mlsanityData to 7 Oct 2026

Consistency Models

arXiv 2303.01469 ↗First posted 2 Mar 2023cs.LG cs.CV stat.MLcited by 1,778

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models have significantly advanced the fields of image, audio, and video generation, but they depend on an iterative sampling process that causes slow generation. To overcome this limitation, we propose consistency models, a new family of models that generate high quality samples by directly mapping noise to data. They support fast one-step generation by design, while still allowing multistep sampling to trade compute for sample quality. They also support zero-shot data editing, such as image inpainting, colorization, and super-resolution, without requiring explicit training on these tasks. Consistency models can be trained either by distilling pre-trained diffusion models, or as standalone generative models altogether. Through extensive experiments, we demonstrate that they outperform existing distillation techniques for diffusion models in one- and few-step sampling, achieving the new state-of-the-art FID of 3.55 on CIFAR-10 and 6.20 on ImageNet 64x64 for one-step generation. When trained in isolation, consistency models become a new family of generative models that can outperform existing one-step, non-adversarial generative models on standard benchmarks such as CIFAR-10, ImageNet 64x64 and LSUN 256x256.

Key facts. Cited by 1,778 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 66 of its 88 references that are in the map. First posted on arXiv 2 Mar 2023.

Builds on

66 of 88 references.

Closest ancestors · 15

Same direction, newest first

  1. 2022Fast Sampling of Diffusion Models via Operator Learning24 Nov
  2. 2022GENIE: Higher-Order Denoising Diffusion Solvers11 Oct
  3. 2022On Distillation of Guided Diffusion Models6 Oct
  4. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  6. 2022Fast Sampling of Diffusion Models with Exponential Integrator29 Apr
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  8. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  9. 2021Score-based Generative Modeling in Latent Space10 Jun
  10. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  11. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed7 Jan
  12. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
3 more
  1. 2020Denoising Diffusion Implicit Models6 Oct
  2. 2020Denoising Diffusion Probabilistic Models19 Jun
  3. 2020Improved Techniques for Training Score-Based Generative Models16 Jun

Other references · 51

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  8. 2018Neural Ordinary Differential Equationscited by 3,733
  9. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  11. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  12. 2015Continuous control with deep reinforcement learningcited by 3,279
38 more
  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  2. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  3. 2016Improved Techniques for Training GANscited by 2,938
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  5. 2022Video Diffusion Modelscited by 2,280
  6. 2016Density estimation using Real NVPcited by 2,029
  7. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  8. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  9. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  10. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  11. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  12. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  13. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  14. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  15. 2022Denoising Diffusion Restoration Modelscited by 951
  16. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  17. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  18. 2016Pixel Recurrent Neural Networkscited by 814
  19. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  20. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  21. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  22. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  23. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  24. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  25. 2019Residual Flows for Invertible Generative Modelingcited by 256
  26. 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
  27. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  28. 2019Consistency Regularization for Generative Adversarial Networkscited by 134
  29. 2021ViTGAN: Training GANs with Vision Transformerscited by 110
  30. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 99
  31. 2022Poisson Flow Generative Modelscited by 95
  32. 2016Neural Autoregressive Distribution Estimationcited by 94
  33. 2018Self-Supervised GANs via Auxiliary Rotation Losscited by 94
  34. 2019AutoGAN: Neural Architecture Search for Generative Adversarial Networkscited by 94
  35. 2013RNADE: The real-valued neural autoregressive density-estimatorcited by 65
  36. 2019Sliced Wasserstein Generative Modelscited by 61
  37. 2020Dual Contradistinctive Generative Autoencodercited by 58
  38. 2021Densely connected normalizing flowscited by 49

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 173; 2024: 450; 2025: 541; 2026: 614.

1,778 papers.

Sort:

By area:

  1. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  2. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  3. 2023Adversarial Diffusion Distillationcited by 741
  4. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  5. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  6. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 569
  7. 2025Mean Flows for One-step Generative Modelingcited by 524
  8. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  9. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 448
  10. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  11. 2023Improved Techniques for Training Consistency Modelscited by 430
  12. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 401
38 more
  1. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  2. 2024One Step Diffusion via Shortcut Modelscited by 373
  3. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  4. 2023DeepCache: Accelerating Diffusion Models for Freecited by 346
  5. 2023SVDiff: Compact Parameter Space for Diffusion Fine-Tuningcited by 338
  6. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllabilitycited by 337
  7. 2023DreamLLM: Synergistic Multimodal Comprehension and Creationcited by 296
  8. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 276
  9. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 276
  10. 2024SDXL-Lightning: Progressive Adversarial Diffusion Distillationcited by 258
  11. 2024Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunitiescited by 247
  12. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 235
  13. 2023NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizerscited by 233
  14. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Modelscited by 232
  15. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  16. 2025Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Stepscited by 225
  17. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  18. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Modulecited by 211
  19. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 211
  20. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 209
  21. 2025Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsitycited by 204
  22. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 199
  23. 2025Real-Time Execution of Action Chunking Flow Policiescited by 199
  24. 2025Unified Video Action Modelcited by 195
  25. 2025Remasking Discrete Diffusion Models with Inference-Time Scalingcited by 181
  26. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistencycited by 180
  27. 2025Self-Forcing++: Towards Minute-Scale High-Quality Video Generationcited by 176
  28. 2025Matrix-game 2.0: An open-source real-time and streaming interactive world modelcited by 174
  29. 2024A Survey on Diffusion Models for Inverse Problemscited by 173
  30. 2023Fast Training of Diffusion Models with Masked Transformerscited by 172
  31. 2024Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformerscited by 169
  32. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  33. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 164
  34. 2023DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statisticscited by 161
  35. 2024SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelscited by 161
  36. 2024Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillationcited by 159
  37. 2024ControlNeXt: Powerful and Efficient Control for Image and Video Generationcited by 158
  38. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 153

50 most cited of 1,778 All 1,778 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Progressive Distillation for Fast Sampling of Diffusion Models
  2. 2024Towards Faster Training of Diffusion Models: An Inspiration of A Consistency Phenomenon
  3. 20243D-Consistent Image Inpainting with Diffusion Models
  4. 2022Improving Diffusion Model Efficiency Through Patching
  5. 2024Advancing Diffusion Models: Alias-Free Resampling and Enhanced Rotational Equivariance
  6. 2024Frame by Familiar Frame: Understanding Replication in Video Diffusion Models
  7. 2022Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion Models
  8. 2026Dual-End Consistency Model