mlsanityData to 7 Oct 2026

Wavelet Diffusion Models are fast and scalable Image Generators

arXiv 2211.16152 ↗First posted 29 Nov 2022cs.CV eess.IVcited by 116

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models are rising as a powerful solution for high-fidelity image generation, which exceeds GANs in quality in many circumstances. However, their slow training and inference speed is a huge bottleneck, blocking them from being used in real-time applications. A recent DiffusionGAN method significantly decreases the models' running time by reducing the number of sampling steps from thousands to several, but their speeds still largely lag behind the GAN counterparts. This paper aims to reduce the speed gap by proposing a novel wavelet-based diffusion scheme. We extract low-and-high frequency components from both image and feature levels via wavelet decomposition and adaptively handle these components for faster processing while maintaining good generation quality. Furthermore, we propose to use a reconstruction term, which effectively boosts the model training convergence. Experimental results on CelebA-HQ, CIFAR-10, LSUN-Church, and STL-10 datasets prove our solution is a stepping-stone to offering real-time and high-fidelity diffusion models. Our code and pre-trained checkpoints are available at urlhttps://github.com/VinAIResearch/WaveDiff.git.

Key facts. Cited by 116 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 49 of its 58 references that are in the map. First posted on arXiv 29 Nov 2022.

Builds on

49 of 58 references.

Closest ancestors · 16

Same direction, newest first

  1. 2022Wavelet Score-Based Generative Modeling9 Aug
  2. 2022Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling5 Jul
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  4. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  5. 2021Variational Diffusion Models1 Jul
  6. 2021Score-based Generative Modeling in Latent Space10 Jun
  7. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matching5 Jun
  8. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
  9. 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
  10. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  11. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  12. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed7 Jan
4 more
  1. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  2. 2020Denoising Diffusion Implicit Models6 Oct
  3. 2020Denoising Diffusion Probabilistic Models19 Jun
  4. 2020Improved Techniques for Training Score-Based Generative Models16 Jun

Other references · 33

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  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. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2022Generative Adversarial Networkscited by 5,603
  7. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  9. 2013Auto-Encoding Variational Bayescited by 3,980
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  12. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
21 more
  1. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  2. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  3. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  4. 2016Pixel Recurrent Neural Networkscited by 814
  5. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  6. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  7. 2020Focal Frequency Loss for Image Reconstruction and Synthesiscited by 204
  8. 2019Photorealistic Style Transfer via Wavelet Transformscited by 166
  9. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
  10. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 122
  11. 2021ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesiscited by 122
  12. 2020VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Modelscited by 103
  13. 2022Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learningcited by 78
  14. 2020Wavelet Integrated CNNs for Noise-Robust Image Classificationcited by 60
  15. 2019Multi-level Wavelet Convolutional Neural Networkscited by 59
  16. 2021WaveFill: A Wavelet-based Generation Network for Image Inpaintingcited by 44
  17. 2021High-Fidelity and Arbitrary Face Editingcited by 35
  18. 2019Wavelet Domain Style Transfer for an Effective Perception-distortion Tradeoff in Single Image Super-Resolutioncited by 30
  19. 2022WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generationcited by 22
  20. 2022FreGAN: Exploiting Frequency Components for Training GANs under Limited Datacited by 16
  21. 2021Wavelet Transform-assisted Adaptive Generative Modeling for Colorizationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 17; 2024: 39; 2025: 37; 2026: 22.

116 papers.

Sort:

By area:

  1. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  2. 2023Structural Pruning for Diffusion Modelscited by 193
  3. 2023Flow Matching in Latent Spacecited by 155
  4. 2023Relay Diffusion: Unifying diffusion process across resolutions for image synthesiscited by 78
  5. 2024Wavelet Convolutions for Large Receptive Fieldscited by 74
  6. 2025Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Modelscited by 61
  7. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
  8. 2024WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesiscited by 56
  9. 2024Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attentioncited by 55
  10. 2024Boosting Diffusion Models with Moving Average Sampling in Frequency Domaincited by 53
  11. 2025A Fourier Space Perspective on Diffusion Modelscited by 48
  12. 2023WaveDM: Wavelet-Based Diffusion Models for Image Restorationcited by 46
38 more
  1. 2024Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modellingcited by 43
  2. 2023Infinite-Dimensional Diffusion Modelscited by 38
  3. 2023Generative-based Fusion Mechanism for Multi-Modal Trackingcited by 33
  4. 2024DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Spacecited by 32
  5. 2022Neural Fourier Filter Bankcited by 29
  6. 2024Blue noise for diffusion modelscited by 29
  7. 2024EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Modelscited by 23
  8. 2024Denoising Diffusion Models for 3D Healthy Brain Tissue Inpaintingcited by 22
  9. 2024LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Modelscited by 22
  10. 2023Diffusion Noise Feature: Accurate and Fast Generated Image Detectioncited by 21
  11. 2024WaveFace: Authentic Face Restoration with Efficient Frequency Recoverycited by 20
  12. 2023Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolutioncited by 19
  13. 2024RAD: Region-Aware Diffusion Models for Image Inpaintingcited by 19
  14. 2024Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifactscited by 16
  15. 2023DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Datacited by 15
  16. 2024Spectral Image Tokenizercited by 15
  17. 2025Lipschitz-Guided Design of Interpolation Schedules in Generative Modelscited by 15
  18. 2024Deep Generative Models for 3D Medical Image Synthesiscited by 14
  19. 2024Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generationcited by 14
  20. 2024All-in-one Weather-degraded Image Restoration via Adaptive Degradation-aware Self-prompting Modelcited by 13
  21. 2025Improved Training Technique for Latent Consistency Modelscited by 13
  22. 2024DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generationcited by 11
  23. 2023Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generationcited by 9
  24. 2024Wavelets Are All You Need for Autoregressive Image Generationcited by 9
  25. 2025Rethinking Brain Tumor Segmentation from the Frequency Domain Perspectivecited by 9
  26. 2023Fr'echet Wavelet Distance: A Domain-Agnostic Metric for Image Generationcited by 8
  27. 2024TriNeRFLet: A Wavelet Based Triplane NeRF Representationcited by 8
  28. 2025Image Editing with Diffusion Models: A Surveycited by 8
  29. 2025fastWDM3D: Fast and Accurate 3D Healthy Tissue Inpaintingcited by 8
  30. 2023Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Modelscited by 7
  31. 2025Decoupling High and Low Frequencies for Faithful Image Generation with Fine Detailscited by 7
  32. 2023DiffNAS: Bootstrapping Diffusion Models by Prompting for Better Architecturescited by 6
  33. 2023A High-Quality Robust Diffusion Framework for Corrupted Datasetcited by 6
  34. 2024See Further When Clear: Curriculum Consistency Modelcited by 6
  35. 2025Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesiscited by 6
  36. 2023Patch-based Selection and Refinement for Early Object Detectioncited by 5
  37. 2024Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognitioncited by 5
  38. 2024U-Know-DiffPAN: An Uncertainty-aware Knowledge Distillation Diffusion Framework with Details Enhancement for PAN-Sharpeningcited by 5

50 most cited of 116 All 116 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
  2. 2025A Hybrid Wavelet-Fourier Method for Next-Generation Conditional Diffusion Models
  3. 2023Efficient Transfer Learning in Diffusion Models via Adversarial Noise
  4. 2022Progressive Distillation for Fast Sampling of Diffusion Models
  5. 2024Accelerating Video Diffusion Models via Distribution Matching
  6. 2022SinFusion: Training Diffusion Models on a Single Image or Video
  7. 2024Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models
  8. 2022SinDiffusion: Learning a Diffusion Model from a Single Natural Image