mlsanityData to 14 Oct 2026

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

arXiv 2206.00927 ↗First posted 2 Jun 2022cs.LG stat.MLcited by 1,979

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

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~ 16× speedup compared with previous state-of-the-art training-free samplers on various datasets.

Key facts. Cited by 1,979 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 28 of its 45 references that are in the map. First posted on arXiv 2 Jun 2022.

Builds on

28 of 45 references.

Closest ancestors · 18

Same direction, newest first

  1. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  2. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality11 Feb
  3. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models17 Jan
  4. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  5. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusion14 Dec
  6. 2021Bilateral Denoising Diffusion Models26 Aug
  7. 2021Variational Diffusion Models1 Jul
  8. 2021Score-based Generative Modeling in Latent Space10 Jun
  9. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
  10. 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
  11. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  12. 2021Noise Estimation for Generative Diffusion Models6 Apr
6 more
  1. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  2. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  3. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed7 Jan
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  5. 2020Denoising Diffusion Implicit Models6 Oct
  6. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 10

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2022Video Diffusion Modelscited by 2,305
  6. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  7. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  8. 2021Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Schemecited by 100
  9. 2021A Study of Face Obfuscation in ImageNetcited by 83
  10. 2021WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesiscited by 65

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 52; 2023: 364; 2024: 525; 2025: 599; 2026: 439.

1,979 papers.

Sort:

By area:

  1. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  2. 2023Consistency Modelscited by 1,822
  3. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  4. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,464
  5. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  6. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  7. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  8. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  9. 2023One-step Diffusion with Distribution Matching Distillationcited by 1,019
  10. 2022Diffusion Models in Vision: A Surveycited by 1,015
  11. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  12. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 931
38 more
  1. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
  2. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  3. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  4. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 846
  5. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  6. 2023Adversarial Diffusion Distillationcited by 759
  7. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 737
  8. 2022On Distillation of Guided Diffusion Modelscited by 725
  9. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 684
  10. 2023ModelScope Text-to-Video Technical Reportcited by 658
  11. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 648
  12. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 590
  13. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learningcited by 562
  14. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 536
  15. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  16. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  17. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  18. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Modelscited by 465
  19. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 459
  20. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Modelscited by 450
  21. 2023Improved Techniques for Training Consistency Modelscited by 439
  22. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 433
  23. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 395
  24. 2023DIRE for Diffusion-Generated Image Detectioncited by 390
  25. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Datacited by 381
  26. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 373
  27. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 368
  28. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 365
  29. 2023DeepCache: Accelerating Diffusion Models for Freecited by 359
  30. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  31. 2023I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Modelscited by 350
  32. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllabilitycited by 347
  33. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 340
  34. 2023Ablating Concepts in Text-to-Image Diffusion Modelscited by 317
  35. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 310
  36. 2023Composer: Creative and Controllable Image Synthesis with Composable Conditionscited by 304
  37. 2024Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesiscited by 304
  38. 2023Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Modelscited by 301

50 most cited of 1,979 All 1,979 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Optimizing Few-Step Sampler for Diffusion Probabilistic Model
  2. 2024Denoising Diffusion Probabilistic Models in Six Simple Steps
  3. 2026Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps
  4. 2024An overview of diffusion models for generative artificial intelligence
  5. 2022Fast Sampling of Diffusion Models with Exponential Integrator
  6. 2026A Tutorial on Diffusion Theory: From Differential Equations to Diffusion Models
  7. 2024ODE-DPS: ODE-based Diffusion Posterior Sampling for Inverse Problems in Partial Differential Equation
  8. 2025Fast Convergence for High-Order ODE Solvers in Diffusion Probabilistic Models