Training-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation

• URL: http://arxiv.org/abs/2509.18602v1
• Date: Tue, 23 Sep 2025 03:47:59 GMT
• Title: Training-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation
• Authors: Xu Liu, Yibo Lu, Xinxian Wang, Xinyu Wu,
• Abstract summary: Adaptive Multi-Style Fusion (AMSF) is a training-free framework that enables controllable fusion of multiple reference styles in diffusion models.<n>AMSF produces multi-style fusion results that consistently outperform state-of-the-art approaches.<n>These capabilities position AMSF as a practical step toward expressive multi-style generation in diffusion models.
• Score: 10.053310365345412
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose Adaptive Multi-Style Fusion (AMSF), a reference-based training-free framework that enables controllable fusion of multiple reference styles in diffusion models. Most of the existing reference-based methods are limited by (a) acceptance of only one style image, thus prohibiting hybrid aesthetics and scalability to more styles, and (b) lack of a principled mechanism to balance several stylistic influences. AMSF mitigates these challenges by encoding all style images and textual hints with a semantic token decomposition module that is adaptively injected into every cross-attention layer of an frozen diffusion model. A similarity-aware re-weighting module then recalibrates, at each denoising step, the attention allocated to every style component, yielding balanced and user-controllable blends without any fine-tuning or external adapters. Both qualitative and quantitative evaluations show that AMSF produces multi-style fusion results that consistently outperform the state-of-the-art approaches, while its fusion design scales seamlessly to two or more styles. These capabilities position AMSF as a practical step toward expressive multi-style generation in diffusion models.

Related papers

• Bridging the Discrete-Continuous Gap: Unified Multimodal Generation via Coupled Manifold Discrete Absorbing Diffusion [60.186310080523135]
  Bifurcation of generative modeling into autoregressive approaches for discrete data (text) and diffusion approaches for continuous data (images) hinders development of truly unified multimodal systems.<n>We propose textbfCoM-DAD, a novel probabilistic framework that reformulates multimodal generation as a hierarchical dual-process.<n>Our method demonstrates superior stability over standard masked modeling, establishing a new paradigm for scalable, unified text-image generation.
  arXiv  Detail & Related papers  (2026-01-07T16:21:19Z)
• Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach [99.80480649258557]
  DiTFuse is an instruction-driven framework that performs semantics-aware fusion within a single model.<n>Experiments on public IVIF, MFF, and MEF benchmarks confirm superior quantitative and qualitative performance, sharper textures, and better semantic retention.
  arXiv  Detail & Related papers  (2025-12-08T05:04:54Z)
• Adding Additional Control to One-Step Diffusion with Joint Distribution Matching [58.37264951734603]
  JDM is a novel approach that minimizes the reverse KL divergence between image-condition joint distributions.<n>By deriving a tractable upper bound, JDM decouples fidelity learning from condition learning.<n>This asymmetric distillation scheme enables our one-step student to handle controls unknown to the teacher model.
  arXiv  Detail & Related papers  (2025-03-09T15:06:50Z)
• Conditional Controllable Image Fusion [56.4120974322286]
  conditional controllable fusion (CCF) framework for general image fusion tasks without specific training. CCF employs specific fusion constraints for each individual in practice. Experiments validate our effectiveness in general fusion tasks across diverse scenarios.
  arXiv  Detail & Related papers  (2024-11-03T13:56:15Z)
• 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)
• No Re-Train, More Gain: Upgrading Backbones with Diffusion model for Pixel-Wise and Weakly-Supervised Few-Shot Segmentation [22.263029309151467]
  Few-Shot (FSS) aims to segment novel classes using only a few annotated images.<n>Current FSS methods face three issues: the inflexibility of backbone upgrade without re-training, the inability to uniformly handle various types of annotations.<n>We propose DiffUp, a novel framework that conceptualizes the FSS task as a conditional generative problem using a diffusion process.
  arXiv  Detail & Related papers  (2024-07-23T05:09:07Z)
• MM-Diff: High-Fidelity Image Personalization via Multi-Modal Condition Integration [7.087475633143941]
  MM-Diff is a tuning-free image personalization framework capable of generating high-fidelity images of both single and multiple subjects in seconds. MM-Diff employs a vision encoder to transform the input image into CLS and patch embeddings. CLS embeddings are used on the one hand to augment the text embeddings, and on the other hand together with patch embeddings to derive a small number of detail-rich subject embeddings.
  arXiv  Detail & Related papers  (2024-03-22T09:32:31Z)
• Unleashing Network Potentials for Semantic Scene Completion [50.95486458217653]
  This paper proposes a novel SSC framework - Adrial Modality Modulation Network (AMMNet) AMMNet introduces two core modules: a cross-modal modulation enabling the interdependence of gradient flows between modalities, and a customized adversarial training scheme leveraging dynamic gradient competition. Extensive experimental results demonstrate that AMMNet outperforms state-of-the-art SSC methods by a large margin.
  arXiv  Detail & Related papers  (2024-03-12T11:48:49Z)
• HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models [84.12784265734238]
  The goal of Arbitrary Style Transfer (AST) is injecting the artistic features of a style reference into a given image/video. We propose HiCAST, which is capable of explicitly customizing the stylization results according to various source of semantic clues. A novel learning objective is leveraged for video diffusion model training, which significantly improve cross-frame temporal consistency.
  arXiv  Detail & Related papers  (2024-01-11T12:26:23Z)
• ArtFusion: Controllable Arbitrary Style Transfer using Dual Conditional Latent Diffusion Models [0.0]
  Arbitrary Style Transfer (AST) aims to transform images by adopting the style from any selected artwork. We propose a new approach, ArtFusion, which provides a flexible balance between content and style.
  arXiv  Detail & Related papers  (2023-06-15T17:58:36Z)
• Balanced Multimodal Learning via On-the-fly Gradient Modulation [10.5602074277814]
  Multimodal learning helps to comprehensively understand the world, by integrating different senses. We propose on-the-fly gradient modulation to adaptively control the optimization of each modality, via monitoring the discrepancy of their contribution towards the learning objective.
  arXiv  Detail & Related papers  (2022-03-29T08:26:38Z)

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.