mlsanityData to 14 Oct 2026

On Fast Sampling of Diffusion Probabilistic Models

arXiv 2106.00132 ↗First posted 31 May 2021cs.LGcited by 170

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

In this work, we propose FastDPM, a unified framework for fast sampling in diffusion probabilistic models. FastDPM generalizes previous methods and gives rise to new algorithms with improved sample quality. We systematically investigate the fast sampling methods under this framework across different domains, on different datasets, and with different amount of conditional information provided for generation. We find the performance of a particular method depends on data domains (e.g., image or audio), the trade-off between sampling speed and sample quality, and the amount of conditional information. We further provide insights and recipes on the choice of methods for practitioners.

Key facts. Cited by 170 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 29 of its 39 references that are in the map. First posted on arXiv 31 May 2021.

Builds on

29 of 39 references.

Closest ancestors · 6

Same direction, newest first

  1. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  2. 2021Noise Estimation for Generative Diffusion Models6 Apr
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  4. 2020Denoising Diffusion Implicit Models6 Oct
  5. 2020Denoising Diffusion Probabilistic Models19 Jun
  6. 2020Improved Techniques for Training Score-Based Generative Models16 Jun

Other references · 23

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  6. 2016Improved Techniques for Training GANscited by 2,970
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  9. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  10. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  11. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  12. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
11 more
  1. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  2. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  3. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 447
  4. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  5. 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speechcited by 157
  6. 2021Symbolic Music Generation with Diffusion Modelscited by 154
  7. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 123
  8. 2019WaveFlow: A Compact Flow-based Model for Raw Audiocited by 51
  9. 2021NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsamplingcited by 50
  10. 2017Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Netcited by 30
  11. 2021Improved Autoregressive Modeling with Distribution Smoothingcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 42; 2023: 55; 2024: 34; 2025: 22; 2026: 4.

170 papers.

Sort:

By area:

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  3. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  4. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  5. 2022Diffusion Models in Vision: A Surveycited by 1,015
  6. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  7. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  8. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 590
  9. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  10. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 532
  11. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  12. 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generationcited by 331
38 more
  1. 2021Crystal Diffusion Variational Autoencoder for Periodic Material Generationcited by 270
  2. 2022EDICT: Exact Diffusion Inversion via Coupled Transformationscited by 258
  3. 2021Deblurring via Stochastic Refinementcited by 249
  4. 2023Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Modelscited by 245
  5. 2022A Survey on Generative Diffusion Modelcited by 240
  6. 2021Likelihood Training of Schr"odinger Bridge using Forward-Backward SDEs Theorycited by 219
  7. 2021Autoregressive Diffusion Modelscited by 210
  8. 2022Diffusion-GAN: Training GANs with Diffusioncited by 205
  9. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  10. 2022Versatile Diffusion: Text, Images and Variations All in One Diffusion Modelcited by 199
  11. 2021A Survey on Neural Speech Synthesiscited by 184
  12. 2023Conditional Image-to-Video Generation with Latent Flow Diffusion Modelscited by 181
  13. 2022Fast Sampling of Diffusion Models via Operator Learningcited by 175
  14. 2023PTQD: Accurate Post-Training Quantization for Diffusion Modelscited by 170
  15. 2024Consistency Models Made Easycited by 144
  16. 2022Semantic Image Synthesis via Diffusion Modelscited by 132
  17. 2021Learning to Efficiently Sample from Diffusion Probabilistic Modelscited by 129
  18. 2022GENIE: Higher-Order Denoising Diffusion Solverscited by 127
  19. 2022gDDIM: Generalized denoising diffusion implicit modelscited by 125
  20. 2022Wavelet Diffusion Models are fast and scalable Image Generatorscited by 117
  21. 2024Transparent Image Layer Diffusion using Latent Transparencycited by 114
  22. 2022Denoising diffusion models for out-of-distribution detectioncited by 104
  23. 2023In-Context Learning Unlocked for Diffusion Modelscited by 104
  24. 2022Let us Build Bridges: Understanding and Extending Diffusion Generative Modelscited by 103
  25. 2023Compositional 3D Scene Generation using Locally Conditioned Diffusioncited by 101
  26. 2021Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Schemecited by 100
  27. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completioncited by 100
  28. 2022Accelerating Diffusion Models via Early Stop of the Diffusion Processcited by 100
  29. 2024DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Modelscited by 98
  30. 2022Lossy Compression with Gaussian Diffusioncited by 90
  31. 2023Input Perturbation Reduces Exposure Bias in Diffusion Modelscited by 90
  32. 2023Optimizing DDPM Sampling with Shortcut Fine-Tuningcited by 81
  33. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Priorcited by 80
  34. 2022Diffusion Models for Counterfactual Explanationscited by 79
  35. 2022Generating High Fidelity Data from Low-density Regions using Diffusion Modelscited by 78
  36. 2022Subspace Diffusion Generative Modelscited by 70
  37. 2022Progressive Distillation for Fast Sampling of Diffusion Modelscited by 69
  38. 2023TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Modelscited by 69

50 most cited of 170 All 170 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025SynBoost: A Synergistic Framework for Fast Sampling of Diffusion Models
  2. 2022Speed up the inference of diffusion models via shortcut MCMC sampling
  3. 2023Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
  4. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality
  5. 2023Fast Diffusion Probabilistic Model Sampling through the lens of Backward Error Analysis
  6. 2024T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
  7. 2024O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal Assumptions
  8. 2025Information-Theoretic Proofs for Diffusion Sampling