SciRE-Solver: Accelerating Diffusion Models Sampling by Score-integrand Solver with Recursive Difference

Shigui Li, Wei Chen, Delu Zeng

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Diffusion Models, Sampler, Accelerating

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We introduce the recursive difference method to calculate the derivative of the score function in the realm of DMs, and propose SciRE-Solver for accelerating sampling of DM.

Abstract:

One downside of Diffusion models (DMs) is their slow iterative process. Recent algorithms for fast sampling are designed from the
differential equations. However, in the fast algorithms, estimating the derivative of the score function evaluations becomes intractable due to the complexity of large-scale, well-trained neural networks. In this work, we introduce the recursive difference method to calculate the derivative of the score function networks. Building upon, we propose \emph{SciRE-Solver} with the convergence order guarantee for accelerating DMs sampling. Our proposed sampling algorithms attain SOTA FIDs in comparison to existing training-free sampling algorithms,
under various number of score function evaluations (NFE). Such as, we achieve $3.48$ FID with $12$ NFE, and $2.42$ FID with $20$ NFE for continuous-time model on CIFAR-10; $1.79$ FID with $20$ NFE and $1.76$ FID with $100$ NFE for the pretrained model of EDM. Experiments demonstrate also that demonstrate that SciRE-Solver with multi-step methods can achieve high-quality samples on popular text-to-image generation tasks with only 6$\sim$20 NFEs.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 4270