mlsanityData to 14 Oct 2026

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models

arXiv 2311.16503 ↗First posted 27 Nov 2023cs.CV cs.AI cs.LGcited by 69

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

The Diffusion model, a prevalent framework for image generation, encounters significant challenges in terms of broad applicability due to its extended inference times and substantial memory requirements. Efficient Post-training Quantization (PTQ) is pivotal for addressing these issues in traditional models. Different from traditional models, diffusion models heavily depend on the time-step t to achieve satisfactory multi-round denoising. Usually, t from the finite set 1, ldots, T is encoded to a temporal feature by a few modules totally irrespective of the sampling data. However, existing PTQ methods do not optimize these modules separately. They adopt inappropriate reconstruction targets and complex calibration methods, resulting in a severe disturbance of the temporal feature and denoising trajectory, as well as a low compression efficiency. To solve these, we propose a Temporal Feature Maintenance Quantization (TFMQ) framework building upon a Temporal Information Block which is just related to the time-step t and unrelated to the sampling data. Powered by the pioneering block design, we devise temporal information aware reconstruction (TIAR) and finite set calibration (FSC) to align the full-precision temporal features in a limited time. Equipped with the framework, we can maintain the most temporal information and ensure the end-to-end generation quality. Extensive experiments on various datasets and diffusion models prove our state-of-the-art results. Remarkably, our quantization approach, for the first time, achieves model performance nearly on par with the full-precision model under 4-bit weight quantization. Additionally, our method incurs almost no extra computational cost and accelerates quantization time by 2.0 × on LSUN-Bedrooms 256 × 256 compared to previous works. Our code is publicly available at https://github.com/ModelTC/TFMQ-DM.

Key facts. Cited by 69 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 39 of its 48 references that are in the map. First posted on arXiv 27 Nov 2023.

Builds on

39 of 48 references.

Closest ancestors · 18

Same direction, newest first

  1. 2023Temporal Dynamic Quantization for Diffusion Models4 Jun
  2. 2023PTQD: Accurate Post-Training Quantization for Diffusion Models18 May
  3. 2023Q-Diffusion: Quantizing Diffusion Models8 Feb
  4. 2022Scalable Diffusion Models with Transformers19 Dec
  5. 2022Post-training Quantization on Diffusion Models28 Nov
  6. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  7. 2022Classifier-Free Diffusion Guidance26 Jul
  8. 2022gDDIM: Generalized denoising diffusion implicit models11 Jun
  9. 2022How Much is Enough? A Study on Diffusion Times in Score-based Generative Models10 Jun
  10. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  11. 2022Accelerating Diffusion Models via Early Stop of the Diffusion Process25 May
  12. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
6 more
  1. 2022Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders19 Feb
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  3. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
  4. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  5. 2020Denoising Diffusion Implicit Models6 Oct
  6. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 21

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2022Generative Adversarial Networkscited by 5,627
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  6. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  8. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  9. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  10. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  11. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  12. 2019Learned Step Size Quantizationcited by 628
9 more
  1. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 621
  2. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  3. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  4. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 307
  5. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 238
  6. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 180
  7. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 151
  8. 2020Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programmingcited by 92
  9. 2017Towards Effective Low-bitwidth Convolutional Neural Networkscited by 78

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 22; 2025: 32; 2026: 14.

69 papers.

Sort:

By area:

  1. 2024SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelscited by 170
  2. 2024Q-DiT: Accurate Post-Training Quantization for Diffusion Transformerscited by 94
  3. 2023StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generationcited by 58
  4. 2024QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuningcited by 49
  5. 2024MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantizationcited by 43
  6. 2024BitsFusion: 1.99 bits Weight Quantization of Diffusion Modelcited by 37
  7. 2024SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flowcited by 30
  8. 2024EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Modelscited by 23
  9. 2025QVGen: Pushing the Limit of Quantized Video Generative Modelscited by 22
  10. 2024MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Modelscited by 21
  11. 2025FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusioncited by 19
  12. 2025Ditto: Accelerating Diffusion Model via Temporal Value Similaritycited by 18
38 more
  1. 2024HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Accelerationcited by 17
  2. 2024QVD: Post-training Quantization for Video Diffusion Modelscited by 14
  3. 2024Timestep-Aware Correction for Quantized Diffusion Modelscited by 13
  4. 2024DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothingcited by 13
  5. 2025SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruningcited by 13
  6. 2025MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillationcited by 12
  7. 2025LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generationcited by 12
  8. 2024BinaryDM: Accurate Weight Binarization for Efficient Diffusion Modelscited by 11
  9. 2024BiDM: Pushing the Limit of Quantization for Diffusion Modelscited by 11
  10. 2025DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Modelscited by 11
  11. 2025Low-bit Model Quantization for Deep Neural Networks: A Surveycited by 11
  12. 2025BWCache: Accelerating Video Diffusion Transformers through Block-Wise Cachingcited by 11
  13. 2025LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generationcited by 11
  14. 2024IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Modelscited by 10
  15. 2024Towards Next-Level Post-Training Quantization of Hyper-Scale Transformerscited by 9
  16. 2025LLMC+: Benchmarking Vision-Language Model Compression with a Plug-and-play Toolkitcited by 7
  17. 2026Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusingcited by 7
  18. 2026Flash-VAED: Plug-and-Play VAE Decoders for Efficient Video Generationcited by 7
  19. 2024TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Modelscited by 6
  20. 2025FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformerscited by 6
  21. 2025Diffusion Model Quantization: A Reviewcited by 6
  22. 2025DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantizationcited by 6
  23. 2025Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modelingcited by 6
  24. 2026PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inferencecited by 6
  25. 2026SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillationcited by 6
  26. 2024Temporal Feature Matters: A Framework for Diffusion Model Quantizationcited by 5
  27. 2024PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Modelscited by 5
  28. 2025Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantizationcited by 5
  29. 2025Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusioncited by 5
  30. 2025Pyramidal Patchification Flow for Visual Generationcited by 4
  31. 2025Test-Time Iterative Error Correction for Efficient Diffusion Modelscited by 4
  32. 2026Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Samplingcited by 4
  33. 2024Accurate Compression of Text-to-Image Diffusion Models via Vector Quantizationcited by 3
  34. 2024Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusioncited by 3
  35. 2025SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsitycited by 3
  36. 2025GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolutioncited by 3
  37. 2025AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Modelscited by 3
  38. 2025TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Searchcited by 3

50 most cited of 69 All 69 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
  2. 2026TMPDiff: Temporal Mixed-Precision for Diffusion Models
  3. 2024PQD: Post-training Quantization for Efficient Diffusion Models
  4. 2024MPQ-Diff: Mixed Precision Quantization for Diffusion Models
  5. 2025D2-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models
  6. 2023Efficient Quantization Strategies for Latent Diffusion Models
  7. 2023Towards Accurate Post-training Quantization for Diffusion Models
  8. 2023Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing