mlsanityData to 7 Oct 2026

Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling

arXiv 2207.02196 ↗First posted 5 Jul 2022cs.CVcited by 19

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Score-based generative models (SGMs) have recently emerged as a promising class of generative models. However, a fundamental limitation is that their inference is very slow due to a need for many (e.g., 2000) iterations of sequential computations. An intuitive acceleration method is to reduce the sampling iterations which however causes severe performance degradation. We investigate this problem by viewing the diffusion sampling process as a Metropolis adjusted Langevin algorithm, which helps reveal the underlying cause to be ill-conditioned curvature. Under this insight, we propose a model-agnostic preconditioned diffusion sampling (PDS) method that leverages matrix preconditioning to alleviate the aforementioned problem. Crucially, PDS is proven theoretically to converge to the original target distribution of a SGM, no need for retraining. Extensive experiments on three image datasets with a variety of resolutions and diversity validate that PDS consistently accelerates off-the-shelf SGMs whilst maintaining the synthesis quality. In particular, PDS can accelerate by up to 29x on more challenging high resolution (1024x1024) image generation.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 23 of its 39 references that are in the map. First posted on arXiv 5 Jul 2022.

Builds on

23 of 39 references.

Closest ancestors · 14

Same direction, newest first

  1. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models17 Jan
  2. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  3. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusion14 Dec
  4. 2021Score-based Generative Modeling in Latent Space10 Jun
  5. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modeling1 Jun
  6. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  7. 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
  8. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  9. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  10. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  11. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  12. 2020Denoising Diffusion Implicit Models6 Oct
2 more
  1. 2020Denoising Diffusion Probabilistic Models19 Jun
  2. 2020Improved Techniques for Training Score-Based Generative Models16 Jun

Other references · 9

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  9. 2015Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networkscited by 121

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 8; 2024: 3; 2025: 3.

19 papers.

Sort:

By area:

  1. 2022Diffusion Probabilistic Model Made Slimcited by 121
  2. 2022Wavelet Diffusion Models are fast and scalable Image Generatorscited by 116
  3. 2022Diffusion Models Beat GANs on Topology Optimizationcited by 79
  4. 2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 76
  5. 2022Conversion Between CT and MRI Images Using Diffusion and Score-Matching Modelscited by 69
  6. 2023WaveDM: Wavelet-Based Diffusion Models for Image Restorationcited by 46
  7. 2023Multi-Architecture Multi-Expert Diffusion Modelscited by 34
  8. 2023ExposureDiffusion: Learning to Expose for Low-light Image Enhancementcited by 29
  9. 2023HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Modelscited by 27
  10. 2023FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Modelscited by 19
  11. 2023Image generation with shortest path diffusioncited by 8
  12. 2023Preconditioned Score-based Generative Modelscited by 6
7 more
  1. 2023Solving Linear Inverse Problems using Higher-Order Annealed Langevin Diffusioncited by 6
  2. 2024Hitchhiker's guide on the relation of Energy-Based Models with other generative models, sampling and statistical physics: a comprehensive reviewcited by 5
  3. 2025Preconditioned Langevin Dynamics with Score-Based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problemscited by 5
  4. 2024Efficient Combinatorial Optimization via Heat Diffusioncited by 2
  5. 2024Inverse design with conditional cascaded diffusion modelscited by 2
  6. 2025TS-Diff: Two-Stage Diffusion Model for Low-Light RAW Image Enhancementcited by 2
  7. 2025PID-controlled Langevin Dynamics for Faster Sampling of Generative Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023A Complete Recipe for Diffusion Generative Models
  2. 2022Accelerating Score-based Generative Models for High-Resolution Image Synthesis
  3. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
  4. 2024Accelerating Convergence of Score-Based Diffusion Models, Provably
  5. 2024A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
  6. 2024A Practical Diffusion Path for Sampling
  7. 2024Score-based Generative Models with Adaptive Momentum
  8. 2021Conditional Image Generation with Score-Based Diffusion Models