mlsanityData to 7 Oct 2026

Accelerating Diffusion Sampling with Optimized Time Steps

arXiv 2402.17376 ↗First posted 27 Feb 2024cs.CV cs.AI cs.LGcited by 67

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis, but their sampling efficiency is still to be desired due to the typically large number of sampling steps. Recent advancements in high-order numerical ODE solvers for DPMs have enabled the generation of high-quality images with much fewer sampling steps. While this is a significant development, most sampling methods still employ uniform time steps, which is not optimal when using a small number of steps. To address this issue, we propose a general framework for designing an optimization problem that seeks more appropriate time steps for a specific numerical ODE solver for DPMs. This optimization problem aims to minimize the distance between the ground-truth solution to the ODE and an approximate solution corresponding to the numerical solver. It can be efficiently solved using the constrained trust region method, taking less than 15 seconds. Our extensive experiments on both unconditional and conditional sampling using pixel- and latent-space DPMs demonstrate that, when combined with the state-of-the-art sampling method UniPC, our optimized time steps significantly improve image generation performance in terms of FID scores for datasets such as CIFAR-10 and ImageNet, compared to using uniform time steps.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 46 of its 53 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

46 of 53 references.

Closest ancestors · 36

Same direction, newest first

  1. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis30 Sep
  2. 2023AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration19 Sep
  3. 2023SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models10 Sep
  4. 2023SciRE-Solver: Accelerating Diffusion Models Sampling by Score-integrand Solver with Recursive Difference15 Aug
  5. 2023OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models15 Jun
  6. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models29 May
  7. 2023Improved Convergence of Score-Based Diffusion Models via Prediction-Correction23 May
  8. 2023The probability flow ODE is provably fast19 May
  9. 2023Fast Diffusion Probabilistic Model Sampling through the lens of Backward Error Analysis22 Apr
  10. 2023Consistency Models2 Mar
  11. 2023Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data14 Feb
  12. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models9 Feb
24 more
  1. 2022Scalable Diffusion Models with Transformers19 Dec
  2. 2022Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions3 Nov
  3. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  4. 2022On Distillation of Guided Diffusion Models6 Oct
  5. 2022Convergence of score-based generative modeling for general data distributions26 Sep
  6. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions22 Sep
  7. 2022Convergence of denoising diffusion models under the manifold hypothesis10 Aug
  8. 2022Convergence for score-based generative modeling with polynomial complexity13 Jun
  9. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  10. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  11. 2022Fast Sampling of Diffusion Models with Exponential Integrator29 Apr
  12. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality11 Feb
  13. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models17 Jan
  14. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  15. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  16. 2021Variational Diffusion Models1 Jul
  17. 2021Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation10 Jun
  18. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  19. 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
  20. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  21. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed7 Jan
  22. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  23. 2020Denoising Diffusion Implicit Models6 Oct
  24. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 10

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  5. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  6. 2022Video Diffusion Modelscited by 2,280
  7. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  8. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  9. 2022BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesiscited by 64
  10. 2022Transcormer: Transformer for Sentence Scoring with Sliding Language Modelingcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 33; 2026: 28.

67 papers.

Sort:

By area:

  1. 2025Training-free and Adaptive Sparse Attention for Efficient Long Video Generationcited by 65
  2. 2024Learning to Discretize Denoising Diffusion ODEscited by 39
  3. 2025Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generationcited by 19
  4. 2024Score-Optimal Diffusion Schedulescited by 16
  5. 2025Lipschitz-Guided Design of Interpolation Schedules in Generative Modelscited by 15
  6. 2024Generating Compositional Scenes via Text-to-image RGBA Instance Generationcited by 13
  7. 2025Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Modelscited by 13
  8. 2025Spectral Analysis of Diffusion Models with Application to Schedule Designcited by 12
  9. 2025S4S: Solving for a Diffusion Model Solvercited by 10
  10. 2025EVODiff: Entropy-aware Variance Optimized Diffusion Inferencecited by 10
  11. 2025Learning to Integrate Diffusion ODEs by Averaging the Derivativescited by 9
  12. 2025Straight-Line Diffusion Model for Efficient 3D Molecular Generationcited by 8
38 more
  1. 2025Adding Additional Control to One-Step Diffusion with Joint Distribution Matchingcited by 8
  2. 2025Learnable Sampler Distillation for Discrete Diffusion Modelscited by 8
  3. 2026TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Rewardcited by 7
  4. 2025Adaptive Stochastic Coefficients for Accelerating Diffusion Samplingcited by 6
  5. 2024SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Modelscited by 5
  6. 2024Learning Efficient and Effective Trajectories for Differential Equation-based Image Restorationcited by 5
  7. 2025Optimal Stepsize for Diffusion Samplingcited by 5
  8. 2025Differentiable Solver Search for Fast Diffusion Samplingcited by 5
  9. 2025Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevincited by 5
  10. 2025Revisiting Diffusion Models: From Generative Pre-training to One-Step Generationcited by 5
  11. 2025B'ezierFlow: Learning B'ezier Stochastic Interpolant Schedulers for Few-Step Generationcited by 5
  12. 2025Towards efficient quantum algorithms for diffusion probabilistic modelscited by 4
  13. 2026Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformerscited by 4
  14. 2026DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Samplingcited by 4
  15. 2025Improved Diffusion-based Generative Model with Better Adversarial Robustnesscited by 3
  16. 2025Noise Consistency Training: A Native Approach for One-Step Generator in Learning Additional Controlscited by 3
  17. 2025Parallel Diffusion Solver via Residual Dirichlet Policy Optimizationcited by 3
  18. 2026Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timestepscited by 3
  19. 2026Few-Step Diffusion Sampling Through Instance-Aware Discretizationscited by 3
  20. 2024Artificial Intelligence for Biomedical Video Generationcited by 2
  21. 2025Hierarchical Schedule Optimization for Fast and Robust Diffusion Model Samplingcited by 2
  22. 2026Mitigating the Contractivity Trap in Diffusion ODEs via Stein Stabilizationcited by 2
  23. 2025Accelerating Diffusion Sampling via Exploiting Local Transition Coherencecited by 1
  24. 2025Graffe: Graph Representation Learning via Diffusion Probabilistic Modelscited by 1
  25. 2025Accelerating Diffusion-based Super-Resolution with Dynamic Time-Spatial Samplingcited by 1
  26. 2025Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communicationscited by 1
  27. 2025Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generationcited by 1
  28. 2026Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Modelscited by 1
  29. 2026StaTS: Spectral Trajectory Schedule Learning for Adaptive Time Series Forecasting with Frequency Guided Denoisercited by 1
  30. 2026Bias mitigation in graph diffusion modelscited by 1
  31. 2025Quick Bypass Mechanism of Zero-Shot Diffusion-Based Image Restorationcited by 0
  32. 2025Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wildcited by 0
  33. 2025Pretrained Diffusion Models Are Inherently Skipped-Step Samplerscited by 0
  34. 2025GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solvercited by 0
  35. 2025Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstructioncited by 0
  36. 2025AsyncDiff: Asynchronous Timestep Conditioning for Enhanced Text-to-Image Diffusion Inferencecited by 0
  37. 2026A Gaussian Perspective for Distributional Discrepancy in Generative Diffusion Modelscited by 0
  38. 2026Minimal-Action Discrete Schr"odinger Bridge Matching for Peptide Sequence Designcited by 0

50 most cited of 67 All 67 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Optimizing Few-Step Sampler for Diffusion Probabilistic Model
  2. 2023DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics
  3. 2025Are First-Order Diffusion Samplers Really Slower? A Fast Forward-Value Approach
  4. 2024Align Your Steps: Optimizing Sampling Schedules in Diffusion Models
  5. 2024PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future Scores
  6. 2025TADA: Improved Diffusion Sampling with Training-free Augmented Dynamics
  7. 2023Fast ODE-based Sampling for Diffusion Models in Around 5 Steps
  8. 2026Optimize Your Sampling: Tuned Diffusion Sampling with Bayesian Optimization