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

TL;DR

This paper introduces a training-free, SVD-based method for style-personalized image generation that achieves high style fidelity and structural consistency during inference without additional training.

Contribution

It proposes a novel, training-free framework using SVD feature decomposition for style control in image generation, with two lightweight modules for style modulation and structural stability.

Findings

Achieves competitive style and prompt fidelity without training.

Offers faster inference and greater deployment flexibility.

Maintains semantic consistency and mitigates content leakage.

Abstract

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.