mlsanityData to 7 Oct 2026

Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation

arXiv 2406.02347 ↗First posted 4 Jun 2024cs.CV cs.AI cs.LGcited by 56

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models: Flash Diffusion. The method reaches state-of-the-art performances in terms of FID and CLIP-Score for few steps image generation on the COCO2014 and COCO2017 datasets, while requiring only several GPU hours of training and fewer trainable parameters than existing methods. In addition to its efficiency, the versatility of the method is also exposed across several tasks such as text-to-image, inpainting, face-swapping, super-resolution and using different backbones such as UNet-based denoisers (SD1.5, SDXL) or DiT (Pixart-α), as well as adapters. In all cases, the method allowed to reduce drastically the number of sampling steps while maintaining very high-quality image generation. The official implementation is available at https://github.com/gojasper/flash-diffusion.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 72 of its 80 references that are in the map. First posted on arXiv 4 Jun 2024.

Builds on

72 of 80 references.

Closest ancestors · 31

Same direction, newest first

  1. 2024Improved Distribution Matching Distillation for Fast Image Synthesis23 May
  2. 2024Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation8 May
  3. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis21 Apr
  4. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation18 Mar
  5. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation7 Mar
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar
  7. 2024SDXL-Lightning: Progressive Adversarial Diffusion Distillation21 Feb
  8. 2023One-step Diffusion with Distribution Matching Distillation30 Nov
  9. 2023Adversarial Diffusion Distillation28 Nov
  10. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Module9 Nov
  11. 2023Improved Techniques for Training Consistency Models22 Oct
  12. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
19 more
  1. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion1 Oct
  2. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis30 Sep
  3. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  4. 2023Consistency Models2 Mar
  5. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models9 Feb
  6. 2022Scalable Diffusion Models with Transformers19 Dec
  7. 2022Fast Sampling of Diffusion Models via Operator Learning24 Nov
  8. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  9. 2022On Distillation of Guided Diffusion Models6 Oct
  10. 2022Classifier-Free Diffusion Guidance26 Jul
  11. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  12. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  13. 2022Fast Sampling of Diffusion Models with Exponential Integrator29 Apr
  14. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  15. 2021Variational Diffusion Models1 Jul
  16. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  17. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed7 Jan
  18. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  19. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 41

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  8. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  9. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  10. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  11. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  12. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
29 more
  1. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  2. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  8. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  9. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  10. 2018Group Normalizationcited by 1,514
  11. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  12. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  13. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  14. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  15. 2016Least Squares Generative Adversarial Networkscited by 1,000
  16. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  17. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 767
  18. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  19. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  20. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 589
  21. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  22. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  23. 2015Generative Moment Matching Networkscited by 252
  24. 2017Geometric GANcited by 232
  25. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
  26. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 165
  27. 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 149
  28. 2021Score-Based Point Cloud Denoisingcited by 83
  29. 2022Fast Point Cloud Generation with Straight Flowscited by 56

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 26; 2026: 25.

56 papers.

Sort:

By area:

  1. 2025Diffusion Adversarial Post-Training for One-Step Video Generationcited by 142
  2. 2025Emu3.5: Native Multimodal Models are World Learnerscited by 119
  3. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  4. 2025Distribution Matching Distillation Meets Reinforcement Learningcited by 43
  5. 2025Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesiscited by 39
  6. 2025Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shieldcited by 38
  7. 2025LBM: Latent Bridge Matching for Fast Image-to-Image Translationcited by 36
  8. 2025SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillationcited by 29
  9. 2024Flow Generator Matchingcited by 26
  10. 2024Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimizationcited by 25
  11. 2026Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesiscited by 20
  12. 2025Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learningcited by 17
38 more
  1. 2025Accelerating Diffusion Transformer via Gradient-Optimized Cachecited by 15
  2. 2024Supercharged One-step Text-to-Image Diffusion Models with Negative Promptscited by 8
  3. 2025Score Distillation of Flow Matching Modelscited by 6
  4. 2026Reinforcing Few-step Generators via Reward-Tilted Distribution Matchingcited by 6
  5. 2025FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillationcited by 5
  6. 2025ProReflow: Progressive Reflow with Decomposed Velocitycited by 5
  7. 2025Audio Driven Real-Time Facial Animation for Social Telepresencecited by 5
  8. 2026Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCachecited by 5
  9. 2025DRAGON: A Large-Scale Dataset of Realistic Images Generated by Diffusion Modelscited by 4
  10. 2025MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devicescited by 4
  11. 2026TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Modelscited by 4
  12. 2026Continuous-Time Distribution Matching for Few-Step Diffusion Distillationcited by 4
  13. 2024Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representationscited by 3
  14. 2025TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimmingcited by 3
  15. 2025The Hidden Cost of an Image: Quantifying the Energy Consumption of AI Image Generationcited by 2
  16. 2025Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generationcited by 2
  17. 2025FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectoriescited by 2
  18. 2026RenderFlow: Single-Step Neural Rendering via Flow Matchingcited by 2
  19. 2026GPD: Guided Progressive Distillation for Fast and High-Quality Video Generationcited by 2
  20. 2026Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learningcited by 2
  21. 2026DefaultShift: Auditing Semantic Default Shift in Accelerated Text-to-Image Modelscited by 2
  22. 2025Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutionscited by 1
  23. 2025F-scheduler: illuminating the free-lunch design space for fast sampling of diffusion modelscited by 1
  24. 2025Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generationcited by 1
  25. 2025Glance: Accelerating Diffusion Models with 1 Samplecited by 1
  26. 2026Fast, faithful and photorealistic diffusion-based image super-resolution with enhanced Flow Map modelscited by 1
  27. 2026Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolutioncited by 1
  28. 2026ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagationcited by 1
  29. 2026BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generationcited by 1
  30. 2026Rdm: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillationcited by 1
  31. 2026Reward-Aware Trajectory Shaping for Few-step Visual Generationcited by 1
  32. 2026Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matchingcited by 1
  33. 2024Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samplescited by 0
  34. 2025REFINE-CONTROL: A Semi-supervised Distillation Method For Conditional Image Generationcited by 0
  35. 2025D2 Actor Critic: Diffusion Actor Meets Distributional Criticcited by 0
  36. 2026WaDi: Weight Direction-aware Distillation for One-step Image Synthesiscited by 0
  37. 2026You Only Erase Once: Erasing Anything without Bringing Unexpected Contentcited by 0
  38. 2026Beyond Trajectory Matching: Reflow with Marginal Distribution Alignmentcited by 0

50 most cited of 56 All 56 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
  2. 2024A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
  3. 2025DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
  4. 2024Simple and Fast Distillation of Diffusion Models
  5. 2024Conditional Image Synthesis with Diffusion Models: A Survey
  6. 2023AdaDiff: Adaptive Step Selection for Fast Diffusion Models
  7. 2024Plug-and-Play Diffusion Distillation
  8. 2024Multistep Distillation of Diffusion Models via Moment Matching