AI RESEARCH
Adversarial Concept Distillation for One-Step Diffusion Personalization
arXiv CS.CV
•
ArXi:2510.20512v2 Announce Type: replace Recent progress in accelerating text-to-image diffusion models enables high-fidelity synthesis within a single denoising step. However, customizing the fast one-step models remains challenging, as existing methods consistently fail to produce acceptable results, underscoring the need for new methodologies to personalize one-step models. Therefore, we propose One-step Personalized Adversarial Distillation (OPAD), a framework that combines teacher-student distillation with adversarial supervision.