mlsanityData to 14 Oct 2026

Flow Generator Matching

arXiv 2410.19310 ↗First posted 25 Oct 2024cs.CV cs.AI cs.LGcited by 26

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

In the realm of Artificial Intelligence Generated Content (AIGC), flow-matching models have emerged as a powerhouse, achieving success due to their robust theoretical underpinnings and solid ability for large-scale generative modeling. These models have demonstrated state-of-the-art performance, but their brilliance comes at a cost. The process of sampling from these models is notoriously demanding on computational resources, as it necessitates the use of multi-step numerical ordinary differential equations (ODEs). Against this backdrop, this paper presents a novel solution with theoretical guarantees in the form of Flow Generator Matching (FGM), an innovative approach designed to accelerate the sampling of flow-matching models into a one-step generation, while maintaining the original performance. On the CIFAR10 unconditional generation benchmark, our one-step FGM model achieves a new record Fr'echet Inception Distance (FID) score of 3.08 among few-step flow-matching-based models, outperforming original 50-step flow-matching models. Furthermore, we use the FGM to distill the Stable Diffusion 3, a leading text-to-image flow-matching model based on the MM-DiT architecture. The resulting MM-DiT-FGM one-step text-to-image model demonstrates outstanding industry-level performance. When evaluated on the GenEval benchmark, MM-DiT-FGM has delivered remarkable generating qualities, rivaling other multi-step models in light of the efficiency of a single generation step.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 77 of its 84 references that are in the map. First posted on arXiv 25 Oct 2024.

Builds on

77 of 84 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Consistency Flow Matching: Defining Straight Flows with Velocity Consistency2 Jul
  2. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation12 Sep
  3. 2022Flow Matching for Generative Modeling6 Oct
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep
  5. 2022Equivariant Diffusion for Molecule Generation in 3D31 Mar

Other references · 72

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  6. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  7. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  8. 2018Neural Ordinary Differential Equationscited by 3,779
  9. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  11. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  12. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
38 more
  1. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  2. 2022Video Diffusion Modelscited by 2,305
  3. 2023Consistency Modelscited by 1,822
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  5. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  6. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  7. 2023One-step Diffusion with Distribution Matching Distillationcited by 1,019
  8. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  9. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  10. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 881
  11. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  12. 2023Adversarial Diffusion Distillationcited by 759
  13. 2022On Distillation of Guided Diffusion Modelscited by 725
  14. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 684
  15. 2022DiffEdit: Diffusion-based semantic image editing with mask guidancecited by 647
  16. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 594
  17. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  18. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
  19. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 459
  20. 2023DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Modelscited by 450
  21. 2023Improved Techniques for Training Consistency Modelscited by 439
  22. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speedcited by 348
  23. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 279
  24. 2019Residual Flows for Invertible Generative Modelingcited by 257
  25. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Modelscited by 236
  26. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 214
  27. 2024Stable Audio Opencited by 197
  28. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Qualitycited by 182
  29. 2022Fast Sampling of Diffusion Models via Operator Learningcited by 175
  30. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 166
  31. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesiscited by 156
  32. 2024Consistency Models Made Easycited by 144
  33. 2023SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillationcited by 110
  34. 2022Action Matching: Learning Stochastic Dynamics from Samplescited by 98
  35. 2023BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrappingcited by 98
  36. 2021Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidancecited by 84
  37. 2024Multistep Distillation of Diffusion Models via Moment Matchingcited by 82
  38. 2023Optimizing DDPM Sampling with Shortcut Fine-Tuningcited by 81

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 19; 2026: 5.

26 papers.

Sort:

By area:

  1. 2025Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusioncited by 625
  2. 2024Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generationcited by 30
  3. 2025Distributional Diffusion Models with Scoring Rulescited by 25
  4. 2025Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervalscited by 24
  5. 2024Self-Guidance: Boosting Flow and Diffusion Generation on Their Owncited by 23
  6. 2025Ultra-Fast Language Generation via Discrete Diffusion Divergence Instructcited by 16
  7. 2025Inverse Bridge Matching Distillationcited by 14
  8. 2025Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instructioncited by 13
  9. 2025Learning to Integrate Diffusion ODEs by Averaging the Derivativescited by 10
  10. 2025Score Distillation of Flow Matching Modelscited by 8
  11. 2026IDLM: Inverse-distilled Diffusion Language Modelscited by 8
  12. 2025Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddingscited by 6
14 more
  1. 2025GenDR: Lighten Generative Detail Restorationcited by 5
  2. 2025Dimathtt[M]O: Distilling Masked Diffusion Models into One-step Generatorcited by 5
  3. 2025Towards High-Order Mean Flow Generative Models: Feasibility, Expressivity, and Provably Efficient Criteriacited by 5
  4. 2025Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs)cited by 5
  5. 2025FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generationcited by 4
  6. 2026Midpoint Generative Modelscited by 4
  7. 2025One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillationcited by 3
  8. 2025InstantViR: Real-Time Video Inverse Problem Solver with Distilled Diffusion Priorcited by 3
  9. 2025Overclocking Electrostatic Generative Modelscited by 2
  10. 2026Ultra Fast PDE Solving via Physics Guided Few-step Diffusioncited by 2
  11. 2025Dive3D: Diverse Distillation-based Text-to-3D Generation via Score Implicit Matchingcited by 1
  12. 2026Straight-Path Flow Matching for Incomplete Multi-View Clusteringcited by 1
  13. 2025On the Inverse Flow Matching Problem in the One-Dimensional and Gaussian Casescited by 0
  14. 2026Distribution Matching Distillation for Continuous Diffusion Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Warm-Start Flow Matching for Guaranteed Fast Text/Image Generation
  2. 2024Explicit Flow Matching: On The Theory of Flow Matching Algorithms with Applications
  3. 2024Exploring Diffusion and Flow Matching Under Generator Matching
  4. 2024Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation
  5. 2023Flow Matching in Latent Space
  6. 2023Straighter Flow Matching via a Diffusion-Based Coupling Prior
  7. 2025Value Gradient Guidance for Flow Matching Alignment
  8. 2026Mean Flow Distillation: Robust and Stable Distillation for Flow Matching Models