Zero-Shot Image Style Transfer Using Conditional Inversion-Free Flow
Journal of Imaging · 09.11.2026 · 12 (11) · 565
DOI: 10.3390/jimaging12110565 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 09.11.2026. Verfasst von Guowen Zhu und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shandong Provincial Natural Science Foundation.
Abstract (Originalsprache)
Zero-shot image style transfer has recently attracted increasing attention, as it enables style manipulation without additional model optimization or parameter tuning. However, most existing approaches still rely on latent inversion, where introduced reconstruction errors may accumulate and gradually degrade content structures. Moreover, current style transfer methods still struggle to balance style strength and content preservation due to inadequate guidance. To address these issues, this paper proposes a novel zero-shot image style transfer method based on conditional inversion-free flow. Built upon pre-trained Flow Matching models, our method eliminates the inversion by constructing a style-transfer trajectory ODE from a gradient-injected discrepancy between content-conditioned and style-conditioned velocity fields. To further enhance style representation, we introduce a conditional guidance mechanism driven by a pre-trained CLIP model. Specifically, a style loss is introduced to align the Gram matrix statistics of CLIP features with those of the reference style; a semantic consistency constraint based on CLIP embedding cosine distance preserves high-level semantics. The dual guidance terms are incorporated during the inversion-free editing stage through loss gradients, guiding the generation trajectory without model fine-tuning or access to internal model features. Extensive quantitative and qualitative experiments demonstrate that our method outperforms state-of-the-art approaches, providing a better balance between style consistency and content preservation.
Förderung
- Shandong Provincial Natural Science Foundation
Zitieren
APA
Zhu, G., Zhang, X., Xiao, Q., Cheng, J., & Zim, H. M. (2026). Zero-Shot Image Style Transfer Using Conditional Inversion-Free Flow. Journal of Imaging, 12(11), 565. https://doi.org/10.3390/jimaging12110565
Vancouver
Zhu G, Zhang X, Xiao Q, Cheng J, Zim HM. Zero-Shot Image Style Transfer Using Conditional Inversion-Free Flow. Journal of Imaging. 2026;12(11):565. doi:10.3390/jimaging12110565
BibTeX
@article{Zhu2026,
author = {Zhu, Guowen and Zhang, Xiancong and Xiao, Qingguo and Cheng, Jianda and Zim, Hamim Mustafiz},
title = {Zero-Shot Image Style Transfer Using Conditional Inversion-Free Flow},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {11},
pages = {565},
doi = {10.3390/jimaging12110565}
}
EUVIMED