D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models 事件

D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models arXiv:2605.05204v3 Announce Type: replace Abstract: The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and FLUX.2-klein). However, these models present significant challenges for direct continuous supervised fine-tuning. For example, applying the commonly used fine-tuning technique