mlsanityData to 7 Oct 2026

Elucidating the Design Space of Diffusion-Based Generative Models

arXiv 2206.00364 ↗First posted 1 Jun 2022cs.CV cs.AI cs.LGcited by 2,994

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

We argue that the theory and practice of diffusion-based generative models are currently unnecessarily convoluted and seek to remedy the situation by presenting a design space that clearly separates the concrete design choices. This lets us identify several changes to both the sampling and training processes, as well as preconditioning of the score networks. Together, our improvements yield new state-of-the-art FID of 1.79 for CIFAR-10 in a class-conditional setting and 1.97 in an unconditional setting, with much faster sampling (35 network evaluations per image) than prior designs. To further demonstrate their modular nature, we show that our design changes dramatically improve both the efficiency and quality obtainable with pre-trained score networks from previous work, including improving the FID of a previously trained ImageNet-64 model from 2.07 to near-SOTA 1.55, and after re-training with our proposed improvements to a new SOTA of 1.36.

Key facts. Cited by 2,994 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 42 of its 65 references that are in the map. First posted on arXiv 1 Jun 2022.

Builds on

42 of 65 references.

Closest ancestors · 21

Same direction, newest first

  1. 2022Subspace Diffusion Generative Models3 May
  2. 2022Fast Sampling of Diffusion Models with Exponential Integrator29 Apr
  3. 2022Perception Prioritized Training of Diffusion Models1 Apr
  4. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  5. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality11 Feb
  6. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models17 Jan
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  8. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusion14 Dec
  9. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representation30 Nov
  10. 2021Diffusion Normalizing Flow14 Oct
  11. 2021Score-based Generative Modeling in Latent Space10 Jun
  12. 2021Learning to Efficiently Sample from Diffusion Probabilistic Models7 Jun
9 more
  1. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matching5 Jun
  2. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  3. 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
  4. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  5. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  6. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed7 Jan
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  8. 2020Denoising Diffusion Implicit Models6 Oct
  9. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 21

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  8. 2022Video Diffusion Modelscited by 2,280
  9. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  10. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  11. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  12. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
9 more
  1. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  2. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  3. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  4. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  5. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  6. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  7. 2021Diffusion Models for Implicit Image Segmentation Ensemblescited by 198
  8. 2020Normalization Techniques in Training DNNs: Methodology, Analysis and Applicationcited by 90
  9. 2021Zero-Shot Translation using Diffusion Modelscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 55; 2023: 452; 2024: 760; 2025: 954; 2026: 773.

2,994 papers.

Sort:

By area:

  1. 2022Scalable Diffusion Models with Transformerscited by 5,931
  2. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  3. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  5. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  6. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  7. 2023Consistency Modelscited by 1,778
  8. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  9. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  10. 2022Diffusion Models in Vision: A Surveycited by 1,008
  11. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  12. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
38 more
  1. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  2. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  3. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  4. 2022On Distillation of Guided Diffusion Modelscited by 721
  5. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  6. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  7. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  8. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  9. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 606
  10. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  11. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 589
  12. 2025Mean Flows for One-step Generative Modelingcited by 524
  13. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 498
  14. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 467
  15. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  16. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 448
  17. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 448
  18. 2023Generative Multimodal Models are In-Context Learnerscited by 446
  19. 2023Emergent Correspondence from Image Diffusioncited by 437
  20. 2023Improved Techniques for Training Consistency Modelscited by 430
  21. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 401
  22. 2023Analyzing and Improving the Training Dynamics of Diffusion Modelscited by 396
  23. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  24. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 379
  25. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  26. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  27. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  28. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllabilitycited by 337
  29. 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 335
  30. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 331
  31. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 326
  32. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
  33. 2022Diffusion Models already have a Semantic Latent Spacecited by 324
  34. 2023Pix2Video: Video Editing using Image Diffusioncited by 318
  35. 2022Novel View Synthesis with Diffusion Modelscited by 299
  36. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 294
  37. 2023Understanding Diffusion Objectives as the ELBO with Simple Data Augmentationcited by 293
  38. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 286

50 most cited of 2,994 All 2,994 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Let us Build Bridges: Understanding and Extending Diffusion Generative Models
  2. 2023Preconditioned Score-based Generative Models
  3. 2022Understanding Diffusion Models: A Unified Perspective
  4. 2026From Score Learning to Discretized Sampling: An End-to-End Generalization Analysis of Diffusion Models
  5. 2025Boosting Generative Image Modeling via Joint Image-Feature Synthesis
  6. 2021Conditional Image Generation with Score-Based Diffusion Models
  7. 2024Generative AI in Vision: A Survey on Models, Metrics and Applications
  8. 2022Progressive Distillation for Fast Sampling of Diffusion Models