A Training-Free Style-Personalization via SVD-Based Feature Decomposition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Kyoungmin, Park, Jihun, Gim, Jongmin, Choi, Wonhyeok, Hwang, Kyumin, Kim, Jaeyeul, Im, Sunghoon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915630443134976
author Lee, Kyoungmin
Park, Jihun
Gim, Jongmin
Choi, Wonhyeok
Hwang, Kyumin
Kim, Jaeyeul
Im, Sunghoon
author_facet Lee, Kyoungmin
Park, Jihun
Gim, Jongmin
Choi, Wonhyeok
Hwang, Kyumin
Kim, Jaeyeul
Im, Sunghoon
contents We present a training-free framework for style-personalized image generation that operates during inference using a scale-wise autoregressive model. Our method generates a stylized image guided by a single reference style while preserving semantic consistency and mitigating content leakage. Through a detailed step-wise analysis of the generation process, we identify a pivotal step where the dominant singular values of the internal feature encode style-related components. Building upon this insight, we introduce two lightweight control modules: Principal Feature Blending, which enables precise modulation of style through SVD-based feature reconstruction, and Structural Attention Correction, which stabilizes structural consistency by leveraging content-guided attention correction across fine stages. Without any additional training, extensive experiments demonstrate that our method achieves competitive style fidelity and prompt fidelity compared to fine-tuned baselines, while offering faster inference and greater deployment flexibility.
format Preprint
id arxiv_https___arxiv_org_abs_2507_04482
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Training-Free Style-Personalization via SVD-Based Feature Decomposition
Lee, Kyoungmin
Park, Jihun
Gim, Jongmin
Choi, Wonhyeok
Hwang, Kyumin
Kim, Jaeyeul
Im, Sunghoon
Computer Vision and Pattern Recognition
We present a training-free framework for style-personalized image generation that operates during inference using a scale-wise autoregressive model. Our method generates a stylized image guided by a single reference style while preserving semantic consistency and mitigating content leakage. Through a detailed step-wise analysis of the generation process, we identify a pivotal step where the dominant singular values of the internal feature encode style-related components. Building upon this insight, we introduce two lightweight control modules: Principal Feature Blending, which enables precise modulation of style through SVD-based feature reconstruction, and Structural Attention Correction, which stabilizes structural consistency by leveraging content-guided attention correction across fine stages. Without any additional training, extensive experiments demonstrate that our method achieves competitive style fidelity and prompt fidelity compared to fine-tuned baselines, while offering faster inference and greater deployment flexibility.
title A Training-Free Style-Personalization via SVD-Based Feature Decomposition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.04482