Training-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916963831250944 |
|---|---|
| author | Liu, Xu Lu, Yibo Wang, Xinxian Wu, Xinyu |
| author_facet | Liu, Xu Lu, Yibo Wang, Xinxian Wu, Xinyu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18602 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Training-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation Liu, Xu Lu, Yibo Wang, Xinxian Wu, Xinyu Computer Vision and Pattern Recognition 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. |
| title | Training-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.18602 |