LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models
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 the retraining phase faces an imbalance issue that a few numerically significant feature loss terms dominate over others throughout the retraining process. To this end, we proposed the layer pruning and normalized distillation for compressing diffusion models (LAPTOP-Diff). We, 1) introduced the layer pruning method to compress SDM's U-Net automatically and proposed an effective one-shot pruning criterion whose one-shot performance is guaranteed by its good additivity property, surpassing other layer pruning and handcrafted layer removal methods, 2) proposed the normalized feature distillation for retraining, alleviated the imbalance issue. Using the proposed LAPTOP-Diff, we compressed the U-Nets of SDXL and SDM-v1.5 for the most advanced performance, achieving a minimal 4.0% decline in PickScore at a pruning ratio of 50% while the comparative methods' minimal PickScore decline is 8.2%. We will release our code.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge DistillationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Structured Pruning Learns Compact and Accurate Models
The growing size of neural language models has led to increased attention in model compression. The two predominant approaches are pruning, which gradually removes weights from a pre-trained model, and distillation, whic…
Model CompressionPluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers
Diffusion Transformers (DiTs) have shown exceptional performance in image generation, yet their large parameter counts incur high computational costs, impeding deployment in resource-constrained settings. To address this…
Image GenerationGreedy-layer Pruning: Speeding up Transformer Models for Natural Language Processing
Fine-tuning transformer models after unsupervised pre-training reaches a very high performance on many different natural language processing tasks. Unfortunately, transformers suffer from long inference times which great…
Knowledge DistillationUnsupervised Pre-trainingStructured Pruning Learns Compact and Accurate Models
The growing size of neural language models has led to increased attention in model compression. Pruning methods start from a large model and gradually remove model weights---they can significantly reduce the model size b…
Model CompressionClass-Discriminative CNN Compression
Compressing convolutional neural networks (CNNs) by pruning and distillation has received ever-increasing focus in the community. In particular, designing a class-discrimination based approach would be desired as it fits…