Diffusion Sampling with Momentum for Mitigating Divergence Artifacts

by   Suttisak Wizadwongsa, et al.

Despite the remarkable success of diffusion models in image generation, slow sampling remains a persistent issue. To accelerate the sampling process, prior studies have reformulated diffusion sampling as an ODE/SDE and introduced higher-order numerical methods. However, these methods often produce divergence artifacts, especially with a low number of sampling steps, which limits the achievable acceleration. In this paper, we investigate the potential causes of these artifacts and suggest that the small stability regions of these methods could be the principal cause. To address this issue, we propose two novel techniques. The first technique involves the incorporation of Heavy Ball (HB) momentum, a well-known technique for improving optimization, into existing diffusion numerical methods to expand their stability regions. We also prove that the resulting methods have first-order convergence. The second technique, called Generalized Heavy Ball (GHVB), constructs a new high-order method that offers a variable trade-off between accuracy and artifact suppression. Experimental results show that our techniques are highly effective in reducing artifacts and improving image quality, surpassing state-of-the-art diffusion solvers on both pixel-based and latent-based diffusion models for low-step sampling. Our research provides novel insights into the design of numerical methods for future diffusion work.


page 22

page 23

page 25

page 28

page 29

page 30

page 31

page 37


Accelerating Guided Diffusion Sampling with Splitting Numerical Methods

Guided diffusion is a technique for conditioning the output of a diffusi...

DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models

Diffusion probabilistic models (DPMs) have achieved impressive success i...

Improved Order Analysis and Design of Exponential Integrator for Diffusion Models Sampling

Efficient differential equation solvers have significantly reduced the s...

Parallel Sampling of Diffusion Models

Diffusion models are powerful generative models but suffer from slow sam...

Fast Diffusion Model

Despite their success in real data synthesis, diffusion models (DMs) oft...

Bi-Noising Diffusion: Towards Conditional Diffusion Models with Generative Restoration Priors

Conditional diffusion probabilistic models can model the distribution of...

Efficient Diffusion Training via Min-SNR Weighting Strategy

Denoising diffusion models have been a mainstream approach for image gen...

Please sign up or login with your details

Forgot password? Click here to reset