StyleAdapter: A Unified Stylized Image Generation Model
International Journal of Computer Vision · 2025-04 · 133 (4) · 1894-1911
DOI: 10.1007/s11263-024-02253-x ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 25.10.2024. Verfasst von Zhouxia Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National key R&D Program, General Research Fund of Hong Kong.
Abstract (Originalsprache)
This work focuses on generating high-quality images with specific style of reference images and content of provided textual descriptions. Current leading algorithms, i.e., DreamBooth and LoRA, require fine-tuning for each style, leading to time-consuming and computationally expensive processes. In this work, we propose StyleAdapter, a unified stylized image generation model capable of producing a variety of stylized images that match both the content of a given prompt and the style of reference images, without the need for per-style fine-tuning. It introduces a two-path cross-attention (TPCA) module to separately process style information and textual prompt, which cooperate with a semantic suppressing vision model (SSVM) to suppress the semantic content of style images. In this way, it can ensure that the prompt maintains control over the content of the generated images, while also mitigating the negative impact of semantic information in style references. This results in the content of the generated image adhering to the prompt, and its style aligning with the style references. Besides, our StyleAdapter can be integrated with existing controllable synthesis methods, such as T2I-adapter and ControlNet, to attain a more controllable and stable generation process. Extensive experiments demonstrate the superiority of our method over previous works.
Förderung
- National key R&D Program
- General Research Fund of Hong Kong
Zitieren
APA
Wang, Z., Wang, X., Xie, L., Qi, Z., Shan, Y., Wang, W., & Luo, P. (2025). StyleAdapter: A Unified Stylized Image Generation Model. International Journal of Computer Vision, 133(4), 1894-1911. https://doi.org/10.1007/s11263-024-02253-x
Vancouver
Wang Z, Wang X, Xie L, Qi Z, Shan Y, Wang W, et al. StyleAdapter: A Unified Stylized Image Generation Model. International Journal of Computer Vision. 2025;133(4):1894-1911. doi:10.1007/s11263-024-02253-x
BibTeX
@article{Wang2025,
author = {Wang, Zhouxia and Wang, Xintao and Xie, Liangbin and Qi, Zhongang and Shan, Ying and Wang, Wenping and Luo, Ping},
title = {StyleAdapter: A Unified Stylized Image Generation Model},
journal = {International Journal of Computer Vision},
year = {2025},
volume = {133},
number = {4},
pages = {1894--1911},
doi = {10.1007/s11263-024-02253-x}
}
EUVIMED