Proposing Face2Diffusion (F2D) for high-editability face personalization by disentangling identity-irrelevant information.
Face2Diffusion proposes novel components to improve face personalization by disentangling identity features and enhancing editability.
The author proposes Face2Diffusion (F2D) to improve face personalization by disentangling identity-irrelevant information, enhancing editability and fidelity.