DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps

Abstract

Diffusion probabilistic models (DPMs) are emerging powerful generative models. Despite their high-quality generation performance, DPMs still suffer from their slow sampling as they generally need hundreds or thousands of sequential function evaluations (steps) of large neural networks to draw a sample. Sampling from DPMs can be viewed alternatively as solving the corresponding diffusion ordinary differential equations (ODEs). In this work, we propose an exact formulation of the solution of diffusion ODEs. The formulation analytically computes the linear part of the solution, rather than leaving all terms to black-box ODE solvers as adopted in previous works. By applying change-of-variable, the solution can be equivalently simplified to an exponentially weighted integral of the neural network. Based on our formulation, we propose DPM-Solver, a fast dedicated high-order solver for diffusion ODEs with the convergence order guarantee. DPM-Solver is suitable for both discrete-time and continuous-time DPMs without any further training. Experimental results show that DPM-Solver can generate high-quality samples in only 10 to 20 function evaluations on various datasets. We achieve 4.70 FID in 10 function evaluations and 2.87 FID in 20 function evaluations on the CIFAR10 dataset, and a $4\sim 16\times$ speedup compared with previous state-of-the-art training-free samplers on various datasets.

Accepted in Neurips 2022

Cited by in corpus (17)

• Diffusion Models in Vision: A Survey
• DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
• Diffusion Models, Image Super-Resolution And Everything: A Survey
• LDMVFI: Video Frame Interpolation with Latent Diffusion Models
• Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects
• Synthetic Lagrangian Turbulence by Generative Diffusion Models
• PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics
• StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
• Face Morphing Attack Detection with Denoising Diffusion Probabilistic Models
• LightGrad: Lightweight Diffusion Probabilistic Model for Text-to-Speech
• Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction
• Diffusion-Based Surrogate Modeling and Multi-Fidelity Calibration
• Convergence Analysis of Probability Flow ODE for Score-based Generative Models
• Optimal Linear Subspace Search: Learning to Construct Fast and High-Quality Schedulers for Diffusion Models
• Fast Inference in Denoising Diffusion Models via MMD Finetuning
• Training-free Subject-Enhanced Attention Guidance for Compositional Text-to-image Generation
• Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value Optimization