On Fast Sampling of Diffusion Probabilistic Models

Abstract

In this work, we propose FastDPM, a unified framework for fast sampling in diffusion probabilistic models. FastDPM generalizes previous methods and gives rise to new algorithms with improved sample quality. We systematically investigate the fast sampling methods under this framework across different domains, on different datasets, and with different amount of conditional information provided for generation. We find the performance of a particular method depends on data domains (e.g., image or audio), the trade-off between sampling speed and sample quality, and the amount of conditional information. We further provide insights and recipes on the choice of methods for practitioners.

arXiv commentCode is released

References in corpus (21)

• Denoising Diffusion Probabilistic Models
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Diffusion Models Beat GANs on Image Synthesis
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Score-Based Generative Modeling through Stochastic Differential Equations
• Generative Modeling by Estimating Gradients of the Data Distribution
• Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
• Improved Techniques for Training Score-Based Generative Models
• DiffWave: A Versatile Diffusion Model for Audio Synthesis
• Denoising Diffusion Implicit Models
• NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
• Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech
• Noise Estimation for Generative Diffusion Models
• Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
• SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models
• Diffusion Probabilistic Models for 3D Point Cloud Generation
• Learning Energy-Based Models by Diffusion Recovery Likelihood
• Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net
• Symbolic Music Generation with Diffusion Models
• Diff-TTS: A Denoising Diffusion Model for Text-to-Speech

Cited by in corpus (12)

• Diffusion Models in Vision: A Survey
• Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review
• A Survey on Neural Speech Synthesis
• DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
• Learning to Efficiently Sample from Diffusion Probabilistic Models
• Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
• Latent Denoising Diffusion GAN: Faster sampling, Higher image quality
• ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation
• Bilateral Denoising Diffusion Models
• Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
• Denoising Diffusion Gamma Models
• Autoregressive Diffusion Models