive images that seamlessly align both text prompts and specific artistic styles remains a significant challenge in Text‐to‐Image (T2I) diffusion models. This paper introduces StyleBlend, a method designed to learn and apply style representations from a limited set of reference images, enabling content synthesis of both text‐aligned and stylistically coherent. Our approach uniquely decomposes style into two components, composition and texture, each learned through different strategies. We then leverage two synthesis branches, each focusing on a corresponding style component, to facilitate effective style blending through shared features without affecting content generation. StyleBlend addresses the common issues of text misalignment and weak style representation that previous methods have struggled with. Extensive qualitative and quantitative comparisons demonstrate the superiority of our approach.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.70034