PokeFusion Attention: Enhancing Reference-Free Style-Conditioned Generation

ArXi:2602.03220v2 Announce Type: replace This paper studies reference-free style-conditioned character generation in text-to-image diffusion models, where high-quality synthesis requires both stable character structure and consistent, fine-grained style expression across diverse prompts. Existing approaches primarily rely on text-only prompting, which is often under-specified for visual style and tends to produce noticeable style drift and geometric inconsistency, or