mlsanityData to 14 Oct 2026

DeepCache: Accelerating Diffusion Models for Free

arXiv 2312.00858 ↗First posted 1 Dec 2023cs.CV cs.AIcited by 359

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models have recently gained unprecedented attention in the field of image synthesis due to their remarkable generative capabilities. Notwithstanding their prowess, these models often incur substantial computational costs, primarily attributed to the sequential denoising process and cumbersome model size. Traditional methods for compressing diffusion models typically involve extensive retraining, presenting cost and feasibility challenges. In this paper, we introduce DeepCache, a novel training-free paradigm that accelerates diffusion models from the perspective of model architecture. DeepCache capitalizes on the inherent temporal redundancy observed in the sequential denoising steps of diffusion models, which caches and retrieves features across adjacent denoising stages, thereby curtailing redundant computations. Utilizing the property of the U-Net, we reuse the high-level features while updating the low-level features in a very cheap way. This innovative strategy, in turn, enables a speedup factor of 2.3× for Stable Diffusion v1.5 with only a 0.05 decline in CLIP Score, and 4.1× for LDM-4-G with a slight decrease of 0.22 in FID on ImageNet. Our experiments also demonstrate DeepCache's superiority over existing pruning and distillation methods that necessitate retraining and its compatibility with current sampling techniques. Furthermore, we find that under the same throughput, DeepCache effectively achieves comparable or even marginally improved results with DDIM or PLMS. The code is available at https://github.com/horseee/DeepCache

Key facts. Cited by 359 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 58 of its 73 references that are in the map. First posted on arXiv 1 Dec 2023.

Builds on

58 of 73 references.

Closest ancestors · 26

Same direction, newest first

  1. 2023Denoising Diffusion Step-aware Models5 Oct
  2. 2023AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration19 Sep
  3. 2023OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models15 Jun
  4. 2023Parallel Sampling of Diffusion Models25 May
  5. 2023Structural Pruning for Diffusion Models18 May
  6. 2023PTQD: Accurate Post-Training Quantization for Diffusion Models18 May
  7. 2023Token Merging for Fast Stable Diffusion30 Mar
  8. 2023Consistency Models2 Mar
  9. 2022Post-training Quantization on Diffusion Models28 Nov
  10. 2022Diffusion Probabilistic Model Made Slim27 Nov
  11. 2022Fast Sampling of Diffusion Models via Operator Learning24 Nov
  12. 2022On Distillation of Guided Diffusion Models6 Oct
14 more
  1. 2022Non-Uniform Diffusion Models20 Jul
  2. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  3. 2022Accelerating Diffusion Models via Early Stop of the Diffusion Process25 May
  4. 2022Fast Sampling of Diffusion Models with Exponential Integrator29 Apr
  5. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  6. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models17 Jan
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  8. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
  9. 2021Score-based Generative Modeling in Latent Space10 Jun
  10. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  11. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  12. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  13. 2020Denoising Diffusion Implicit Models6 Oct
  14. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 32

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  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. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  8. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  9. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  10. 2016Improved Techniques for Training GANscited by 2,970
  11. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  12. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
20 more
  1. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  2. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  3. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  4. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  5. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  6. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  7. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  8. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,178
  9. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  10. 2022Denoising Diffusion Restoration Modelscited by 963
  11. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  12. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 927
  13. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  14. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  15. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 450
  16. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 447
  17. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  18. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 384
  19. 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generationcited by 331
  20. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 76; 2025: 129; 2026: 151.

359 papers.

Sort:

By area:

  1. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 217
  2. 2025Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsitycited by 217
  3. 2024Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformerscited by 175
  4. 2024SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelscited by 170
  5. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 169
  6. 2024Accelerating Diffusion Transformers with Token-wise Feature Cachingcited by 156
  7. 2024Real-Time Video Generation with Pyramid Attention Broadcastcited by 149
  8. 2025dKV-Cache: The Cache for Diffusion Language Modelscited by 143
  9. 2024Learning-to-Cache: Accelerating Diffusion Transformer via Layer Cachingcited by 142
  10. 2024FORA: Fast-Forward Caching in Diffusion Transformer Accelerationcited by 137
  11. 2025From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeerscited by 136
  12. 2024FasterCache: Training-Free Video Diffusion Model Acceleration with High Qualitycited by 122
38 more
  1. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationcited by 115
  2. 2024DiTFastAttn: Attention Compression for Diffusion Transformer Modelscited by 115
  3. 2024Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyondcited by 111
  4. 2025DDT: Decoupled Diffusion Transformercited by 109
  5. 2024Adaptive Caching for Faster Video Generation with Diffusion Transformerscited by 108
  6. 2025LongCat-Image Technical Reportcited by 100
  7. 2025A Survey on Diffusion Language Modelscited by 78
  8. 2024Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Imagescited by 69
  9. 2025Training-free and Adaptive Sparse Attention for Efficient Long Video Generationcited by 69
  10. 2025Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generationcited by 69
  11. 2024MindBridge: A Cross-Subject Brain Decoding Frameworkcited by 66
  12. 2024Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decodingcited by 66
  13. 2024Dynamic Diffusion Transformercited by 62
  14. 2024xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelismcited by 56
  15. 2024Faster Diffusion via Temporal Attention Decompositioncited by 54
  16. 2024LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Modelscited by 53
  17. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 52
  18. 2025Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithmscited by 47
  19. 2025EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editingcited by 45
  20. 2024LinFusion: 1 GPU, 1 Minute, 16K Imagecited by 43
  21. 2024DiP-GO: A Diffusion Pruner via Few-step Gradient Optimizationcited by 43
  22. 2025Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animationcited by 43
  23. 2024Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillationcited by 39
  24. 2024Looking Backward: Streaming Video-to-Video Translation with Feature Bankscited by 38
  25. 2025VMoBA: Mixture-of-Block Attention for Video Diffusion Modelscited by 37
  26. 2025Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generationcited by 36
  27. 2025POSTA: A Go-to Framework for Customized Artistic Poster Generationcited by 36
  28. 2025Efficient Diffusion Models: A Surveycited by 35
  29. 2023Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inferencecited by 34
  30. 2025FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruningcited by 34
  31. 2025Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformerscited by 34
  32. 2024T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitchingcited by 33
  33. 2024Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generationcited by 33
  34. 2024Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficientcited by 33
  35. 2025Attention Is All You Need for KV Cache in Diffusion LLMscited by 32
  36. 2025Accelerated Diffusion Models via Speculative Samplingcited by 31
  37. 2024SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flowcited by 30
  38. 2024Token Caching for Diffusion Transformer Accelerationcited by 30

50 most cited of 359 All 359 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Cache Me if You Can: Accelerating Diffusion Models through Block Caching
  2. 2026FeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion Inference
  3. 2026CacheScope: Exact-Compute Allocation for Training-Free Diffusion Acceleration
  4. 2023Masked Diffusion Models Are Fast Distribution Learners
  5. 2024DuoDiff: Accelerating Diffusion Models with a Dual-Backbone Approach
  6. 2025Glance: Accelerating Diffusion Models with 1 Sample
  7. 2022Diffusion Models in Vision: A Survey
  8. 2024Diffusion Models in Low-Level Vision: A Survey