AttDiff-GAN: A Hybrid Diffusion-GAN Framework for Facial Attribute Editing

ArXi:2604.21289v1 Announce Type: new Facial attribute editing aims to modify target attributes while preserving attribute-irrelevant content and overall image fidelity. Existing GAN-based methods provide favorable controllability, but often suffer from weak alignment between style codes and attribute semantics. Diffusion-based methods can synthesize highly realistic images; however, their editing precision is limited by the entanglement of semantic directions among different attributes.