MAST: Mask-Guided Attention Control for Training-Free Regional-Multi Style Transfer
MAST (Mask-Guided Attention Control for Training-Free Regional-Multi Style Transfer), a unified attention-control framework for frozen diffusion models, achieves the best average ArtFID, FID, and R-FID among all baselines, demonstrating regional style fidelity, content preservation, and scalability.
Dong-Sig Kang, Jae-Young Hwang, Junseo Park et al.
· 0 citations