mlsanityData to 7 Oct 2026

Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation

arXiv 2403.12015 ↗First posted 18 Mar 2024cs.CVcited by 276

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models are the main driver of progress in image and video synthesis, but suffer from slow inference speed. Distillation methods, like the recently introduced adversarial diffusion distillation (ADD) aim to shift the model from many-shot to single-step inference, albeit at the cost of expensive and difficult optimization due to its reliance on a fixed pretrained DINOv2 discriminator. We introduce Latent Adversarial Diffusion Distillation (LADD), a novel distillation approach overcoming the limitations of ADD. In contrast to pixel-based ADD, LADD utilizes generative features from pretrained latent diffusion models. This approach simplifies training and enhances performance, enabling high-resolution multi-aspect ratio image synthesis. We apply LADD to Stable Diffusion 3 (8B) to obtain SD3-Turbo, a fast model that matches the performance of state-of-the-art text-to-image generators using only four unguided sampling steps. Moreover, we systematically investigate its scaling behavior and demonstrate LADD's effectiveness in various applications such as image editing and inpainting.

Key facts. Cited by 276 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 59 of its 71 references that are in the map. First posted on arXiv 18 Mar 2024.

Builds on

59 of 71 references.

Closest ancestors · 22

Same direction, newest first

  1. 2024Multistep Consistency Models11 Mar
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar
  3. 2024Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping29 Feb
  4. 2024SDXL-Lightning: Progressive Adversarial Diffusion Distillation21 Feb
  5. 2023One-step Diffusion with Distribution Matching Distillation30 Nov
  6. 2023Adversarial Diffusion Distillation28 Nov
  7. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Module9 Nov
  8. 2023Improved Techniques for Training Consistency Models22 Oct
  9. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
  10. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  11. 2023TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation7 Mar
  12. 2023Consistency Models2 Mar
10 more
  1. 2022Scalable Diffusion Models with Transformers19 Dec
  2. 2022On Distillation of Guided Diffusion Models6 Oct
  3. 2022Classifier-Free Diffusion Guidance26 Jul
  4. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  5. 2022Fast Sampling of Diffusion Models with Exponential Integrator29 Apr
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  7. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  9. 2020Denoising Diffusion Implicit Models6 Oct
  10. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2020Scaling Laws for Neural Language Modelscited by 6,411
  9. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  10. 2022Flow Matching for Generative Modelingcited by 5,426
  11. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  12. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
25 more
  1. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  2. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  3. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  4. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  5. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  6. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  7. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
  8. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  9. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 767
  10. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  11. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 615
  12. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 589
  13. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  14. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  15. 2023Emu Edit: Precise Image Editing via Recognition and Generation Taskscited by 321
  16. 2023Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystackcited by 278
  17. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  18. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 211
  19. 2021Projected GANs Converge Fastercited by 204
  20. 2023HIVE: Harnessing Human Feedback for Instructional Visual Editingcited by 172
  21. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 165
  22. 2023Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Codecited by 145
  23. 2023Intriguing properties of generative classifierscited by 52
  24. 2023Bespoke Solvers for Generative Flow Modelscited by 36
  25. 2019Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)cited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 74; 2025: 115; 2026: 87.

276 papers.

Sort:

By area:

  1. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
  2. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  3. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  4. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 569
  5. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllabilitycited by 337
  6. 2024AnyEdit: Mastering Unified High-Quality Image Editing for Any Ideacited by 235
  7. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 153
  8. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 152
  9. 2024OmniEdit: Building Image Editing Generalist Models Through Specialist Supervisioncited by 145
  10. 2025Diffusion Adversarial Post-Training for One-Step Video Generationcited by 142
  11. 2024Consistency Models Made Easycited by 140
  12. 2024Video Diffusion Alignment via Reward Gradientscited by 101
38 more
  1. 2025SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillationcited by 85
  2. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 84
  3. 2025Align Your Flow: Scaling Continuous-Time Flow Map Distillationcited by 81
  4. 2025Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistencycited by 81
  5. 2024Distilling Diffusion Models into Conditional GANscited by 78
  6. 2024EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagationcited by 76
  7. 2025A Survey on Diffusion Language Modelscited by 75
  8. 2025Training-free and Adaptive Sparse Attention for Efficient Long Video Generationcited by 65
  9. 2024Degradation-Guided One-Step Image Super-Resolution with Diffusion Priorscited by 64
  10. 2025Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Modelscited by 61
  11. 2024EM Distillation for One-step Diffusion Modelscited by 60
  12. 2024TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negativescited by 57
  13. 2024Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generationcited by 56
  14. 2024Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesiscited by 55
  15. 2024Diffusion Models and Representation Learning: A Surveycited by 53
  16. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  17. 2026Context Forcing: Consistent Autoregressive Video Generation with Long Contextcited by 47
  18. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  19. 2025GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modelingcited by 43
  20. 2025One-step Diffusion Models with f-Divergence Distribution Matchingcited by 43
  21. 2025Distribution Matching Distillation Meets Reinforcement Learningcited by 43
  22. 2024SF-V: Single Forward Video Generation Modelcited by 40
  23. 2024Efficient Diffusion Models: A Comprehensive Survey from Principles to Practicescited by 39
  24. 2025Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesiscited by 39
  25. 2025Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shieldcited by 38
  26. 2024PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Modelscited by 36
  27. 2024OSV: One Step is Enough for High-Quality Image to Video Generationcited by 36
  28. 2025LBM: Latent Bridge Matching for Fast Image-to-Image Translationcited by 36
  29. 2024Alignment of Diffusion Models: Fundamentals, Challenges, and Futurecited by 34
  30. 2025Transition Models: Rethinking the Generative Learning Objectivecited by 32
  31. 2024Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusioncited by 31
  32. 2025DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolutioncited by 30
  33. 2025FlashWorld: High-quality 3D Scene Generation within Secondscited by 30
  34. 2024HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editingcited by 29
  35. 2025SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillationcited by 29
  36. 2024SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusioncited by 28
  37. 2025Diffusion Models without Classifier-free Guidancecited by 28
  38. 2026Qwen-Image-2.0 Technical Reportcited by 28

50 most cited of 276 All 276 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Adv-KD: Adversarial Knowledge Distillation for Faster Diffusion Sampling
  2. 2024Unlocking Dataset Distillation with Diffusion Models
  3. 2022Progressive Distillation for Fast Sampling of Diffusion Models
  4. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation
  5. 2023Boosting Latent Diffusion with Flow Matching
  6. 2024Accelerating Video Diffusion Models via Distribution Matching
  7. 2023Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution
  8. 2024Simple and Fast Distillation of Diffusion Models