UltraStyle: Best of both worlds in style and content for style transfer

Yongqian Tan and Fanju Zeng

PLOS ONE, 2026, vol. 21, issue 4, 1-17

Abstract: Achieving an ideal balance between style fidelity and content preservation remains a critical challenge in style transfer. In this work, we present UltraStyle, a new framework that reconciles these two objectives through a reformulation of the learning process. Unlike prior LoRA-based methods that rely on noise prediction, UltraStyle adopts a reconstruction-centered optimization paradigm, allowing the diffusion model to better retain global structural features while faithfully reproducing stylistic patterns. We propose a dual-phase training method that first isolates content representations before specializing style learning, minimizing cross-interference. To further refine detail preservation without sacrificing structure, we introduce a progressive loss transition strategy during training. Moreover, we develop a flexible inference control mechanism that enables smooth adjustment of content and style influences in the generation phase. Experimental results demonstrate that UltraStyle consistently delivers stylized outputs with superior structural integrity and stylistic authenticity, significantly mitigating issues such as content drift and feature entanglement found in existing methods.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0346260 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 46260&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0346260

DOI: 10.1371/journal.pone.0346260

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().