mlsanityData to 7 Oct 2026

Ultra-High-Resolution Image Synthesis with Pyramid Diffusion Model

arXiv 2403.12915 ↗First posted 19 Mar 2024cs.CVcited by 1

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

We introduce the Pyramid Diffusion Model (PDM), a novel architecture designed for ultra-high-resolution image synthesis. PDM utilizes a pyramid latent representation, providing a broader design space that enables more flexible, structured, and efficient perceptual compression which enable AutoEncoder and Network of Diffusion to equip branches and deeper layers. To enhance PDM's capabilities for generative tasks, we propose the integration of Spatial-Channel Attention and Res-Skip Connection, along with the utilization of Spectral Norm and Decreasing Dropout Strategy for the Diffusion Network and AutoEncoder. In summary, PDM achieves the synthesis of images with a 2K resolution for the first time, demonstrated on two new datasets comprising images of sizes 2048x2048 pixels and 2048x1024 pixels respectively. We believe that this work offers an alternative approach to designing scalable image generative models, while also providing incremental reinforcement for existing frameworks.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 52 of its 66 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

52 of 66 references.

Closest ancestors · 12

Same direction, newest first

  1. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  2. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models25 Apr
  3. 2023Simple diffusion: End-to-end diffusion for high resolution images26 Jan
  4. 2022All are Worth Words: A ViT Backbone for Diffusion Models25 Sep
  5. 2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations14 Jul
  6. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  8. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  9. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  10. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  11. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  12. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 40

  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. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2017Neural Discrete Representation Learningcited by 4,650
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  9. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  10. 2016Wide Residual Networkscited by 3,057
  11. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  12. 2016Improved Techniques for Training GANscited by 2,938
28 more
  1. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  2. 2017Improved Training of Wasserstein GANscited by 2,223
  3. 2016Density estimation using Real NVPcited by 2,029
  4. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  5. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  6. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  7. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  8. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  9. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  10. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  11. 2016Pixel Recurrent Neural Networkscited by 814
  12. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  13. 2021Generating Images with Sparse Representationscited by 262
  14. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 218
  15. 2016Unrolled Generative Adversarial Networkscited by 208
  16. 2021Projected GANs Converge Fastercited by 204
  17. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  18. 2023A Survey on Video Diffusion Modelscited by 203
  19. 2015The Power of Depth for Feedforward Neural Networkscited by 181
  20. 2021EditGAN: High-Precision Semantic Image Editingcited by 156
  21. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
  22. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 84
  23. 2019Sliced Wasserstein Generative Modelscited by 61
  24. 2023Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Modelscited by 50
  25. 2022Efficient Image Generation with Variadic Attention Headscited by 17
  26. 2023Image-to-Image Translation with Disentangled Latent Vectors for Face Editingcited by 13
  27. 2018f-VAEs: Improve VAEs with Conditional Flowscited by 10
  28. 2022Supervised Attribute Information Removal and Reconstruction for Image Manipulationcited by 3

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024From Noise to Nuance: Advances in Deep Generative Image Modelscited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2024DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance
  2. 2024UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks
  3. 2022Pyramidal Denoising Diffusion Probabilistic Models
  4. 2025Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models
  5. 2023Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
  6. 2024DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis
  7. 2023ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models
  8. 2025Ultra-High-Resolution Image Synthesis: Data, Method and Evaluation