Diffusion Model Inference Acceleration

Ask about this topic

Overview

Diffusion models repeatedly denoise a sample, so inference acceleration studies how to reduce the cost of those steps for image, video, language, and action generation. Methods reduce the number of evaluations with faster solvers, timestep schedules, and few-step distillation, or reduce work within each step using caching, sparse attention, token pruning, compression, and lower-precision computation. Systems work also targets memory movement, GPU parallelism, and serving, while adaptive methods allocate computation according to uncertainty, content, or task difficulty. The central challenge is preserving fidelity, diversity, and task accuracy as skipped or approximated computations can accumulate errors; gains therefore depend on the model, workload, hardware, and end-to-end evaluation.

Latest papers

CardsList

509 papers73 papers in the last four weeks, up 66% on the four weeks before. 0.4% of all new papers.

  1. FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion

    Feb 5, 2026Zhuokun Chen, Jianfei Cai, Bohan ZhuangVideo Diffusion ModelsSelf-Attention

    1Monash University · 2Zhejiang University

  2. PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

    Feb 1, 2026Haopeng Li, Shitong Shao, Wenliang Zhong +4Diffusion Model Inference AccelerationAttention Approximation

    The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology

  3. Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Caching

    Jan 28, 2026Fengrui Zuo, Zhiwei Ke, Yiming Liu +3Diffusion Language Model InferenceToken Pruning

    School of Computer Science and Technology, University of Science and Technology of China · Suzhou Institute of Advanced Research, University of Science and Technology of China

  4. ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule

    Jan 26, 2026Yilie Huang, Wenpin Tang, Xunyu ZhouDiffusion SamplingAdaptive Sampling

    Department of Industrial Engineering and Operations Research, Columbia University, New York, NY 10027, USA. · Department of Industrial Engineering and Operations Research & Data Science Institute, Columbia University, New York, NY 10027, USA.

  5. Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding

    Jan 25, 2026Zhongyu Xiao, Zhiwei Hao, Jianyuan Guo +4Adaptive InferenceBlockwise Diffusion Language Models

    School of information and Electronics, Beijing Institute of Technology, Beijing · Department of Computer Science, City University of Hong Kong, Hong Kong · School of Computer Science, Wuhan University, Wuhan +2

  6. Turbo4DGen: Ultra-Fast Acceleration for 4D Generation

    Jan 24, 2026Yuanbin Man, Ying Huang, Zhile Ren +14D Scene GenerationDiffusion Model Inference Acceleration

    Department of Computer Science Engineering, University of Texas at Arlington, TX, USA · Independent Researcher, CA, USA

  7. A Gaussian Perspective for Distributional Discrepancy in Generative Diffusion Models

    Jan 20, 2026Qiang Sun, H. Vincent Poor, Wenyi ZhangDiffusion SamplingKullback-Leibler Divergence

    Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China · Department of Electrical Engineering, Princeton University, Princeton, NJ, USA

  8. Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers

    Jan 14, 2026Yuxi Liu, Yipeng Hu, Zekun Zhang +2Video Diffusion ModelsDiffusion Transformer

    Peking University · University of Electronic Science and Technology of China · University of Science and Technology of China

  9. SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

    Jan 13, 2026Dongting Hu, Aarush Gupta, Magzhan Gabidolla +12Diffusion TransformerDiffusion Model Distillation

    Snap Inc. · University of Melbourne · MBZUAI

  10. Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion

    Dec 29, 2025Hau-Shiang Shiu, Chin-Yang Lin, Zhixiang Wang +4Video Super-ResolutionDiffusion Model Inference Acceleration

    National Yang Ming Chiao Tung University · Shanda AI Research Tokyo · MediaTek Inc.

  11. ReDiF: Resource-Efficient Few-Step Diffusion Distillation via Reinforcement Learning

    Dec 28, 2025Amirhossein Tighkhorshid, Zahra Dehghanian, Hamid R. RabieeDiffusion DistillationRL for Diffusion Models

    Computer Engineering Sharif University of Technology

  12. Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models

    Dec 16, 2025Shufan Li, Jiuxiang Gu, Kangning Liu +4Masked Diffusion ModelsDiffusion Language Model Inference

    Adobe · UCLA

  13. Early Estimation of Language to Latent Alignment in Diffusion Models

    Dec 9, 2025Vasco Ramos, Regev Cohen, Idan Szpektor +1Diffusion Model AlignmentVision-Language Alignment

    NOVALINCS, NOVA University of Lisbon, Portugal · Google Research

  14. Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

    Nov 27, 2025Z-Image Team, Huanqia Cai, Sihan Cao +21Diffusion TransformerDiffusion Model Inference Acceleration

    Z-Image Team, Alibaba Group

  15. Sphinx: Efficiently Serving Novel View Synthesis using Regression-Guided Selective Refinement

    Nov 24, 2025Yuchen Xia, Souvik Kundu, Mosharaf Chowdhury +1Novel View SynthesisDiffusion Model Serving

    University of Illinois Urbana-Champaign, Illinois, USA · Intel AI Group, USA · University of Michigan, Michigan, USA

  16. DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing

    Nov 21, 2025Hao Chen, Renzheng Zhang, Scott S. HowardDiffusion Models for Image RestorationBayesian Inverse Problems

    University of Notre Dame, Notre Dame, IN 46556, USA

  17. InstantViR: Real-Time Video Inverse Problem Solver with Distilled Diffusion Prior

    Nov 18, 2025Weimin Bai, Suzhe Xu, Yiwei Ren +4Diffusion-Based Inverse ProblemsVideo Diffusion Models

    Peking University · Huaqiao University · Kuaishou Technology

  18. UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention

    Oct 18, 2025Yuyao Zhang, Yu-Wing TaiImage GenerationDiffusion Model Inference Acceleration

    Dartmouth College, USA

  19. DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space

    Sep 29, 2025Wenkun He, Yuchao Gu, Junyu Chen +11Diffusion Model Fine-TuningDiffusion Model Inference Acceleration

  20. Enabling Approximate Joint Sampling in Diffusion LMs

    Sep 25, 2025Parikshit Bansal, Sujay SanghaviMasked Diffusion ModelsDiffusion Language Model Decoding

    UT Austin

  21. TinySR: Pruning Diffusion for Real-World Image Super-Resolution

    Aug 24, 2025Linwei Dong, Qingnan Fan, Yuhang Yu +4Diffusion Models for Image RestorationDiffusion Model Pruning

    Zhejiang University · Vivo Mobile Communication Co. Ltd · Zhejiang Lab

  22. Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter

    Aug 23, 2025Wen Ge, Lei Jiang, Lingyi Yang +7Path SignaturesDiffusion Model Distillation

    University College London · University of Oxford · JPMorganChase +1

  23. Double-Diffusion: Balancing Speed, Accuracy, and Uncertainty in Probabilistic Forecasting for Urban Sensor Networks

    Jun 29, 2025Hanlin Dong, Arian Prabowo, Hao Xue +4Spatiotemporal ForecastingDiffusion Model Inference Acceleration

    University of New South Wales Sydney, Australia · University of Maryland College Park, United States · The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China

  24. Stochastic and Non-local Closure Modeling for Nonlinear Dynamical Systems via Latent Score-based Generative Models

    Jun 25, 2025Xinghao Dong, Huchen Yang, Jin-Long WuDynamical SystemsLatent Diffusion Models

    Department of Mechanical Engineering, University of Wisconsin-Madison, Madison, WI, 53706, USA

  25. Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations

    Jun 25, 2025Shunqi Mao, Wei Guo, Chaoyi Zhang +3Diffusion SamplingConditional Diffusion Models

    School of Computer Science, The University of Sydney, Australia

  26. Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models

    Feb 12, 2025Khaled Kahouli, Winfried Ripken, Stefan Gugler +3Diffusion Model SamplingDiffusion Timestep Scheduling

    BIFOLD – Berlin Institute for the Foundations of Learning and Data · Machine Learning Group, Technische Universität Berlin · Google DeepMind +3

  27. DICE: Distilling Classifier-Free Guidance into Text Embeddings

    Feb 6, 2025Zhenyu Zhou, Defang Chen, Can Wang +2Diffusion Model AlignmentDiffusion Model Guidance

    Zhejiang University, State Key Laboratory of Blockchain and Data Security · University at Buffalo, State University of New York

  28. RDM: Recurrent Diffusion Model for Human Motion Generation

    Jun 11, 2024Mirgahney Mohamed, Harry Jake Cunningham, Riccardo Barbano +2Diffusion Models for Motion GenerationDiffusion Models

    Department of Computer Science, University College London

  29. Decoupled Data Consistency with Diffusion Purification for Image Restoration

    Mar 10, 2024Xiang Li, Soo Min Kwon, Shijun Liang +3Diffusion Models for Image RestorationDiffusion-Based Inverse Problems

    Department of Electrical Engineering and Computer Science, University of Michigan · Departments of Computational Mathematics, Science and Engineering, and Biomedical Engineering, Michigan State University