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

TL;DR

DPM-Solver++ is a high-order, fast solver for guided sampling in diffusion probabilistic models, significantly reducing the number of steps needed for high-quality image synthesis compared to existing methods.

Contribution

The paper introduces DPM-Solver++, a novel high-order solver that improves guided sampling speed and stability in diffusion models, outperforming previous solvers especially at large guidance scales.

Findings

DPM-Solver++ generates high-quality images in 15-20 steps.

It outperforms DDIM and previous high-order solvers in speed and stability.

The multistep variant reduces instability issues.

Abstract

Diffusion probabilistic models (DPMs) have achieved impressive success in high-resolution image synthesis, especially in recent large-scale text-to-image generation applications. An essential technique for improving the sample quality of DPMs is guided sampling, which usually needs a large guidance scale to obtain the best sample quality. The commonly-used fast sampler for guided sampling is DDIM, a first-order diffusion ODE solver that generally needs 100 to 250 steps for high-quality samples. Although recent works propose dedicated high-order solvers and achieve a further speedup for sampling without guidance, their effectiveness for guided sampling has not been well-tested before. In this work, we demonstrate that previous high-order fast samplers suffer from instability issues, and they even become slower than DDIM when the guidance scale grows large. To further speed up guided sampling, we propose DPM-Solver++, a high-order solver for the guided sampling of DPMs. DPM-Solver++ solves the diffusion ODE with the data prediction model and adopts thresholding methods to keep the solution matches training data distribution. We further propose a multistep variant of DPM-Solver++ to address the instability issue by reducing the effective step size. Experiments show that DPM-Solver++ can generate high-quality samples within only 15 to 20 steps for guided sampling by pixel-space and latent-space DPMs.