mlsanityData to 14 Oct 2026

Temporal Dynamic Quantization for Diffusion Models

arXiv 2306.02316 ↗First posted 4 Jun 2023cs.CVcited by 81

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

The diffusion model has gained popularity in vision applications due to its remarkable generative performance and versatility. However, high storage and computation demands, resulting from the model size and iterative generation, hinder its use on mobile devices. Existing quantization techniques struggle to maintain performance even in 8-bit precision due to the diffusion model's unique property of temporal variation in activation. We introduce a novel quantization method that dynamically adjusts the quantization interval based on time step information, significantly improving output quality. Unlike conventional dynamic quantization techniques, our approach has no computational overhead during inference and is compatible with both post-training quantization (PTQ) and quantization-aware training (QAT). Our extensive experiments demonstrate substantial improvements in output quality with the quantized diffusion model across various datasets.

Key facts. Cited by 81 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 44 of its 49 references that are in the map. First posted on arXiv 4 Jun 2023.

Builds on

44 of 49 references.

Closest ancestors · 10

Same direction, newest first

  1. 2023PTQD: Accurate Post-Training Quantization for Diffusion Models18 May
  2. 2022Post-training Quantization on Diffusion Models28 Nov
  3. 2022On Distillation of Guided Diffusion Models6 Oct
  4. 2022Classifier-Free Diffusion Guidance26 Jul
  5. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  7. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  9. 2020Denoising Diffusion Implicit Models6 Oct
  10. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  7. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  9. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  10. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  11. 2016Improved Techniques for Training GANscited by 2,970
  12. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
22 more
  1. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  2. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  3. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  4. 2018On the Spectral Bias of Neural Networkscited by 1,341
  5. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  6. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
  7. 2019Learned Step Size Quantizationcited by 628
  8. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 621
  9. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 526
  10. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  11. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  12. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  13. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 336
  14. 2020LSQ+: Improving low-bit quantization through learnable offsets and better initializationcited by 189
  15. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 180
  16. 2018Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Losscited by 160
  17. 2022MobileOne: An Improved One millisecond Mobile Backbonecited by 109
  18. 2020PROFIT: A Novel Training Method for sub-4-bit MobileNet Modelscited by 50
  19. 2022NIPQ: Noise proxy-based Integrated Pseudo-Quantizationcited by 35
  20. 2022CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolutioncited by 27
  21. 2022Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networkscited by 21
  22. 2022INSTA-BNN: Binary Neural Network with INSTAnce-aware Thresholdcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 30; 2025: 31; 2026: 16.

81 papers.

Sort:

By area:

  1. 2024Timestep Embedding Tells: It's Time to Cache for Video Diffusion Modelcited by 269
  2. 2024Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformerscited by 175
  3. 2024Real-Time Video Generation with Pyramid Attention Broadcastcited by 149
  4. 2024FasterCache: Training-Free Video Diffusion Model Acceleration with High Qualitycited by 122
  5. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationcited by 115
  6. 2024Q-DiT: Accurate Post-Training Quantization for Diffusion Transformerscited by 94
  7. 2023EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Modelscited by 78
  8. 2023TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Modelscited by 69
  9. 2024Dynamic Diffusion Transformercited by 62
  10. 2024QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuningcited by 49
  11. 2024MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantizationcited by 43
  12. 2025MagCache: Fast Video Generation with Magnitude-Aware Cachecited by 41
38 more
  1. 2024BitsFusion: 1.99 bits Weight Quantization of Diffusion Modelcited by 37
  2. 2025Efficient Diffusion Models: A Surveycited by 35
  3. 2024EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Modelscited by 23
  4. 2024Importance-Based Token Merging for Efficient Image and Video Generationcited by 22
  5. 2025QVGen: Pushing the Limit of Quantized Video Generative Modelscited by 22
  6. 2023Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxingcited by 21
  7. 2023FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Modelscited by 20
  8. 2025Ditto: Accelerating Diffusion Model via Temporal Value Similaritycited by 18
  9. 2025Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Accelerationcited by 17
  10. 2025Recurrent Diffusion for Large-Scale Parameter Generationcited by 15
  11. 2024QVD: Post-training Quantization for Video Diffusion Modelscited by 14
  12. 2024Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Modelscited by 13
  13. 2024Timestep-Aware Correction for Quantized Diffusion Modelscited by 13
  14. 2024QNCD: Quantization Noise Correction for Diffusion Modelscited by 11
  15. 2024BinaryDM: Accurate Weight Binarization for Efficient Diffusion Modelscited by 11
  16. 2024BiDM: Pushing the Limit of Quantization for Diffusion Modelscited by 11
  17. 2025DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Modelscited by 11
  18. 2025Low-bit Model Quantization for Deep Neural Networks: A Surveycited by 11
  19. 2026SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Modelscited by 11
  20. 2024PTQ4VM: Post-Training Quantization for Visual Mambacited by 10
  21. 2025LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generationcited by 10
  22. 2026MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inferencecited by 10
  23. 2024PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolutioncited by 9
  24. 2025Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformerscited by 7
  25. 2025FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformerscited by 6
  26. 2025Diffusion Model Quantization: A Reviewcited by 6
  27. 2025Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuningcited by 6
  28. 2025DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantizationcited by 6
  29. 2024Temporal Feature Matters: A Framework for Diffusion Model Quantizationcited by 5
  30. 2025Random Conditioning with Distillation for Data-Efficient Diffusion Model Compressioncited by 5
  31. 2025FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Trainingcited by 5
  32. 2024FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillationcited by 4
  33. 2025ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generationcited by 4
  34. 2026DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformerscited by 4
  35. 2024Accurate Compression of Text-to-Image Diffusion Models via Vector Quantizationcited by 3
  36. 2024PTQ4ADM: Post-Training Quantization for Efficient Text Conditional Audio Diffusion Modelscited by 3
  37. 2024Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusioncited by 3
  38. 2025Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Schedulingcited by 3

50 most cited of 81 All 81 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025TR-DQ: Time-Rotation Diffusion Quantization
  2. 20266Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models
  3. 2024PQD: Post-training Quantization for Efficient Diffusion Models
  4. 2023Towards Accurate Post-training Quantization for Diffusion Models
  5. 2023Q-Diffusion: Quantizing Diffusion Models
  6. 2023Efficient Quantization Strategies for Latent Diffusion Models
  7. 2024TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models
  8. 2023Effective Quantization for Diffusion Models on CPUs