mlsanityData to 7 Oct 2026

Simple diffusion: End-to-end diffusion for high resolution images

arXiv 2301.11093 ↗First posted 26 Jan 2023cs.CV cs.LG stat.MLcited by 413

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Currently, applying diffusion models in pixel space of high resolution images is difficult. Instead, existing approaches focus on diffusion in lower dimensional spaces (latent diffusion), or have multiple super-resolution levels of generation referred to as cascades. The downside is that these approaches add additional complexity to the diffusion framework. This paper aims to improve denoising diffusion for high resolution images while keeping the model as simple as possible. The paper is centered around the research question: How can one train a standard denoising diffusion models on high resolution images, and still obtain performance comparable to these alternate approaches? The four main findings are: 1) the noise schedule should be adjusted for high resolution images, 2) It is sufficient to scale only a particular part of the architecture, 3) dropout should be added at specific locations in the architecture, and 4) downsampling is an effective strategy to avoid high resolution feature maps. Combining these simple yet effective techniques, we achieve state-of-the-art on image generation among diffusion models without sampling modifiers on ImageNet.

Key facts. Cited by 413 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 28 of its 32 references that are in the map. First posted on arXiv 26 Jan 2023.

Builds on

28 of 32 references.

Closest ancestors · 11

Same direction, newest first

  1. 2022Scalable Diffusion Models with Transformers19 Dec
  2. 2022f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation10 Oct
  3. 2022On Distillation of Guided Diffusion Models6 Oct
  4. 2022Classifier-Free Diffusion Guidance26 Jul
  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 Probabilistic Models19 Jun

Other references · 17

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  8. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  9. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  10. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  11. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  12. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
5 more
  1. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 640
  2. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  3. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  4. 2022Scalable Adaptive Computation for Iterative Generationcited by 190
  5. 2022ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Expertscited by 110

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 57; 2024: 123; 2025: 124; 2026: 109.

413 papers.

Sort:

By area:

  1. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  2. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  3. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
  4. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  5. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  6. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  7. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 633
  8. 2023GAIA-1: A Generative World Model for Autonomous Drivingcited by 618
  9. 2025Mean Flows for One-step Generative Modelingcited by 524
  10. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 450
  11. 2023Improved Techniques for Training Consistency Modelscited by 430
  12. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
38 more
  1. 2023Analyzing and Improving the Training Dynamics of Diffusion Modelscited by 396
  2. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  3. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 326
  4. 2023Photorealistic Video Generation with Diffusion Modelscited by 304
  5. 2023Text-to-3D using Gaussian Splattingcited by 299
  6. 2024An Image is Worth 32 Tokens for Reconstruction and Generationcited by 295
  7. 2023Understanding Diffusion Objectives as the ELBO with Simple Data Augmentationcited by 293
  8. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 286
  9. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 276
  10. 2025Diffusion Transformers with Representation Autoencoderscited by 275
  11. 2025World Simulation with Video Foundation Models for Physical AIcited by 183
  12. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Modelscited by 179
  13. 2023Denoising Diffusion Bridge Modelscited by 171
  14. 2023Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Modelscited by 169
  15. 2025History-Guided Video Diffusioncited by 165
  16. 2023Diffusion Schr"odinger Bridge Matchingcited by 151
  17. 2024PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Modelscited by 139
  18. 2024Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformerscited by 137
  19. 2024Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiTcited by 130
  20. 2023ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Modelscited by 127
  21. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Samplingcited by 124
  22. 2024Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformerscited by 116
  23. 2024MV-Adapter: Multi-view Consistent Image Generation Made Easycited by 111
  24. 2024Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Modelscited by 107
  25. 2025Inductive Moment Matchingcited by 107
  26. 2023DemoFusion: Democratising High-Resolution Image Generation With No cited by 105
  27. 2024Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesiscited by 105
  28. 2023DiffiT: Diffusion Vision Transformers for Image Generationcited by 104
  29. 2023Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscalingcited by 103
  30. 2024Rolling Diffusion Modelscited by 102
  31. 2025Improved Mean Flows: On the Challenges of Fastforward Generative Modelscited by 102
  32. 2024DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Modelscited by 98
  33. 2026Generative Modeling via Driftingcited by 98
  34. 2024MaskBit: Embedding-free Image Generation via Bit Tokenscited by 96
  35. 2025Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Thinkcited by 95
  36. 2024MotionBooth: Motion-Aware Customized Text-to-Video Generationcited by 92
  37. 2024LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generationcited by 91
  38. 2024Align Your Steps: Optimizing Sampling Schedules in Diffusion Modelscited by 91

50 most cited of 413 All 413 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025LowDiff: Efficient Diffusion Sampling with Low-Resolution Condition
  2. 2023Real-World Denoising via Diffusion Model
  3. 2026Efficient and Training-Free Single-Image Diffusion Models
  4. 2024Diffusion Posterior Proximal Sampling for Image Restoration
  5. 2023Residual Denoising Diffusion Models
  6. 2023PartDiff: Image Super-resolution with Partial Diffusion Models
  7. 2026Scale Space Diffusion
  8. 2023SVNR: Spatially-variant Noise Removal with Denoising Diffusion