Denoising Diffusion Implicit Models

Abstract

Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present denoising diffusion implicit models (DDIMs), a more efficient class of iterative implicit probabilistic models with the same training procedure as DDPMs. In DDPMs, the generative process is defined as the reverse of a Markovian diffusion process. We construct a class of non-Markovian diffusion processes that lead to the same training objective, but whose reverse process can be much faster to sample from. We empirically demonstrate that DDIMs can produce high quality samples $10\times$ to $50\times$ faster in terms of wall-clock time compared to DDPMs, allow us to trade off computation for sample quality, and can perform semantically meaningful image interpolation directly in the latent space.

ICLR 2021; updated connections with ODEs at page 6, fixed some typos in the proof

References in corpus (5)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Learning in Implicit Generative Models
• Adversarial score matching and improved sampling for image generation
• Continuous-in-Depth Neural Networks

Cited by in corpus (24)

• Diffusion Models Beat GANs on Image Synthesis
• Variational Diffusion Models
• A Survey on Neural Speech Synthesis
• UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models
• Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
• Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling
• On Fast Sampling of Diffusion Probabilistic Models
• Learning to Efficiently Sample from Diffusion Probabilistic Models
• Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
• Score-Based Generative Models for PET Image Reconstruction
• Gotta Go Fast When Generating Data with Score-Based Models
• Non Gaussian Denoising Diffusion Models
• ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models
• Bilateral Denoising Diffusion Models
• Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery
• Active inference and deep generative modeling for cognitive ultrasound
• PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real Images
• Diff-TTS: A Denoising Diffusion Model for Text-to-Speech
• Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction
• Denoising Diffusion Gamma Models
• Deep Generative Learning via Schrödinger Bridge
• D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
• Turbulent Injection assisted by Diffusion Models for Scale Resolving Simulations
• Improving Compositionality of Neural Networks by Decoding Representations to Inputs