# MAST: Mask-Guided Attention Control for Training-Free Regional-Multi Style Transfer

arXiv: https://arxiv.org/abs/2604.12281 · HTML: https://mlsanity.com/paper/2604.12281/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Builds on (most cited first, 29 of 29)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [Inversion-Based Style Transfer with Diffusion Models](https://mlsanity.com/paper/2211.13203/) (2022)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer](https://mlsanity.com/paper/2312.09008/) (2023)
- [StyTr2: Image Style Transfer with Transformers](https://mlsanity.com/paper/2105.14576/) (2021)
- [StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models](https://mlsanity.com/paper/2308.07863/) (2023)
- [ArtFID: Quantitative Evaluation of Neural Style Transfer](https://mlsanity.com/paper/2207.12280/) (2022)
- [Softmax is not Enough (for Sharp Size Generalisation)](https://mlsanity.com/paper/2410.01104/) (2024)
- [StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer](https://mlsanity.com/paper/2501.11319/) (2025)
- [Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate](https://mlsanity.com/paper/2304.09728/) (2023)
- [Fine-Grained Image Style Transfer with Visual Transformers](https://mlsanity.com/paper/2210.05176/) (2022)
- [AttenST: A Training-Free Attention-Driven Style Transfer Framework with Pre-Trained Diffusion Models](https://mlsanity.com/paper/2503.07307/) (2025)
- [ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfer](https://mlsanity.com/paper/2503.10614/) (2025)
- [Style Mixer: Semantic-aware Multi-Style Transfer Network](https://mlsanity.com/paper/1910.13093/) (2019)
- [Controllable Style Transfer via Test-time Training of Implicit Neural Representation](https://mlsanity.com/paper/2210.07762/) (2022)
- [An Efficient and Harmonized Framework for Balanced Cross-Domain Feature Integration](https://mlsanity.com/paper/2403.18461/) (2024)
- [DiffuseST: Unleashing the Capability of the Diffusion Model for Style Transfer](https://mlsanity.com/paper/2410.15007/) (2024)
- [StyleGallery: Training-free and Semantic-aware Personalized Style Transfer from Arbitrary Image References](https://mlsanity.com/paper/2603.10354/) (2026)
- [Improving Masked Style Transfer using Blended Partial Convolution](https://mlsanity.com/paper/2508.05769/) (2025)
- [Leveraging Diffusion Models for Stylization using Multiple Style Images](https://mlsanity.com/paper/2508.12784/) (2025)
- [SCAdapter: Content-Style Disentanglement for Diffusion Style Transfer](https://mlsanity.com/paper/2512.12963/) (2025)
- [CoCoDiff: Correspondence-Consistent Diffusion Model for Fine-grained Style Transfer](https://mlsanity.com/paper/2602.14464/) (2026)
- [RegionRoute: Regional Style Transfer with Diffusion Model](https://mlsanity.com/paper/2602.19254/) (2026)

## Abstract (arXiv)

Style transfer applies the appearance of a reference image to a content image while preserving its spatial structure. Recent diffusion-based methods achieve strong stylization but typically assume a single global style. We instead consider regional-multi style transfer, which assigns multiple references to user-specified regions of a content image. Extending them to this setting reveals two coupled shared-attention issues: ambiguous mass allocation among content and style partitions and degraded selectivity as more styles are jointly normalized, while style aggregation at the attention output further suppresses fine details. We propose MAST (Mask-Guided Attention Control for Training-Free Regional-Multi Style Transfer), a unified attention-control framework for frozen diffusion models. Logit-level Attention Mass Allocation enforces mask-derived partition masses, Sharpness-aware Temperature Scaling adaptively restores selectivity, and Discrepancy-aware Detail Injection recovers high-frequency content. MAST jointly processes all style--mask pairs in a single denoising pass without training, optimization, or post-hoc composition. Across two to five styles, MAST achieves the best average ArtFID, FID, and R-FID among all baselines, demonstrating regional style fidelity, content preservation, and scalability.