mlsanityData to 7 Oct 2026

Relay Diffusion: Unifying diffusion process across resolutions for image synthesis

arXiv 2309.03350 ↗First posted 4 Sep 2023cs.CV cs.LGcited by 78

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models achieved great success in image synthesis, but still face challenges in high-resolution generation. Through the lens of discrete cosine transformation, we find the main reason is that the same noise level on a higher resolution results in a higher Signal-to-Noise Ratio in the frequency domain. In this work, we present Relay Diffusion Model (RDM), which transfers a low-resolution image or noise into an equivalent high-resolution one for diffusion model via blurring diffusion and block noise. Therefore, the diffusion process can continue seamlessly in any new resolution or model without restarting from pure noise or low-resolution conditioning. RDM achieves state-of-the-art FID on CelebA-HQ and sFID on ImageNet 256×256, surpassing previous works such as ADM, LDM and DiT by a large margin. All the codes and checkpoints are open-sourced at urlhttps://github.com/THUDM/RelayDiffusion.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 32 of its 36 references that are in the map. First posted on arXiv 4 Sep 2023.

Builds on

32 of 36 references.

Closest ancestors · 16

Same direction, newest first

  1. 2023MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer25 Mar
  2. 2023Simple diffusion: End-to-end diffusion for high resolution images26 Jan
  3. 2023On the Importance of Noise Scheduling for Diffusion Models26 Jan
  4. 2022Scalable Diffusion Models with Transformers19 Dec
  5. 2022Wavelet Diffusion Models are fast and scalable Image Generators29 Nov
  6. 2022Blurring Diffusion Models12 Sep
  7. 2022Classifier-Free Diffusion Guidance26 Jul
  8. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  9. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  10. 2021Score-based Generative Modeling in Latent Space10 Jun
  11. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  12. 2021Diffusion Models Beat GANs on Image Synthesis11 May
4 more
  1. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  3. 2020Denoising Diffusion Implicit Models6 Oct
  4. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 16

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  8. 2016Improved Techniques for Training GANscited by 2,938
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  10. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  11. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  12. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 691
4 more
  1. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  2. 2021Generating Images with Sparse Representationscited by 262
  3. 2022Generative Modelling With Inverse Heat Dissipationcited by 164
  4. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 24; 2025: 33; 2026: 19.

78 papers.

Sort:

By area:

  1. 2024Pyramidal Flow Matching for Efficient Video Generative Modelingcited by 354
  2. 2025Diffusion Transformers with Representation Autoencoderscited by 275
  3. 2024Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformerscited by 137
  4. 2023ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Modelscited by 127
  5. 2024Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesiscited by 105
  6. 2025DDT: Decoupled Diffusion Transformercited by 100
  7. 2025PixelFlow: Pixel-Space Generative Models with Flowcited by 91
  8. 2025PixNerd: Pixel Neural Field Diffusioncited by 75
  9. 2024Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusioncited by 74
  10. 2024CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusioncited by 72
  11. 2024FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesiscited by 58
  12. 2025DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generationcited by 55
38 more
  1. 2024Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptationcited by 50
  2. 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformerscited by 47
  3. 2025DiP: Taming Diffusion Models in Pixel Spacecited by 42
  4. 2024RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Modelscited by 36
  5. 2025FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generationcited by 32
  6. 2024Causal Diffusion Transformers for Generative Modelingcited by 31
  7. 2024Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budgetcited by 30
  8. 2024FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusioncited by 29
  9. 2023HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Modelscited by 27
  10. 2024MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuningcited by 25
  11. 2025Training-free Diffusion Acceleration with Bottleneck Samplingcited by 25
  12. 2024Hierarchical Patch Diffusion Models for High-Resolution Video Generationcited by 24
  13. 2024ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidancecited by 21
  14. 2024RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusioncited by 21
  15. 2024I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flowcited by 21
  16. 2025HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidancecited by 21
  17. 2024FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Samplingcited by 15
  18. 2024Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Modelscited by 14
  19. 2025Improved Training Technique for Latent Consistency Modelscited by 13
  20. 2025Audio Super-Resolution with Latent Bridge Modelscited by 13
  21. 2025DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusioncited by 13
  22. 2025Scale-wise Distillation of Diffusion Modelscited by 11
  23. 2025UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformerscited by 10
  24. 2026PixelGen: Improving Pixel Diffusion with Perceptual Supervisioncited by 10
  25. 2024BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusioncited by 9
  26. 2024Text-to-Image Synthesis: A Decade Surveycited by 9
  27. 2025GIViC: Generative Implicit Video Compressioncited by 9
  28. 2025Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformerscited by 9
  29. 2025D2iT: Dynamic Diffusion Transformer for Accurate Image Generationcited by 8
  30. 2025HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streamingcited by 8
  31. 2026Hyperspherical Autoencoder for High-Fidelity Image Reconstruction and Generationcited by 7
  32. 2024RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generationcited by 6
  33. 2025Improving Progressive Generation with Decomposable Flow Matchingcited by 6
  34. 2026PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusioncited by 6
  35. 2025ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restorationcited by 5
  36. 2025ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusioncited by 5
  37. 2026Laplacian Multi-scale Flow Matching for Generative Modelingcited by 5
  38. 2025TD-BFR: Truncated Diffusion Model for Efficient Blind Face Restorationcited by 4

50 most cited of 78 All 78 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis
  2. 2024FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion
  3. 2024DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance
  4. 2024DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
  5. 2024Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis
  6. 2023Residual Denoising Diffusion Models
  7. 2026HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Models
  8. 2024Diffusion Models, Image Super-Resolution And Everything: A Survey