Diffusion Model Quantization

Ask about this topic

Overview

Diffusion model quantization studies how to use fewer bits for model weights, activations, and attention caches while keeping iterative generation close to full precision, enabling larger models to run with less memory and time. Common approaches include post-training quantization and quantization-aware training, with rotations, smoothing, outlier handling, low-rank compensation, and mixed precision used to control errors. Methods increasingly account for changing sensitivity across denoising steps, classifier-free guidance, and temporal consistency, while sampling-side corrections and fused low-bit kernels address error propagation and real deployment speed. W4A4 and even lower-bit settings can retain useful quality on image and video benchmarks such as COCO and VBench, but results remain model- and hardware-dependent: aggressive compression can harm fidelity, and speedups require kernels that use a device’s native low-precision operations.

Latest papers

CardsList

39 papers4 papers in the last four weeks, down 20% on the four weeks before. 0.0% of all new papers.

  1. Triage: Skip, Skim, or Refine Attention Tiles in Video Diffusion Transformers

    Oct 26, 2026Yeonjae Kim, Omin Kwon, Seong Hoon Seo +1Diffusion Model Inference AccelerationVideo Diffusion Models

    Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea.

  2. Deflating the Hessian: Rank-4 W4A4 Quantization for Multimodal Diffusion Transformers

    Oct 8, 2026Shiwen Wang, Pengxiang Zhao, Xiaoming YuanDiffusion Model QuantizationPost-Training Quantization

    The University of Hong Kong · Huawei Technologies Co., Ltd.

  3. SoloQ: Calibration-Free Quantization for Diffusion Language Models

    Oct 5, 2026Donghyun Lee, Arkapravo Ghosh, Varun Manjunath +5Diffusion Model QuantizationKV-Cache Quantization

    University of Southern California · Yale University · Korea University

  4. CentriQ: Calibration-Free Quantization of Diffusion Transformers via Exact Mean Centering

    Oct 5, 2026Nataša Jovanović, Mathieu Salzmann, Saqib JavedDiffusion TransformerDiffusion Model Quantization

    Tenstorrent · EPFL

  5. Joint Branch-Space Transform Coding for Diffusion Activation Quantization with Classifier-Free Guidance

    Oct 1, 2026Mingrun Jiang, Yuejia Liu, Zishan Shao +11Classifier-Free GuidanceDiffusion Model Quantization

    Duke University · Carnegie Mellon University · University of Florida +2

  6. JustQuant: You Don't Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantization

    Sep 27, 2026Kaicheng Yang, Kaisen Yang, Chunyu Liu +8Neural Network QuantizationDiffusion Model Quantization

    Shanghai Jiao Tong University · Tsinghua University · The Hong Kong Polytechnic University

  7. Chameleon: Dynamic Format Adapter for Efficient Diffusion

    Sep 27, 2026Arnab Sanyal, Sandeep ChinchaliDiffusion Model QuantizationPost-Training Quantization

    UT SWARM Lab, Department of Electrical & Computer Engineering The University of Texas, Austin TX 78712

  8. PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers

    Sep 27, 2026Yutong Wang, Xingtong Ge, Enhuai Liu +4Video Diffusion ModelsDiffusion Transformer

    The University of Sydney · The Hong Kong University of Science and Technology · The Chinese University of Hong Kong +1

  9. Quantization-Aware Kalman Estimation for Diffusion Sampling

    Sep 18, 2026Qitan Shi, Cheng Jin, Jiawei Zhang +1Diffusion Model QuantizationDiffusion Sampling

    Tsinghua University

  10. DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation

    Sep 3, 2026Shuaiting Li, Zelin Gao, Haibin Shen +3Diffusion Model GuidanceVideo Diffusion Models

    1Robbyant · 2ZJU · 4HKUST +1

  11. Post-training Quantization for Hybrid Iterative Generative Models

    Aug 14, 2026Jing Gao, Junyi Wu, Wei Wang +2Post-Training QuantizationNeural Network Quantization

    Institute of Information Science, Beijing Jiaotong University, Beijing, China · University of Illinois Chicago, Chicago, IL, USA

  12. TTS-Q: Speaker-Aware Post-Training Quantization of Text-to-Speech Diffusion Transformers

    Aug 11, 2026Xiaoqin Feng, Yuqi Li, Weilun Feng +9Diffusion Model QuantizationPost-Training Quantization

    Wyze Inc., USA · The City College of New York, City University of New York, USA · Institute of Computing Technology, Chinese Academy of Sciences, China +2

  13. TASQ: Temporal-Adaptive Bit Sparsification Quantization for Diffusion Models

    Aug 4, 2026Seokho Han, Dongwei Wang, Jinhee Kim +4Weight-Only QuantizationMixed-Precision Quantization

    Department of Electrical and Computer Engineering, Sungkyunkwan University, Korea · Department of Electrical and Computer Engineering, University of Arizona, USA · Department of Electrical and Computer Engineering, Duke University, USA +1

  14. MXAttention: Data-Free Optimal Scaling and Pre-Normalization Quantization for MXFP4 Attention

    Jul 27, 2026Jianlin Yu, Jing Lin, Linghui Kong +13Video Diffusion ModelsDiffusion Model Quantization

    Huawei Technologies Co., Ltd.

  15. KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers

    Jul 23, 2026Yann Bouquet, Alireza Khodamoradi, Kristof Denolf +1Diffusion TransformerDiffusion Model Quantization

    EPFL, Lausanne, Switzerland. · Advanced Micro Devices, Inc., Longmont, CO, USA.

  16. Closing the Null Space: Guidance-Aware Quantization for Classifier-Free Diffusion

    Jul 9, 2026Abdullah Al Shafi, Sumaiya Rahim SumaMixed-Precision QuantizationClassifier-Free Guidance

    Department of Computer Science and Engineering Khulna University of Engineering & Technology Khulna-9203, Bangladesh

  17. FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models

    Jul 7, 2026Bowen Xue, Zihan Min, Xingyang Li +8Diffusion Model QuantizationQuantization-Aware Training

    Nunchux AI · MIT · Stanford +2

  18. OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers

    Jul 2, 2026Donghyun Lee, Jitesh Chavan, Duy Nguyen +5Video Diffusion ModelsDiffusion Transformer

    Cantina Labs · University of Southern California · *Work done during an internship at Cantina Labs. +1

  19. W4A4 Quantization for Inference on Wan2.2-I2V-A14B

    Jun 28, 2026Yidong Chen, Chengyu Shi, Jiahao LiuDiffusion Model QuantizationPost-Training Quantization

    Tsinghua University

  20. HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models

    Jun 22, 2026Yuval Domb, Hadar Sackstein, Tomer SolbergLLM QuantizationDiffusion Model Quantization

  21. Realizing Native INT8 Compute for Diffusion Transformers on Consumer GPUs: A Fused INT8 GEMM Kernel for Ideogram 4.0

    Jun 12, 2026Ali Asaria, Tony Salomone, Deep GandhiGPU Kernel OptimizationDiffusion Transformer

    Transformer Lab

  22. Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs

    Jun 10, 2026Deep Gandhi, Ali Asaria, Tony SalomoneMixed-Precision QuantizationDiffusion Transformer

    Transformer Lab

  23. FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models

    Jun 4, 2026Haoyu Huang, Linlin Yang, Sheng Xu +5LLM QuantizationDiffusion Model Quantization

    National College for Excellent Engineers, Beihang University, Beijing, China · State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China · Independent researcher +4

  24. STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models

    Jun 3, 2026Xin Yan, Aqiang Wang, Zhenglin Wan +2LLM QuantizationDiffusion Model Quantization

    School of Artificial Intelligence, Beijing Normal University, Beijing, China · Department of Computer Science, National University of Singapore, Singapore · Centre for Frontier AI Research, Agency for Science, Technology and Research (A*STAR), Singapore

  25. Boundary-Protection W8A8 HiFloat8 Quantization for Large-Scale Text-to-Video Diffusion Transformers

    May 31, 2026Yiming ZhaoVideo Diffusion ModelsDiffusion Model Quantization

    University of Chinese Academy of Sciences Beijing, China

  26. Collaborative Few-Step Distillation and Low-Bit Quantization for Wan2.2 Dual-Expert Video Diffusion Models

    May 30, 2026Jinyang Du, Shenghao Jin, Ziqian Xu +5Video Diffusion ModelsDiffusion Model Quantization

    SenseTime

  27. Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V

    May 26, 2026Junhao Wu, Dezhong Yao, Hai JinVideo Diffusion ModelsDiffusion Transformer

    School of Computer Science and Technology, Huazhong University of Science and Technology Wuhan, Hubei, China 430074

  28. Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion

    May 25, 2026Tuna Tuncer, Felix Becker, Thomas PfeilVideo Diffusion ModelsSelf-Attention

    1Technical University of Munich · 2Tensordyne

  29. Q-ARVD: Quantizing Autoregressive Video Diffusion Models

    May 20, 2026Siao Tang, Xinyin Ma, Gongfan Fang +2Video Diffusion ModelsDiffusion Model Quantization

    National University of Singapore · The Hong Kong Polytechnic University

  30. DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers

    May 16, 2026Sayeh Sharify, Mahsa Salmani, Hesham MostafaDiffusion TransformerDiffusion Model Quantization

    d-Matrix Santa Clara, CA 95054