mlsanityData to 7 Oct 2026

Q-Diffusion: Quantizing Diffusion Models

arXiv 2302.04304 ↗First posted 8 Feb 2023cs.CV cs.LGcited by 266

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion models have achieved great success in image synthesis through iterative noise estimation using deep neural networks. However, the slow inference, high memory consumption, and computation intensity of the noise estimation model hinder the efficient adoption of diffusion models. Although post-training quantization (PTQ) is considered a go-to compression method for other tasks, it does not work out-of-the-box on diffusion models. We propose a novel PTQ method specifically tailored towards the unique multi-timestep pipeline and model architecture of the diffusion models, which compresses the noise estimation network to accelerate the generation process. We identify the key difficulty of diffusion model quantization as the changing output distributions of noise estimation networks over multiple time steps and the bimodal activation distribution of the shortcut layers within the noise estimation network. We tackle these challenges with timestep-aware calibration and split shortcut quantization in this work. Experimental results show that our proposed method is able to quantize full-precision unconditional diffusion models into 4-bit while maintaining comparable performance (small FID change of at most 2.34 compared to >100 for traditional PTQ) in a training-free manner. Our approach can also be applied to text-guided image generation, where we can run stable diffusion in 4-bit weights with high generation quality for the first time.

Key facts. Cited by 266 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 59 of its 71 references that are in the map. First posted on arXiv 8 Feb 2023.

Builds on

59 of 71 references.

Closest ancestors · 16

Same direction, newest first

  1. 2022Scalable Diffusion Models with Transformers19 Dec
  2. 2022Post-training Quantization on Diffusion Models28 Nov
  3. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  4. 2022On Distillation of Guided Diffusion Models6 Oct
  5. 2022Understanding Diffusion Models: A Unified Perspective25 Aug
  6. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  7. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  8. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models17 Jan
  9. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  10. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  11. 2021UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models12 Apr
  12. 2021Noise Estimation for Generative Diffusion Models6 Apr
4 more
  1. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  3. 2020Denoising Diffusion Implicit Models6 Oct
  4. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 43

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  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. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  9. 2016Improved Techniques for Training GANscited by 2,938
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  11. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  12. 2022Video Diffusion Modelscited by 2,280
31 more
  1. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  2. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  4. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 881
  5. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  6. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  7. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  8. 2019Learned Step Size Quantizationcited by 604
  9. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  10. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  11. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  12. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  13. 2021A White Paper on Neural Network Quantizationcited by 453
  14. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  15. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 387
  16. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 265
  17. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
  18. 2021Generating Images with Sparse Representationscited by 262
  19. 2019HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networkscited by 250
  20. 2020Learning Gradient Fields for Shape Generationcited by 245
  21. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 211
  22. 2020LSQ+: Improving low-bit quantization through learnable offsets and better initializationcited by 180
  23. 2019Improving Neural Network Quantization without Retraining using Outlier Channel Splittingcited by 150
  24. 2022NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformerscited by 59
  25. 2020EasyQuant: Post-training Quantization via Scale Optimizationcited by 57
  26. 2022SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximationcited by 51
  27. 2022Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Modelscited by 44
  28. 2022Structural Pruning via Latency-Saliency Knapsackcited by 40
  29. 2021BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantizationcited by 37
  30. 2021Unsupervised Selective Labeling for More Effective Semi-Supervised Learningcited by 27
  31. 2022CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsificationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 21; 2024: 75; 2025: 97; 2026: 73.

266 papers.

Sort:

By area:

  1. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 331
  2. 2023SqueezeLLM: Dense-and-Sparse Quantizationcited by 285
  3. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
  4. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 209
  5. 2025Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsitycited by 204
  6. 2023PTQD: Accurate Post-Training Quantization for Diffusion Modelscited by 167
  7. 2024SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelscited by 161
  8. 2024Accelerating Diffusion Transformers with Token-wise Feature Cachingcited by 143
  9. 2024Learning-to-Cache: Accelerating Diffusion Transformer via Layer Cachingcited by 138
  10. 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Modelscited by 126
  11. 2025From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeerscited by 124
  12. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationcited by 110
38 more
  1. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  2. 2024Adaptive Caching for Faster Video Generation with Diffusion Transformerscited by 100
  3. 2024DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Modelscited by 98
  4. 2024Q-DiT: Accurate Post-Training Quantization for Diffusion Transformerscited by 91
  5. 2024Dreamitate: Real-World Visuomotor Policy Learning via Video Generationcited by 84
  6. 2023EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Modelscited by 77
  7. 2024PTQ4DiT: Post-training Quantization for Diffusion Transformerscited by 77
  8. 2023TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Modelscited by 67
  9. 2024LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insightscited by 65
  10. 2025Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generationcited by 64
  11. 2024Dynamic Diffusion Transformercited by 60
  12. 2023StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generationcited by 56
  13. 2024Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesiscited by 55
  14. 2024QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuningcited by 48
  15. 2023Towards Accurate Post-training Quantization for Diffusion Modelscited by 46
  16. 2024TinyFusion: Diffusion Transformers Learned Shallowcited by 44
  17. 2024MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantizationcited by 42
  18. 2024BitsFusion: 1.99 bits Weight Quantization of Diffusion Modelcited by 37
  19. 2025Efficient Diffusion Models: A Surveycited by 35
  20. 2025FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruningcited by 34
  21. 2024Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generationcited by 33
  22. 2025Training-Free Efficient Video Generation via Dynamic Token Carvingcited by 33
  23. 2024T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitchingcited by 32
  24. 2024PTQ4SAM: Post-Training Quantization for Segment Anythingcited by 32
  25. 2024Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficientcited by 32
  26. 2024On the Challenges and Opportunities in Generative AIcited by 31
  27. 2024SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flowcited by 30
  28. 2024Token Caching for Diffusion Transformer Accelerationcited by 29
  29. 2023The Efficiency Spectrum of Large Language Models: An Algorithmic Surveycited by 25
  30. 2024EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Modelscited by 23
  31. 2024SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditionscited by 23
  32. 202570% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)cited by 23
  33. 2025Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compressioncited by 22
  34. 2023Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxingcited by 21
  35. 2023Diffusion Noise Feature: Accurate and Fast Generated Image Detectioncited by 21
  36. 2024DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecturecited by 21
  37. 2025DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidancecited by 21
  38. 2024Importance-Based Token Merging for Efficient Image and Video Generationcited by 20

50 most cited of 266 All 266 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024PQD: Post-training Quantization for Efficient Diffusion Models
  2. 2024TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models
  3. 2024DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation
  4. 2024Qua2SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models
  5. 2024MPQ-Diff: Mixed Precision Quantization for Diffusion Models
  6. 2025Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression
  7. 2024Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion
  8. 2026TASQ: Temporal-Adaptive Bit Sparsification Quantization for Diffusion Models