LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models

arXiv:2404.11098v1 Announce Type: new
Abstract: In the era of AIGC, the demand for low-budget or even on-device applications of diffusion models emerged. In terms of compressing the Stable Diffusion models (SDMs), several approaches have been proposed, and most of them leveraged the handcrafted layer removal methods to obtain smaller U-Nets, along with knowledge distillation to recover the network performance. However, such a handcrafting manner of layer removal is inefficient and lacks scalability and generalization, and the feature distillation employed in …

abstract aigc applications arxiv budget cs.cv demand diff diffusion diffusion models distillation laptop layer low pruning stable diffusion stable diffusion models terms them type