mlsanityData to 13 Oct 2026

Adversarial Diffusion Distillation

arXiv 2311.17042 ↗First posted 28 Nov 2023cs.CVcited by 751

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to leverage large-scale off-the-shelf image diffusion models as a teacher signal in combination with an adversarial loss to ensure high image fidelity even in the low-step regime of one or two sampling steps. Our analyses show that our model clearly outperforms existing few-step methods (GANs, Latent Consistency Models) in a single step and reaches the performance of state-of-the-art diffusion models (SDXL) in only four steps. ADD is the first method to unlock single-step, real-time image synthesis with foundation models. Code and weights available under https://github.com/Stability-AI/generative-models and https://huggingface.co/stabilityai/ .

Key facts. Cited by 751 papers in the map (data through 13 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 63 of its 71 references that are in the map. First posted on arXiv 28 Nov 2023.

Builds on

63 of 71 references.

Closest ancestors · 19

Same direction, newest first

  1. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Module9 Nov
  2. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
  3. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion1 Oct
  4. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  5. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models29 May
  6. 2023Unifying GANs and Score-Based Diffusion as Generative Particle Models25 May
  7. 2023Common Diffusion Noise Schedules and Sample Steps are Flawed15 May
  8. 2023Consistency Models2 Mar
  9. 2022Scalable Diffusion Models with Transformers19 Dec
  10. 2022GENIE: Higher-Order Denoising Diffusion Solvers11 Oct
  11. 2022On Distillation of Guided Diffusion Models6 Oct
  12. 2022Classifier-Free Diffusion Guidance26 Jul
7 more
  1. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  2. 2022Fast Sampling of Diffusion Models with Exponential Integrator29 Apr
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  4. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  6. 2020Denoising Diffusion Implicit Models6 Oct
  7. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 44

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,588
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,231
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,857
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,023
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,915
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,564
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,000
  9. 2022Generative Adversarial Networkscited by 5,614
  10. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,141
  11. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,691
  12. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,607
32 more
  1. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,585
  2. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,237
  3. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,019
  4. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,407
  5. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,768
  6. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,467
  7. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,289
  8. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,212
  9. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,041
  10. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 961
  11. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 926
  12. 2018Which Training Methods for GANs do actually Converge?cited by 676
  13. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 641
  14. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  15. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  16. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  17. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 490
  18. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 391
  19. 2023Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystackcited by 279
  20. 2018cGANs with Projection Discriminatorcited by 253
  21. 2017Geometric GANcited by 232
  22. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
  23. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  24. 2021Projected GANs Converge Fastercited by 207
  25. 2023Text-To-4D Dynamic Scene Generationcited by 205
  26. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 200
  27. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 165
  28. 2023Noise-Free Score Distillationcited by 99
  29. 2020Adversarial score matching and improved sampling for image generationcited by 95
  30. 2023DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generationcited by 81
  31. 2023ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collectionscited by 22
  32. 2022When, Why, and Which Pretrained GANs Are Useful?cited by 14

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 12; 2024: 229; 2025: 268; 2026: 242.

751 papers.

Sort:

By area:

  1. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,130
  2. 2023One-step Diffusion with Distribution Matching Distillationcited by 991
  3. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 985
  4. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 679
  5. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 664
  6. 2025Mean Flows for One-step Generative Modelingcited by 541
  7. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 473
  8. 2024From Slow Bidirectional to Fast Autoregressive Video Diffusion Modelscited by 414
  9. 2024One Step Diffusion via Shortcut Modelscited by 382
  10. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generationcited by 327
  11. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 296
  12. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 278
38 more
  1. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 277
  2. 2024Timestep Embedding Tells: It's Time to Cache for Video Diffusion Modelcited by 258
  3. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  4. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 212
  5. 2024Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformerscited by 170
  6. 2024SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelscited by 165
  7. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 160
  8. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 158
  9. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 154
  10. 2025Diffusion Adversarial Post-Training for One-Step Video Generationcited by 147
  11. 2024CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Modelscited by 145
  12. 2024Real-Time Video Generation with Pyramid Attention Broadcastcited by 144
  13. 2024PuLID: Pure and Lightning ID Customization via Contrastive Alignmentcited by 143
  14. 2024Consistency Models Made Easycited by 143
  15. 2024SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistencycited by 143
  16. 2025Fast Video Generation with Sliding Tile Attentioncited by 126
  17. 2024ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationcited by 118
  18. 2024FasterCache: Training-Free Video Diffusion Model Acceleration with High Qualitycited by 118
  19. 2025RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twinscited by 118
  20. 2024One-Step Image Translation with Text-to-Image Modelscited by 113
  21. 2025Inductive Moment Matchingcited by 110
  22. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 108
  23. 2024Adaptive Caching for Faster Video Generation with Diffusion Transformerscited by 104
  24. 2024PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Acceleratorcited by 97
  25. 2024Align Your Steps: Optimizing Sampling Schedules in Diffusion Modelscited by 93
  26. 2023VideoLCM: Video Latent Consistency Modelcited by 91
  27. 2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 86
  28. 2025SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillationcited by 86
  29. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 86
  30. 2024Phased Consistency Modelscited by 85
  31. 2024What If We Recaption Billions of Web Images with LLaMA-3?cited by 85
  32. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 85
  33. 2025Align Your Flow: Scaling Continuous-Time Flow Map Distillationcited by 84
  34. 2025Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistencycited by 83
  35. 2024GenAI Arena: An Open Evaluation Platform for Generative Modelscited by 82
  36. 2024Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusioncited by 80
  37. 2025What matters for Representation Alignment: Global Information or Spatial Structure?cited by 79
  38. 2024Distilling Diffusion Models into Conditional GANscited by 78

50 most cited of 751 All 751 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Progressive Distillation for Fast Sampling of Diffusion Models
  2. 2024Adv-KD: Adversarial Knowledge Distillation for Faster Diffusion Sampling
  3. 2025Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
  4. 2025A Survey on Pre-Trained Diffusion Model Distillations
  5. 2024Unlocking Dataset Distillation with Diffusion Models
  6. 2021Diffusion Models Beat GANs on Image Synthesis
  7. 2023MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model
  8. 2023DiffFlow: A Unified SDE Framework for Score-Based Diffusion Models and Generative Adversarial Networks