paper-with-me

Papers

CleanStyle: Plug-and-Play Style Conditioning Purification for Text-to-Image Stylization

2026-02-24 · Xiaoman Feng, Mingkun Lei, Yang Wang, Dingwen Fu, Chi Zhang arxiv

Style transfer in diffusion models enables controllable visual generation by injecting the style of a reference image. However, recent encoder-based methods, while efficient and tuning-free, often suffer from content leakage, where semantic elements from the style image undesirably appear in the output, impairing prompt fidelity and stylistic consistency. In this work, we introduce CleanStyle, a plug-and-play framework that filters out content-related noise from the style embedding without retraining. Motivated by empirical analysis, we observe that such leakage predominantly stems from the tail components of the style embedding, which are isolated via Singular Value Decomposition (SVD). To address this, we propose CleanStyleSVD (CS-SVD), which dynamically suppresses tail components using a time-aware exponential schedule, providing clean, style-preserving conditional embeddings throughout the denoising process. Furthermore, we present Style-Specific Classifier-Free Guidance (SS-CFG), which reuses the suppressed tail components to construct style-aware unconditional inputs. Unlike conventional methods that use generic negative embeddings (e.g., zero vectors), SS-CFG introduces targeted negative signals that reflect style-specific but prompt-irrelevant visual elements. This enables the model to effectively suppress these distracting patterns during generation, thereby improving prompt fidelity and enhancing the overall visual quality of stylized outputs. Our approach is lightweight, interpretable, and can be seamlessly integrated into existing encoder-based diffusion models without retraining. Extensive experiments demonstrate that CleanStyle substantially reduces content leakage, improves stylization quality and improves prompt alignment across a wide range of style references and prompts.

📄 PDF Abstract BibTeX arXiv:2602.20721

Code (0)

등록된 구현이 없습니다.

Tasks

Style Transfer

Similar Papers 제목 키워드 기반

Self-supervised Adversarial Purification for Graph Neural Networks

2026-05-22 · Woohyun Lee, Hogun Park arxiv

Defending Graph Neural Networks (GNNs) against adversarial attacks requires balancing accuracy and robustness, a trade-off often mishandled by traditional methods like adversarial training that intertwine these conflicti…

Preconditioned Plug-and-Play ADMM with Locally Adjustable Denoiser for Image Restoration

2021-10-01 · Mikael Le Pendu, Christine Guillemot

Plug-and-Play optimization recently emerged as a powerful technique for solving inverse problems by plugging a denoiser into a classical optimization algorithm. The denoiser accounts for the regularization and therefore …

DemosaickingDenoisingImage DenoisingImage Restoration

PokeFusion Attention: A Lightweight Cross-Attention Mechanism for Style-Conditioned Image Generation

2026-02-03 · Jingbang Tang arxiv

Style-conditioned text-to-image (T2I) generation with diffusion models requires both stable character structure and consistent, fine-grained style expression across diverse prompts. Existing approaches either rely on tex…

Image Generation

Assisted Sound Sample Generation with Musical Conditioning in Adversarial Auto-Encoders

2019-04-12 · Adrien Bitton, Philippe Esling, Antoine Caillon, Martin Fouilleul

Generative models have thrived in computer vision, enabling unprecedented image processes. Yet the results in audio remain less advanced. Our project targets real-time sound synthesis from a reduced set of high-level par…

AttributeAudio GenerationDecoder

DBLP: Noise Bridge Consistency Distillation For Efficient And Reliable Adversarial Purification

2025-08-01 · Chihan Huang, Belal Alsinglawi, Islam Al-qudah arxiv

Recent advances in deep neural networks (DNNs) have led to remarkable success across a wide range of tasks. However, their susceptibility to adversarial perturbations remains a critical vulnerability. Existing diffusion-…