mlsanityData to 7 Oct 2026

On the Design Fundamentals of Diffusion Models: A Survey

arXiv 2306.04542 ↗First posted 7 Jun 2023cs.LG cs.AI cs.CVcited by 59

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models are learning pattern-learning systems to model and sample from data distributions with three functional components namely the forward process, the reverse process, and the sampling process. The components of diffusion models have gained significant attention with many design factors being considered in common practice. Existing reviews have primarily focused on higher-level solutions, covering less on the design fundamentals of components. This study seeks to address this gap by providing a comprehensive and coherent review of seminal designable factors within each functional component of diffusion models. This provides a finer-grained perspective of diffusion models, benefiting future studies in the analysis of individual components, the design factors for different purposes, and the implementation of diffusion models.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 276 of its 370 references that are in the map. First posted on arXiv 7 Jun 2023.

Builds on

276 of 370 references.

Closest ancestors · 114

Same direction, newest first

  1. 2023Training Data Attribution for Diffusion Models3 Jun
  2. 2023Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations3 Jun
  3. 2023Conditional Generation from Unconditional Diffusion Models using Denoiser Representations2 Jun
  4. 2023Understanding and Mitigating Copying in Diffusion Models31 May
  5. 2023A Geometric Perspective on Diffusion Models31 May
  6. 2023Spontaneous Symmetry Breaking in Generative Diffusion Models31 May
  7. 2023Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels31 May
  8. 2023Parallel Sampling of Diffusion Models25 May
  9. 2023Trans-Dimensional Generative Modeling via Jump Diffusion Models25 May
  10. 2023Unifying GANs and Score-Based Diffusion as Generative Particle Models25 May
  11. 2023Knowledge Diffusion for Distillation25 May
  12. 2023Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps24 May
38 more
  1. 2023On the Generalization of Diffusion Model24 May
  2. 2023Optimal Linear Subspace Search: Learning to Construct Fast and High-Quality Schedulers for Diffusion Models24 May
  3. 2023GSURE-Based Diffusion Model Training with Corrupted Data22 May
  4. 2023Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?22 May
  5. 2023Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces18 May
  6. 2023Structural Pruning for Diffusion Models18 May
  7. 2023Selective Guidance: Are All the Denoising Steps of Guided Diffusion Important?16 May
  8. 2023Common Diffusion Noise Schedules and Sample Steps are Flawed15 May
  9. 2023Meta-DM: Applications of Diffusion Models on Few-Shot Learning14 May
  10. 2023Null-text Guidance in Diffusion Models is Secretly a Cartoon-style Creator11 May
  11. 2023Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs6 May
  12. 2023A Comprehensive Survey on Knowledge Distillation of Diffusion Models9 Apr
  13. 2023A Closer Look at Parameter-Efficient Tuning in Diffusion Models31 Mar
  14. 2023MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer25 Mar
  15. 2023End-to-End Diffusion Latent Optimization Improves Classifier Guidance23 Mar
  16. 2023One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale12 Mar
  17. 2023Diffusion Models are Minimax Optimal Distribution Estimators3 Mar
  18. 2023Consistency Models2 Mar
  19. 2023Diffusion Probabilistic Fields1 Mar
  20. 2023Denoising Diffusion Samplers27 Feb
  21. 2023Unsupervised Discovery of Semantic Latent Directions in Diffusion Models24 Feb
  22. 2023On Calibrating Diffusion Probabilistic Models21 Feb
  23. 2023Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels21 Feb
  24. 2023Universal Guidance for Diffusion Models14 Feb
  25. 2023Learning Data Representations with Joint Diffusion Models31 Jan
  26. 2023Don't Play Favorites: Minority Guidance for Diffusion Models29 Jan
  27. 2023On the Importance of Noise Scheduling for Diffusion Models26 Jan
  28. 2023On the Mathematics of Diffusion Models25 Jan
  29. 2022Exploring Vision Transformers as Diffusion Learners28 Dec
  30. 2022Exploring Transformer Backbones for Image Diffusion Models27 Dec
  31. 2022Scalable Diffusion Models with Transformers19 Dec
  32. 2022Wavelet Diffusion Models are fast and scalable Image Generators29 Nov
  33. 2022Fast Sampling of Diffusion Models via Operator Learning24 Nov
  34. 2022Accelerating Diffusion Sampling with Classifier-based Feature Distillation22 Nov
  35. 2022Few-shot Image Generation with Diffusion Models7 Nov
  36. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  37. 2022Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise Models21 Oct
  38. 2022Conditional Diffusion with Less Explicit Guidance via Model Predictive Control21 Oct

50 newest of 114 All 114 (JSON)

Other references · 162

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  9. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  10. 2022Flow Matching for Generative Modelingcited by 5,426
  11. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  12. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
38 more
  1. 2016Wide Residual Networkscited by 3,057
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  3. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  4. 2018Group Normalizationcited by 1,514
  5. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  6. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  7. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  8. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  9. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  10. 2022Human Motion Diffusion Modelcited by 1,062
  11. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  12. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  13. 2023Training Diffusion Models with Reinforcement Learningcited by 939
  14. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  15. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  16. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  17. 2023Extracting Training Data from Diffusion Modelscited by 723
  18. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 696
  19. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  20. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  21. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  22. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 592
  23. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
  24. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 541
  25. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  26. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  27. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  28. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Modelscited by 463
  29. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  30. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 439
  31. 2023Emergent Correspondence from Image Diffusioncited by 437
  32. 2022Blended Latent Diffusioncited by 430
  33. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  34. 2022Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesiscited by 386
  35. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  36. 2023Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Modelscited by 358
  37. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
  38. 2023Diffusion Self-Guidance for Controllable Image Generationcited by 305

50 most cited of 162 All 162 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 24; 2025: 20; 2026: 9.

59 papers.

Sort:

By area:

  1. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  2. 2024Diffusion Models and Representation Learning: A Surveycited by 53
  3. 2024Diffusion Model-Based Video Editing: A Surveycited by 44
  4. 2024Diffusion Model Predictive Controlcited by 35
  5. 2024The Rise of Diffusion Models in Time-Series Forecastingcited by 25
  6. 2024A Comprehensive Survey of Action Quality Assessment: Method and Benchmarkcited by 20
  7. 2023U3DS3: Unsupervised 3D Semantic Scene Segmentationcited by 16
  8. 2025Offline Model-Based Optimization: Comprehensive Reviewcited by 14
  9. 2024CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation Methodcited by 13
  10. 2025Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusioncited by 12
  11. 2023Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradientcited by 10
  12. 2024MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generationcited by 10
38 more
  1. 2024HINT: High-quality INPainting Transformer with Mask-Aware Encoding and Enhanced Attentioncited by 10
  2. 2025SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpaintingcited by 10
  3. 2024Applications of Generative AI (GAI) for Mobile and Wireless Networking: A Surveycited by 9
  4. 2025BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Predictioncited by 9
  5. 2025Rethinking Brain Tumor Segmentation from the Frequency Domain Perspectivecited by 9
  6. 2025TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced Efficiencycited by 8
  7. 2023Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformerscited by 7
  8. 2024GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusioncited by 6
  9. 2026ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Taskscited by 6
  10. 2025Ambiguous Medical Image Segmentation Using Diffusion Schr"odinger Bridgecited by 5
  11. 2025Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applicationscited by 5
  12. 2025Towards efficient quantum algorithms for diffusion probabilistic modelscited by 4
  13. 2023Consistent Mesh Diffusioncited by 3
  14. 2024EvolvED: Evolutionary Embeddings to Understand the Generation Process of Diffusion Modelscited by 3
  15. 2024UV-free Texture Generation with Denoising and Geodesic Heat Diffusionscited by 3
  16. 2025FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessmentcited by 3
  17. 2025Large-Scale Multi-Character Interaction Synthesiscited by 3
  18. 2023An Overview about Emerging Technologies of Autonomous Drivingcited by 2
  19. 2024One-Index Vector Quantization Based Adversarial Attack on Image Classificationcited by 2
  20. 2024Data Augmentation via Diffusion Model to Enhance AI Fairnesscited by 2
  21. 2024Adaptive Graph Learning from Spatial Information for Surgical Workflow Anticipationcited by 2
  22. 2025Bigger Isn't Always Better: Towards a General Prior for Medical Image Reconstructioncited by 2
  23. 2024The Uncanny Valley: A Comprehensive Analysis of Diffusion Modelscited by 1
  24. 2024MxT: Mamba x Transformer for Image Inpaintingcited by 1
  25. 2024Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Surveycited by 1
  26. 2024Control of Overfitting with Physicscited by 1
  27. 2025Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Reviewcited by 1
  28. 2025Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generationcited by 1
  29. 2026ART: Adaptive Relational Transformer for Pedestrian Trajectory Prediction with Temporal-Aware Relationscited by 1
  30. 2026Optimizing Visual Generative Models via Distribution-wise Rewardscited by 1
  31. 2026DiFA: Inference-Time Forward-Process Alignment for Diffusion Modelscited by 1
  32. 2023Correlation-Distance Graph Learning for Treatment Response Prediction from rs-fMRIcited by 0
  33. 2024Fault Detection in Mobile Networks Using Diffusion Modelscited by 0
  34. 2024ST-SACLF: Style Transfer Informed Self-Attention Classifier for Bias-Aware Painting Classificationcited by 0
  35. 2024Dark Miner: Defend against undesirable generation for text-to-image diffusion modelscited by 0
  36. 2024SEM-Net: Efficient Pixel Modelling for image inpainting with Spatially Enhanced SSMcited by 0
  37. 2025Distinct hydrologic response patterns and trends worldwide revealed by physics-embedded learningcited by 0
  38. 2025SoccerDiffusion: Toward Learning End-to-End Humanoid Robot Soccer from Gameplay Recordingscited by 0

50 most cited of 59 All 59 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
  2. 2024Generative Diffusion Modeling: A Practical Handbook
  3. 2025Loss Functions in Diffusion Models: A Comparative Study
  4. 2026A Mathematical Introduction to Diffusion Models
  5. 2024A Comprehensive Survey on Diffusion Models and Their Applications
  6. 2024On the Feature Learning in Diffusion Models
  7. 2025On the Design of One-step Diffusion via Shortcutting Flow Paths
  8. 2023The Emergence of Reproducibility and Generalizability in Diffusion Models