Only-Style: Stylistic Consistency in Image Generation without Content Leakage

• URL: http://arxiv.org/abs/2506.09916v1
• Date: Wed, 11 Jun 2025 16:33:09 GMT
• Title: Only-Style: Stylistic Consistency in Image Generation without Content Leakage
• Authors: Tilemachos Aravanis, Panagiotis Filntisis, Petros Maragos, George Retsinas,
• Abstract summary: Only-Style is a method designed to mitigate content leakage in a semantically coherent manner while preserving stylistic consistency.<n>Only-Style works by localizing content leakage during inference, allowing the adaptive tuning of a parameter that controls the style alignment process.<n>Our approach demonstrates a significant improvement over state-of-the-art methods through extensive evaluation across diverse instances.
• Score: 21.68241134664501
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating images in a consistent reference visual style remains a challenging computer vision task. State-of-the-art methods aiming for style-consistent generation struggle to effectively separate semantic content from stylistic elements, leading to content leakage from the image provided as a reference to the targets. To address this challenge, we propose Only-Style: a method designed to mitigate content leakage in a semantically coherent manner while preserving stylistic consistency. Only-Style works by localizing content leakage during inference, allowing the adaptive tuning of a parameter that controls the style alignment process, specifically within the image patches containing the subject in the reference image. This adaptive process best balances stylistic consistency with leakage elimination. Moreover, the localization of content leakage can function as a standalone component, given a reference-target image pair, allowing the adaptive tuning of any method-specific parameter that provides control over the impact of the stylistic reference. In addition, we propose a novel evaluation framework to quantify the success of style-consistent generations in avoiding undesired content leakage. Our approach demonstrates a significant improvement over state-of-the-art methods through extensive evaluation across diverse instances, consistently achieving robust stylistic consistency without undesired content leakage.

Related papers

• ConsiStyle: Style Diversity in Training-Free Consistent T2I Generation [49.1574468325115]
  We introduce a training-free method that achieves both style alignment and subject consistency.<n>Our method effectively decouples style from subject appearance and enables faithful generation of text-aligned images.
  arXiv  Detail & Related papers  (2025-05-27T02:06:08Z)
• LLM-Enabled Style and Content Regularization for Personalized Text-to-Image Generation [14.508665960053643]
  The personalized text-to-image generation has rapidly advanced with the emergence of Stable Diffusion.<n>Existing methods, which typically fine-tune models using embedded identifiers, often struggle with insufficient stylization and inaccurate image content.<n>We propose style refinement and content preservation strategies.
  arXiv  Detail & Related papers  (2025-04-19T04:08:42Z)
• ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfer [20.088714830700916]
  Style transfer involves transferring the style from a reference image to the content of a target image.<n>Recent advancements in LoRA-based (Low-Rank Adaptation) methods have shown promise in effectively capturing the style of a single image.<n>These approaches still face significant challenges such as content inconsistency, style misalignment, and content leakage.
  arXiv  Detail & Related papers  (2025-03-13T17:55:58Z)
• AttenST: A Training-Free Attention-Driven Style Transfer Framework with Pre-Trained Diffusion Models [4.364797586362505]
  AttenST is a training-free attention-driven style transfer framework.<n>We propose a style-guided self-attention mechanism that conditions self-attention on the reference style.<n>We also introduce a dual-feature cross-attention mechanism to fuse content and style features.
  arXiv  Detail & Related papers  (2025-03-10T13:28:36Z)
• ZePo: Zero-Shot Portrait Stylization with Faster Sampling [61.14140480095604]
  This paper presents an inversion-free portrait stylization framework based on diffusion models that accomplishes content and style feature fusion in merely four sampling steps. We propose a feature merging strategy to amalgamate redundant features in Consistency Features, thereby reducing the computational load of attention control.
  arXiv  Detail & Related papers  (2024-08-10T08:53:41Z)
• InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation [4.1177497612346]
  Style transfer is an inventive process designed to create an image that maintains the essence of the original while embracing the visual style of another. We introduce InstantStyle-Plus, an approach that prioritizes the integrity of the original content while seamlessly integrating the target style.
  arXiv  Detail & Related papers  (2024-06-30T18:05:33Z)
• ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model [73.95608242322949]
  Stylized Text-to-Image Generation (STIG) aims to generate images from text prompts and style reference images. We present ArtWeaver, a novel framework that leverages pretrained Stable Diffusion to address challenges such as misinterpreted styles and inconsistent semantics.
  arXiv  Detail & Related papers  (2024-05-24T07:19:40Z)
• StyleAdapter: A Unified Stylized Image Generation Model [97.24936247688824]
  StyleAdapter is a unified stylized image generation model capable of producing a variety of stylized images. It can be integrated with existing controllable synthesis methods, such as T2I-adapter and ControlNet.
  arXiv  Detail & Related papers  (2023-09-04T19:16:46Z)
• Style Intervention: How to Achieve Spatial Disentanglement with Style-based Generators? [100.60938767993088]
  We propose a lightweight optimization-based algorithm which could adapt to arbitrary input images and render natural translation effects under flexible objectives. We verify the performance of the proposed framework in facial attribute editing on high-resolution images, where both photo-realism and consistency are required.
  arXiv  Detail & Related papers  (2020-11-19T07:37:31Z)
• Parameter-Free Style Projection for Arbitrary Style Transfer [64.06126075460722]
  This paper proposes a new feature-level style transformation technique, named Style Projection, for parameter-free, fast, and effective content-style transformation. This paper further presents a real-time feed-forward model to leverage Style Projection for arbitrary image style transfer.
  arXiv  Detail & Related papers  (2020-03-17T13:07:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.