mlsanityData to 14 Oct 2026

Improving Diffusion Model Efficiency Through Patching

arXiv 2207.04316 ↗First posted 9 Jul 2022cs.LG cs.CVcited by 15

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models are a powerful class of generative models that iteratively denoise samples to produce data. While many works have focused on the number of iterations in this sampling procedure, few have focused on the cost of each iteration. We find that adding a simple ViT-style patching transformation can considerably reduce a diffusion model's sampling time and memory usage. We justify our approach both through an analysis of the diffusion model objective, and through empirical experiments on LSUN Church, ImageNet 256, and FFHQ 1024. We provide implementations in Tensorflow and Pytorch.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 30 of its 40 references that are in the map. First posted on arXiv 9 Jul 2022.

Builds on

30 of 40 references.

Closest ancestors · 8

Same direction, newest first

  1. 2022Subspace Diffusion Generative Models3 May
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  3. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
  4. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  5. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  6. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  8. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  9. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  11. 2016Density estimation using Real NVPcited by 2,042
  12. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
10 more
  1. 2018Group Normalizationcited by 1,524
  2. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  3. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  4. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  5. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  6. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  7. 2021Vector-quantized Image Modeling with Improved VQGANcited by 658
  8. 2021Generating Images with Sparse Representationscited by 266
  9. 2021You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectioncited by 170
  10. 2021ViTGAN: Training GANs with Vision Transformerscited by 110

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 7; 2024: 2; 2025: 1.

15 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  2. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 931
  3. 2022Scalable Adaptive Computation for Iterative Generationcited by 195
  4. 20234M: Massively Multimodal Masked Modelingcited by 120
  5. 2023DiffiT: Diffusion Vision Transformers for Image Generationcited by 106
  6. 2023Patched Denoising Diffusion Models For High-Resolution Image Synthesiscited by 45
  7. 2023ArchiSound: Audio Generation with Diffusioncited by 20
  8. 2024Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problemscited by 20
  9. 2022Boomerang: Local sampling on image manifolds using diffusion modelscited by 16
  10. 2023Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modelingcited by 13
  11. 2022Dimensionality-Varying Diffusion Processcited by 12
  12. 2023Unsupervised CT Metal Artifact Reduction by Plugging Diffusion Priors in Dual Domainscited by 12
3 more
  1. 2024Quantum Denoising Diffusion Modelscited by 11
  2. 2023Leveraging Graph Diffusion Models for Network Refinement Taskscited by 1
  3. 2025Local Patches Meet Global Context: Scalable 3D Diffusion Priors for Computed Tomography Reconstructioncited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models
  2. 2026Efficient and Training-Free Single-Image Diffusion Models
  3. 2022Progressive Distillation for Fast Sampling of Diffusion Models
  4. 2023Neural Diffusion Models
  5. 2024A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
  6. 2023Memory Efficient Diffusion Probabilistic Models via Patch-based Generation
  7. 2025Diffusion Models: A Mathematical Introduction
  8. 2025Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment