AI RESEARCH
WaDi: Weight Direction-aware Distillation for One-step Image Synthesis
arXiv CS.CV
•
ArXi:2603.08258v1 Announce Type: new Despite the impressive performance of diffusion models such as Stable Diffusion (SD) in image generation, their slow inference limits practical deployment. Recent works accelerate inference by distilling multi-step diffusion into one-step generators. To better understand the distillation mechanism, we analyze U-Net/DiT weight changes between one-step students and their multi-step teacher counterparts. Our analysis reveals that changes in weight direction significantly exceed those in weight norm, highlighting it as the key factor during distillation.