mlsanityData to 7 Oct 2026

Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices

arXiv 2410.11795 ↗First posted 15 Oct 2024cs.CVcited by 39

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

As one of the most popular and sought-after generative models in the recent years, diffusion models have sparked the interests of many researchers and steadily shown excellent advantage in various generative tasks such as image synthesis, video generation, molecule design, 3D scene rendering and multimodal generation, relying on their dense theoretical principles and reliable application practices. The remarkable success of these recent efforts on diffusion models comes largely from progressive design principles and efficient architecture, training, inference, and deployment methodologies. However, there has not been a comprehensive and in-depth review to summarize these principles and practices to help the rapid understanding and application of diffusion models. In this survey, we provide a new efficiency-oriented perspective on these existing efforts, which mainly focuses on the profound principles and efficient practices in architecture designs, model training, fast inference and reliable deployment, to guide further theoretical research, algorithm migration and model application for new scenarios in a reader-friendly way. urlhttps://github.com/ponyzym/Efficient-DMs-Survey

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 187 of its 542 references that are in the map. First posted on arXiv 15 Oct 2024.

Builds on

187 of 542 references.

Closest ancestors · 27

Same direction, newest first

  1. 2024Dynamic Diffusion Transformer4 Oct
  2. 2024Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network Selection23 Sep
  3. 2024Neural Residual Diffusion Models for Deep Scalable Vision Generation19 Jun
  4. 2024CV-VAE: A Compatible Video VAE for Latent Generative Video Models30 May
  5. 2024Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers9 May
  6. 2024Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models6 Apr
  7. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation18 Mar
  8. 2024T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching21 Feb
  9. 2024FiT: Flexible Vision Transformer for Diffusion Model19 Feb
  10. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers16 Jan
  11. 2023GenTron: Diffusion Transformers for Image and Video Generation7 Dec
  12. 2023Adversarial Diffusion Distillation28 Nov
15 more
  1. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Module9 Nov
  2. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
  3. 2023TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation7 Mar
  4. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  5. 2022Diffusion Models already have a Semantic Latent Space20 Oct
  6. 2022A Survey on Generative Diffusion Model6 Sep
  7. 2022Diffusion Models: A Comprehensive Survey of Methods and Applications2 Sep
  8. 2022Understanding Diffusion Models: A Unified Perspective25 Aug
  9. 2022Accelerating Diffusion Models via Early Stop of the Diffusion Process25 May
  10. 2022Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders19 Feb
  11. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
  12. 2021Learning to Efficiently Sample from Diffusion Probabilistic Models7 Jun
  13. 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
  14. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed7 Jan
  15. 2020Denoising Diffusion Implicit Models6 Oct

Other references · 160

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  10. 2013Auto-Encoding Variational Bayescited by 3,980
  11. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  12. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
38 more
  1. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  2. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  3. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  4. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  5. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  6. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  7. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
  8. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,418
  9. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  10. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  11. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 975
  12. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  13. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 814
  14. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  15. 2023Baichuan 2: Open Large-scale Language Modelscited by 664
  16. 2020Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuningcited by 658
  17. 2023ModelScope Text-to-Video Technical Reportcited by 651
  18. 2022DiffEdit: Diffusion-based semantic image editing with mask guidancecited by 643
  19. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 633
  20. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
  21. 2024VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Modelscited by 568
  22. 2024Latte: Latent Diffusion Transformer for Video Generationcited by 536
  23. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generationcited by 530
  24. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  25. 2023Gated Linear Attention Transformers with Hardware-Efficient Trainingcited by 490
  26. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 467
  27. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Modelscited by 463
  28. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 450
  29. 2023TokenFlow: Consistent Diffusion Features for Consistent Video Editingcited by 440
  30. 2024InstantID: Zero-shot Identity-Preserving Generation in Secondscited by 431
  31. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
  32. 2023Aligning Text-to-Image Models using Human Feedbackcited by 418
  33. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  34. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 392
  35. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 385
  36. 2018Measuring the Intrinsic Dimension of Objective Landscapescited by 364
  37. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  38. 2023Human Motion Diffusion as a Generative Priorcited by 354

50 most cited of 160 All 160 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 22; 2026: 17.

39 papers.

Sort:

By area:

  1. 2025Controllable Video Generation: A Surveycited by 93
  2. 2025Efficient Diffusion Models: A Surveycited by 35
  3. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 26
  4. 2025Residual Diffusion Bridge Model for Image Restorationcited by 14
  5. 2025FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Computecited by 12
  6. 2026Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approachcited by 10
  7. 2026Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimizationcited by 9
  8. 2025Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modelingcited by 8
  9. 2026InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generationcited by 5
  10. 2025DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generationcited by 4
  11. 2025Lung-DDPM+: Efficient Thoracic CT Image Synthesis using Diffusion Probabilistic Modelcited by 4
  12. 2025Elucidating and Endowing the Diffusion Training Paradigm for General Image Restorationcited by 3
27 more
  1. 2025Consistent and Controllable Image Animation with Motion Linear Diffusion Transformerscited by 3
  2. 2025Emotion-Director: Bridging Affective Shortcut in Emotion-Oriented Image Generationcited by 3
  3. 2025Flow Diverse and Efficient: Learning Momentum Flow Matching via Stochastic Velocity Field Samplingcited by 2
  4. 2025Deep Neural Networks Inspired by Differential Equationscited by 2
  5. 2026WorldCache: Content-Aware Caching for Accelerated Video World Modelscited by 2
  6. 2025MAP-based Problem-Agnostic diffusion model for Inverse Problemscited by 1
  7. 2025UniTransfer: Video Concept Transfer via Progressive Spatial and Timestep Decompositioncited by 1
  8. 2025SPID: Distilled Protein Backbone Generationcited by 1
  9. 2026A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Modelscited by 1
  10. 2026Image-to-Video Diffusion: From Foundations to Open Frontierscited by 1
  11. 2026SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generationcited by 1
  12. 2025Vision-Driven Prompt Optimization for Large Language Models in Multimodal Generative Taskscited by 0
  13. 2025Exploring Textual Semantics Diversity for Image Transmission in Semantic Communication Systems using Visual Language Modelcited by 0
  14. 2025Optimization-Free Diffusion Model -- A Perturbation Theory Approachcited by 0
  15. 2025Multimodal Cinematic Video Synthesis Using Text-to-Image and Audio Generation Modelscited by 0
  16. 2025TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidancecited by 0
  17. 2025Clinical Metadata Guided Limited-Angle CT Image Reconstructioncited by 0
  18. 2026"I'm happy even though it's not real": GenAI Photo Editing as a Remembering Experiencecited by 0
  19. 2026Projected Representation Conditioning for High-fidelity Novel View Synthesiscited by 0
  20. 2026MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generationcited by 0
  21. 2026Tucker Diffusion Model for High-dimensional Tensor Generationcited by 0
  22. 2026SA-Kura: An Energy-Efficient Systolic Array Accelerator for Locally-Coupled Kuramoto Drift in Diffusion Samplingcited by 0
  23. 2026Efficient Text-to-Audio Generation via Pruningcited by 0
  24. 2026Renormalization Group Flow Matching for Scalable Local Generative Modelingcited by 0
  25. 2026GAN-Blot: A Controllable Structure-Style Synthesis Benchmark for Western Blot Forensicscited by 0
  26. 2026CleanVideo: Adaptive Concept Erasure for Text-to-Video Diffusion Modelscited by 0
  27. 2026A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platformcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Efficient Diffusion Models for Vision: A Survey
  2. 2024An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
  3. 2023State of the Art on Diffusion Models for Visual Computing
  4. 2024Generative Diffusion Modeling: A Practical Handbook
  5. 2024A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
  6. 2022Let us Build Bridges: Understanding and Extending Diffusion Generative Models
  7. 2026Efficient Video Diffusion Models: Advancements and Challenges
  8. 2023Improving Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architectures