mlsanityData to 7 Oct 2026

On the Importance of Noise Scheduling for Diffusion Models

arXiv 2301.10972 ↗First posted 26 Jan 2023cs.CV cs.GR cs.LGcited by 193

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

We empirically study the effect of noise scheduling strategies for denoising diffusion generative models. There are three findings: (1) the noise scheduling is crucial for the performance, and the optimal one depends on the task (e.g., image sizes), (2) when increasing the image size, the optimal noise scheduling shifts towards a noisier one (due to increased redundancy in pixels), and (3) simply scaling the input data by a factor of b while keeping the noise schedule function fixed (equivalent to shifting the logSNR by log b) is a good strategy across image sizes. This simple recipe, when combined with recently proposed Recurrent Interface Network (RIN), yields state-of-the-art pixel-based diffusion models for high-resolution images on ImageNet, enabling single-stage, end-to-end generation of diverse and high-fidelity images at 1024×1024 resolution (without upsampling/cascades).

Key facts. Cited by 193 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 19 of its 21 references that are in the map. First posted on arXiv 26 Jan 2023.

Builds on

19 of 21 references.

Closest ancestors · 12

Same direction, newest first

  1. 2022f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation10 Oct
  2. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning8 Aug
  3. 2022Classifier-Free Diffusion Guidance26 Jul
  4. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  6. 2021Variational Diffusion Models1 Jul
  7. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  8. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  9. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  10. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  11. 2020Denoising Diffusion Implicit Models6 Oct
  12. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 7

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2016Improved Techniques for Training GANscited by 2,938
  4. 2019Large Batch Optimization for Deep Learning: Training BERT in 76 minutescited by 671
  5. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  6. 2022Scalable Adaptive Computation for Iterative Generationcited by 190
  7. 2022A Generalist Framework for Panoptic Segmentation of Images and Videoscited by 99

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 37; 2024: 70; 2025: 50; 2026: 36.

193 papers.

Sort:

By area:

  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  2. 2025Cosmos World Foundation Model Platform for Physical AIcited by 833
  3. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  4. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  5. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 516
  6. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 450
  7. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 326
  8. 2025Diffusion Transformers with Representation Autoencoderscited by 275
  9. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 254
  10. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generationcited by 249
  11. 2023Efficient Diffusion Training via Min-SNR Weighting Strategycited by 242
  12. 2025World Simulation with Video Foundation Models for Physical AIcited by 183
38 more
  1. 2025History-Guided Video Diffusioncited by 165
  2. 2023Diffusion Schr"odinger Bridge Matchingcited by 151
  3. 2023DDP: Diffusion Model for Dense Visual Predictioncited by 148
  4. 2024PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Modelscited by 139
  5. 2023ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Modelscited by 127
  6. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Samplingcited by 124
  7. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  8. 2024Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesiscited by 105
  9. 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attentioncited by 99
  10. 2025PixelFlow: Pixel-Space Generative Models with Flowcited by 91
  11. 2024Multi-Track Timeline Control for Text-Driven 3D Human Motion Generationcited by 88
  12. 2023Relay Diffusion: Unifying diffusion process across resolutions for image synthesiscited by 78
  13. 2024Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusioncited by 74
  14. 2024DITTO: Diffusion Inference-Time T-Optimization for Music Generationcited by 73
  15. 2023Matryoshka Diffusion Modelscited by 70
  16. 2024FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modificationcited by 64
  17. 2023Texture Generation on 3D Meshes with Point-UV Diffusioncited by 63
  18. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  19. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
  20. 2023CDDM: Channel Denoising Diffusion Models for Wireless Semantic Communicationscited by 58
  21. 2024FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesiscited by 58
  22. 2023High-Fidelity Image Compression with Score-based Generative Modelscited by 53
  23. 2024CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modellingcited by 52
  24. 2023Diffusion Models With Learned Adaptive Noisecited by 50
  25. 2024Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptationcited by 50
  26. 2025SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Imagescited by 41
  27. 2024OctFusion: Octree-based Diffusion Models for 3D Shape Generationcited by 40
  28. 2023VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encodercited by 39
  29. 2024Improved Noise Schedule for Diffusion Trainingcited by 38
  30. 2024RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Modelscited by 36
  31. 2023World Models via Policy-Guided Trajectory Diffusioncited by 34
  32. 2024Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generationcited by 33
  33. 2023Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangementcited by 29
  34. 2024Blue noise for diffusion modelscited by 29
  35. 2024M&M VTO: Multi-Garment Virtual Try-On and Editingcited by 29
  36. 2025Continuous Diffusion Model for Language Modelingcited by 29
  37. 2024Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Modelcited by 27
  38. 2024M2Diffuser: Diffusion-based Trajectory Optimization for Mobile Manipulation in 3D Scenescited by 26

50 most cited of 193 All 193 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Constant Rate Scheduling: A General Framework for Optimizing Diffusion Noise Schedule via Distributional Change
  2. 2025F-scheduler: illuminating the free-lunch design space for fast sampling of diffusion models
  3. 2024Connective Viewpoints of Signal-to-Noise Diffusion Models
  4. 2025Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment
  5. 2024Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation
  6. 2024FIND: Fine-tuning Initial Noise Distribution with Policy Optimization for Diffusion Models
  7. 2023The Missing U for Efficient Diffusion Models
  8. 2025Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance