mlsanityData to 7 Oct 2026

PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator

arXiv 2405.07510 ↗First posted 13 May 2024cs.LGcited by 95

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

Abstract (arXiv)

We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models. PeRFlow divides the sampling process of generative flows into several time windows and straightens the trajectories in each interval via the reflow operation, thereby approaching piecewise linear flows. PeRFlow achieves superior performance in a few-step generation. Moreover, through dedicated parameterizations, the PeRFlow models inherit knowledge from the pretrained diffusion models. Thus, the training converges fast and the obtained models show advantageous transfer ability, serving as universal plug-and-play accelerators that are compatible with various workflows based on the pre-trained diffusion models. Codes for training and inference are publicly released. https://github.com/magic-research/piecewise-rectified-flow

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 48 of its 55 references that are in the map. First posted on arXiv 13 May 2024.

Builds on

48 of 55 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Bellman Optimal Stepsize Straightening of Flow-Matching Models27 Dec
  2. 2023Straighter Flow Matching via a Diffusion-Based Coupling Prior28 Nov
  3. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation12 Sep
  4. 2023Multisample Flow Matching: Straightening Flows with Minibatch Couplings28 Apr
  5. 2022Flow Matching for Generative Modeling6 Oct
  6. 2022Rectified Flow: A Marginal Preserving Approach to Optimal Transport29 Sep
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 41

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2022Classifier-Free Diffusion Guidancecited by 5,717
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  7. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  8. 2022Video Diffusion Modelscited by 2,280
  9. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  10. 2023Consistency Modelscited by 1,778
  11. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
  12. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,418
29 more
  1. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  2. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  3. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  4. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  5. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  6. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  7. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  8. 2023Adversarial Diffusion Distillationcited by 741
  9. 2022On Distillation of Guided Diffusion Modelscited by 721
  10. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  11. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 526
  12. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  13. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Modelscited by 463
  14. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Modelscited by 240
  15. 2020How to train your neural ODE: the world of Jacobian and kinetic regularizationcited by 228
  16. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
  17. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Modulecited by 211
  18. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 211
  19. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  20. 2023JourneyDB: A Benchmark for Generative Image Understandingcited by 203
  21. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 165
  22. 2023TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillationcited by 115
  23. 2023SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillationcited by 109
  24. 2023BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrappingcited by 96
  25. 2023Minimizing Trajectory Curvature of ODE-based Generative Modelscited by 87
  26. 2023MagicEdit: High-Fidelity and Temporally Coherent Video Editingcited by 75
  27. 2024Analysis of Classifier-Free Guidance Weight Schedulerscited by 64
  28. 2024MagicVideo-V2: Multi-Stage High-Aesthetic Video Generationcited by 48
  29. 2023AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Modelscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 22; 2025: 50; 2026: 23.

95 papers.

Sort:

By area:

  1. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  2. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 354
  3. 2025Diffusion Adversarial Post-Training for One-Step Video Generationcited by 142
  4. 2025PixelFlow: Pixel-Space Generative Models with Flowcited by 91
  5. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 84
  6. 2024Multistep Distillation of Diffusion Models via Moment Matchingcited by 76
  7. 2024One-Step Diffusion Distillation through Score Implicit Matchingcited by 68
  8. 2024EM Distillation for One-step Diffusion Modelscited by 60
  9. 2024Rectified Diffusion: Straightness Is Not Your Need in Rectified Flowcited by 59
  10. 2024Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matchingcited by 50
  11. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  12. 2025Learning Few-Step Diffusion Models by Trajectory Distribution Matchingcited by 49
38 more
  1. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  2. 2025One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillationcited by 40
  3. 2024Efficient Diffusion Models: A Comprehensive Survey from Principles to Practicescited by 39
  4. 2025MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesiscited by 39
  5. 2025Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesiscited by 39
  6. 2024OSV: One Step is Enough for High-Quality Image to Video Generationcited by 36
  7. 2025Efficient Diffusion Models: A Surveycited by 35
  8. 2025Variational Rectified Flow Matchingcited by 34
  9. 2025FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generationcited by 32
  10. 2024Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferencescited by 30
  11. 2025Diff2Flow: Training Flow Matching Models via Diffusion Model Alignmentcited by 27
  12. 2025Unleashing Vecset Diffusion Model for Fast Shape Generationcited by 25
  13. 2024OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offscited by 22
  14. 2026Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesiscited by 20
  15. 2024LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videoscited by 18
  16. 2024NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Trainingcited by 16
  17. 2025Ultra-Fast Language Generation via Discrete Diffusion Divergence Instructcited by 15
  18. 2025AccVideo: Accelerating Video Diffusion Model with Synthetic Datasetcited by 13
  19. 2025ReDi: Rectified Discrete Flowcited by 13
  20. 2024Adversarial Schr"odinger Bridge Matchingcited by 12
  21. 2025RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectoriescited by 12
  22. 2024RectifID: Personalizing Rectified Flow with Anchored Classifier Guidancecited by 11
  23. 2024On the Convergence and Straightness of Rectified Flowcited by 11
  24. 2025M4V: Multimodal Mamba for Efficient Text-to-Video Generationcited by 11
  25. 2024Accelerating Video Diffusion Models via Distribution Matchingcited by 10
  26. 2025Adams Bashforth Moulton Solver for Inversion and Editing in Rectified Flowcited by 10
  27. 2025Few-Step Diffusion via Score identity Distillationcited by 10
  28. 2025CurveFlow: Curvature-Guided Flow Matching for Image Generationcited by 10
  29. 2025Adversarial Flow Modelscited by 10
  30. 2024Diffusion & Adversarial Schr"odinger Bridges via Iterative Proportional Markovian Fittingcited by 9
  31. 2024Multi-student Diffusion Distillation for Better One-step Generatorscited by 9
  32. 2025Adding Additional Control to One-Step Diffusion with Joint Distribution Matchingcited by 8
  33. 2025HERO: Hierarchical Extrapolation and Refresh for Efficient World Modelscited by 8
  34. 2025InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flowcited by 7
  35. 2026Fast Image Super-Resolution via Consistency Rectified Flowcited by 7
  36. 2025RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformercited by 6
  37. 2025Stochastic Interpolants via Conditional Dependent Couplingcited by 6
  38. 2026RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPOcited by 6

50 most cited of 95 All 95 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow
  2. 2024Simple ReFlow: Improved Techniques for Fast Flow Models
  3. 2024Improving the Training of Rectified Flows
  4. 2025A-FloPS: Accelerating Diffusion Models via Adaptive Flow Path Sampler
  5. 2024Text-to-Image Rectified Flow as Plug-and-Play Priors
  6. 2025Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
  7. 2025An Introduction to Flow Matching and Diffusion Models
  8. 2025From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity