In this work, we target the task of text-driven style transfer in the context of text-to-image (T2I) diffusion models. The main challenge is consistent structure preservation while enabling effective style transfer effects. The past approaches in this field directly concatenate the content and style prompts for a prompt-level style injection, leading to unavoidable structure distortions. In this work, we propose a novel solution to the text-driven style transfer task, namely, Adaptive Style Incorporation~(ASI), to achieve fine-grained feature-level style incorporation. It consists of the Siamese Cross-Attention~(SiCA) to decouple the single-track cross-attention to a dual-track structure to obtain separate content and style features, and the Adaptive Content-Style Blending (AdaBlending) module to couple the content and style information from a structure-consistent manner. Experimentally, our method exhibits much better performance in both structure preservation and stylized effects.
@article{arxiv.2404.06835,
title = {Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer},
author = {Yanqi Ge and Jiaqi Liu and Qingnan Fan and Xi Jiang and Ye Huang and Shuai Qin and Hong Gu and Wen Li and Lixin Duan},
journal= {arXiv preprint arXiv:2404.06835},
year = {2026}
}