StyleGallery: Training-free and Semantic-aware Personalized Style Transfer from Arbitrary Image References

ArXi:2603.10354v1 Announce Type: new Despite the advancements in diffusion-based image style transfer, existing methods are commonly limited by 1) semantic gap: the style reference could miss proper content semantics, causing uncontrollable stylization; 2) reliance on extra constraints (e.g., semantic masks) restricting applicability; 3) rigid feature associations lacking adaptive global-local alignment, failing to balance fine-grained stylization and global content preservation.