mlsanityData to 14 Oct 2026

FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

arXiv 2410.19355 ↗First posted 25 Oct 2024cs.CVcited by 122

On the map: Diffusion models → Video generation

Abstract (arXiv)

In this paper, we present textbftextitFasterCache, a novel training-free strategy designed to accelerate the inference of video diffusion models with high-quality generation. By analyzing existing cache-based methods, we observe that textitdirectly reusing adjacent-step features degrades video quality due to the loss of subtle variations. We further perform a pioneering investigation of the acceleration potential of classifier-free guidance (CFG) and reveal significant redundancy between conditional and unconditional features within the same timestep. Capitalizing on these observations, we introduce FasterCache to substantially accelerate diffusion-based video generation. Our key contributions include a dynamic feature reuse strategy that preserves both feature distinction and temporal continuity, and CFG-Cache which optimizes the reuse of conditional and unconditional outputs to further enhance inference speed without compromising video quality. We empirically evaluate FasterCache on recent video diffusion models. Experimental results show that FasterCache can significantly accelerate video generation (eg 1.67× speedup on Vchitect-2.0) while keeping video quality comparable to the baseline, and consistently outperform existing methods in both inference speed and video quality.

Key facts. Cited by 122 papers in the map (data through 14 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 46 of its 52 references that are in the map. First posted on arXiv 25 Oct 2024.

Builds on

46 of 52 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer12 Aug
  2. 2024AnimateDiff-Lightning: Cross-Model Diffusion Distillation19 Mar
  3. 2024VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models8 Mar
  4. 2024Latte: Latent Diffusion Transformer for Video Generation5 Jan
  5. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets25 Nov
  6. 2023DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors18 Oct
  7. 2023ControlVideo: Training-free Controllable Text-to-Video Generation22 May
  8. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation22 Dec
  9. 2022Video Diffusion Models7 Apr

Other references · 37

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2022Scalable Diffusion Models with Transformerscited by 6,054
  6. 2022Classifier-Free Diffusion Guidancecited by 5,847
  7. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  8. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  9. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  10. 2023Consistency Modelscited by 1,822
  11. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  12. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
25 more
  1. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  2. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 846
  3. 2023Adversarial Diffusion Distillationcited by 759
  4. 2022On Distillation of Guided Diffusion Modelscited by 725
  5. 2023DeepCache: Accelerating Diffusion Models for Freecited by 359
  6. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generationcited by 329
  7. 2022Post-training Quantization on Diffusion Modelscited by 267
  8. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
  9. 2023Token Merging for Fast Stable Diffusioncited by 224
  10. 2023FreeU: Free Lunch in Diffusion U-Netcited by 196
  11. 2024Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformerscited by 175
  12. 2023PTQD: Accurate Post-Training Quantization for Diffusion Modelscited by 170
  13. 2023Cache Me if You Can: Accelerating Diffusion Models through Block Cachingcited by 151
  14. 2024Real-Time Video Generation with Pyramid Attention Broadcastcited by 149
  15. 2024PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Modelscited by 141
  16. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationcited by 115
  17. 2023Temporal Dynamic Quantization for Diffusion Modelscited by 81
  18. 2023AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Accelerationcited by 70
  19. 2024LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Modelscited by 53
  20. 2024Attention-Driven Training-Free Efficiency Enhancement of Diffusion Modelscited by 38
  21. 2024BitsFusion: 1.99 bits Weight Quantization of Diffusion Modelcited by 37
  22. 2023Denoising Diffusion Step-aware Modelscited by 24
  23. 2023FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Modelscited by 20
  24. 2024Plug-and-Play Diffusion Distillationcited by 16
  25. 2024DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformerscited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 46; 2026: 72.

122 papers.

Sort:

By area:

  1. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  2. 2024Timestep Embedding Tells: It's Time to Cache for Video Diffusion Modelcited by 269
  3. 2025Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsitycited by 217
  4. 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Modelscited by 143
  5. 2025dKV-Cache: The Cache for Diffusion Language Modelscited by 143
  6. 2025From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeerscited by 136
  7. 2025Fast Video Generation with Sliding Tile Attentioncited by 128
  8. 2024Adaptive Caching for Faster Video Generation with Diffusion Transformerscited by 108
  9. 2025Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutationcited by 106
  10. 2025A Survey on Diffusion Language Modelscited by 78
  11. 2025DiCache: Let Diffusion Model Determine Its Own Cachecited by 42
  12. 2025MagCache: Fast Video Generation with Magnitude-Aware Cachecited by 41
38 more
  1. 2025VMoBA: Mixture-of-Block Attention for Video Diffusion Modelscited by 37
  2. 2025Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformerscited by 34
  3. 2025FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximationcited by 24
  4. 2025VORTA: Efficient Video Diffusion via Routing Sparse Attentioncited by 23
  5. 2024Importance-Based Token Merging for Efficient Image and Video Generationcited by 22
  6. 2025QVGen: Pushing the Limit of Quantized Video Generative Modelscited by 22
  7. 2025Dual-Expert Consistency Model for Efficient and High-Quality Video Generationcited by 21
  8. 2025FreqCa: Accelerating Diffusion Models via Frequency-Aware Cachingcited by 20
  9. 2025A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generationcited by 16
  10. 2025Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Modelscited by 15
  11. 2025UniCP: A Unified Caching and Pruning Framework for Efficient Video Generationcited by 14
  12. 2025AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reusecited by 13
  13. 2025ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusioncited by 12
  14. 2025Astraea: A Token-wise Acceleration Framework for Video Diffusion Transformerscited by 11
  15. 2025BWCache: Accelerating Video Diffusion Transformers through Block-Wise Cachingcited by 11
  16. 2026SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Modelscited by 11
  17. 2025Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformerscited by 10
  18. 2025LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generationcited by 10
  19. 2026SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routingcited by 10
  20. 2025HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streamingcited by 8
  21. 2026Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformerscited by 8
  22. 2026PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generationcited by 8
  23. 2025SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperationcited by 7
  24. 2026SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformercited by 7
  25. 2026DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Cachingcited by 7
  26. 2026SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Cachingcited by 7
  27. 2026Adaptive Spectral Feature Forecasting for Diffusion Sampling Accelerationcited by 7
  28. 2026Efficient Video Diffusion Models: Advancements and Challengescited by 7
  29. 2025Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generationcited by 6
  30. 2025SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tilingcited by 6
  31. 2026SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillationcited by 6
  32. 2026AlayaWorld: Long-Horizon and Playable Video World Generationcited by 6
  33. 2025Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generationcited by 5
  34. 2026FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Spacecited by 5
  35. 2026Relational Feature Caching for Accelerating Diffusion Transformerscited by 5
  36. 2026ToProVAR: Efficient Visual Autoregressive Modeling via Tri-Dimensional Entropy-Aware Semantic Analysis and Sparsity Optimizationcited by 5
  37. 2026Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithmscited by 5
  38. 2026Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolationcited by 5

50 most cited of 122 All 122 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
  2. 2025LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation
  3. 2025TaoCache: Structure-Maintained Video Generation Acceleration
  4. 2026LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching
  5. 2026Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep
  6. 2026LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration
  7. 2026Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse
  8. 2025Adaptive Hybrid Caching for Efficient Text-to-Video Diffusion Model Acceleration