Accelerating Diffusion Sampling with Classifier-based Feature Distillation
Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distillation is thus proposed for fast sampling by progressively aligning output images of $N$-step teacher sampler with $N/2$-step student sampler. In this paper, we argue that this distillation-based accelerating method can be further improved, especially for few-step samplers, with our proposed \textbf{C}lassifier-based \textbf{F}eature \textbf{D}istillation (CFD). Instead of aligning output images, we distill teacher's sharpened feature distribution into the student with a dataset-independent classifier, making the student focus on those important features to improve performance. We also introduce a dataset-oriented loss to further optimize the model. Experiments on CIFAR-10 show the superiority of our method in achieving high quality and fast sampling. Code is provided at \url{https://github.com/zju-SWJ/RCFD}.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Attention Distillation: A Unified Approach to Visual Characteristics Transfer
Recent advances in generative diffusion models have shown a notable inherent understanding of image style and semantics. In this paper, we leverage the self-attention features from pretrained diffusion networks to transf…
DenoisingImage GenerationAccelerating Diffusion Models with One-to-Many Knowledge Distillation
Significant advancements in image generation have been made with diffusion models. Nevertheless, when contrasted with previous generative models, diffusion models face substantial computational overhead, leading to failu…
Image GenerationKnowledge DistillationOn Distillation of Guided Diffusion Models
Classifier-free guided diffusion models have recently been shown to be highly effective at high-resolution image generation, and they have been widely used in large-scale diffusion frameworks including DALLE-2, Stable Di…
DenoisingImage Generationtext-guided-image-editingPresto! Distilling Steps and Layers for Accelerating Music Generation
Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers …
DiversityMusic GenerationAccelerating the Generation of Molecular Conformations with Progressive Distillation of Equivariant Latent Diffusion Models
Recent advances in fast sampling methods for diffusion models have demonstrated significant potential to accelerate generation on image modalities. We apply these methods to 3-dimensional molecular conformations by build…
Drug Discovery