2025/03/20 by Chen, Lei, Li, Hao, Zhang, Yuxin +2
#FOS: Computer and information sciences #Graphics (cs.GR)
paper · doi:10.48550/arxiv.2503.16133
Text-driven image style transfer has seen remarkable progress with methods leveraging cross-modal embeddings for fast, high-quality stylization. However, most existing pipelines assume a single textual style prompt, limiting the range of artistic control and expressiveness. In this paper, we propose a novel multi-prompt style interpolation framework that extends the recently introduced StyleMamba approach. Our method supports blending or interpolating among multiple textual prompts (eg, ``cubism,'' ``impressionism,'' and ``cartoon''), allowing the creation of nuanced or hybrid artistic styles within a single image. We introduce a Multi-Prompt Embedding Mixer combined with Adaptive Blending Weights to enable fine-grained control over the spatial and semantic influence of each style. Further, we propose a Hierarchical Masked Directional Loss to refine region-specific style consistency. Experiments and user studies confirm our approach outperforms single-prompt baselines and naive linear combinations of styles, achieving superior style fidelity, text-image alignment, and artistic flexibility, all while maintaining the computational efficiency offered by the state-space formulation.