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. Dual-Solver: A Generalized ODE Solver for Diffusion Models with Dual Prediction

    Mar 4, 2026Soochul Park, Yeon Ju LeeDiffusion Model Inference AccelerationFew-Step Diffusion Sampling

    SteAI · MODULABS · Korea University

  2. LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning

    Mar 4, 2026Yanzhe Hu, Yijie Jin, Pengfei Liu +2Parallel Decoding for Diffusion Language ModelsBlockwise Diffusion Language Models

    Shanghai Jiao Tong University · Huazhong University of Science and Technology

  3. TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration

    Mar 4, 2026Haowei Zhu, Tingxuan Huang, Xing Wang +7Diffusion Model AccelerationDiffusion Model Inference Acceleration

    Tsinghua University · ByteDance

  4. Accelerating Video Generation Inference with Sequential-Parallel 3D Positional Encoding Using a Global Time Index

    Mar 2, 2026Chao Yuan, Pan LiDiffusion Model Inference AccelerationAutoregressive Video Generation

  5. Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration

    Mar 2, 2026Jiaqi Han, Juntong Shi, Puheng Li +3Video Diffusion ModelsDiffusion-Based Image Generation

    Stanford University · ByteDance

  6. FAST-DIPS: Adjoint-Free Analytic Steps and Hard-Constrained Likelihood Correction for Diffusion-Prior Inverse Problems

    Mar 2, 2026Minwoo Kim, Seunghyeok Shin, Hongki LimDiffusion-Based Inverse ProblemsInverse Problems

    Department of Electrical and Computer Engineering, Inha University Incheon, 22212, South Korea

  7. Efficient Token-Level Policy Optimization for Masked Diffusion Models via Velocity Alignment

    Mar 2, 2026Chenxing Wei, Jiazhen Kang, Hong Wang +8RL for Diffusion ModelsPolicy Optimization

    Shenzhen University, China · Guangming Laboratory, China · ByteDance, China +5

  8. An Open-Source Modular Benchmark for Diffusion-Based Motion Planning in Closed-Loop Autonomous Driving

    Mar 1, 2026Yun Li, Simon Thompson, Yidu Zhang +2Diffusion-Based PlanningAutonomous Driving Planning

    Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan. · TIER IV, Inc., Tokyo, Japan.

  9. PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation

    Mar 1, 2026Jiangshan Wang, Kang Zhao, Jiayi Guo +5Efficient Video GenerationDiffusion Model Inference Acceleration

    MMLab, CUHK · Tsinghua University · Tongyi Lab, Alibaba

  10. Analyzing and Improving Fast Sampling of Text-to-Image Diffusion Models

    Feb 28, 2026Zhenyu Zhou, Defang Chen, Siwei Lyu +2Diffusion Model Inference AccelerationT2I Diffusion Models

    State Key Laboratory of Blockchain and Data Security, Zhejiang University · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security · University of California, Berkeley +1

  11. Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness

    Feb 28, 2026Yuyang Chen, Linqian Zeng, Yijin ZHou +2Diffusion Timestep SchedulingDiffusion Model Inference Acceleration

    Shanghai Jiaotong University · Tsinghua University

  12. Joint Geometric and Trajectory Consistency Learning for One-Step Real-World Super-Resolution

    Feb 27, 2026Chengyan Deng, Zhangquan Chen, Li Yu +3Image Super-ResolutionConsistency Models

    University of Electronic Science and Technology of China · Tsinghua University · Nanjing University

  13. SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

    Feb 27, 2026Yasaman Haghighi, Alexandre AlahiVideo Diffusion ModelsDiffusion Model Caching

    Ecole Polytechnique Fédérale de Lausanne (EPFL)

  14. Diffusion Probe: Generated Image Result Prediction Using CNN Probes

    Feb 27, 2026Benlei Cui, Bukun Huang, Zhizeng Ye +7T2I Diffusion ModelsDiffusion Models

    Yuvion Team, Alibaba Group · Laboratory for Statistical Monitoring and Intelligent Governance of Common Prosperity, School of Statistics and Data Science, Zhejiang Gongshang University · Southeast University +2

  15. Rejection Mixing: Fast Semantic Propagation of Mask Tokens for Efficient DLLM Inference

    Feb 26, 2026Yushi Ye, Feng Hong, Huangjie Zheng +4Diffusion Language Model InferenceDiffusion Language Model Decoding

    Cooperative Medianet Innovation Center, Shanghai Jiao Tong University · School of Artificial Intelligence, Shanghai Jiao Tong University

  16. Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache

    Feb 26, 2026Bowen Cui, Yuanbin Wang, Huajiang Xu +6Diffusion Model Inference AccelerationDiffusion Model Caching

    Alibaba Group

  17. Causal Motion Diffusion Models for Autoregressive Motion Generation

    Feb 26, 2026Qing Yu, Akihisa Watanabe, Kent FujiwaraHuman Motion GenerationDiffusion Models for Motion Generation

    LY Corporation · Waseda University

  18. Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling

    Feb 25, 2026Euisoo Jung, Byunghyun Kim, Hyunjin Kim +2Diffusion Model Inference AccelerationDiffusion Model Guidance

    School of Computing, KAIST

  19. LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration

    Feb 24, 2026Peiliang Cai, Jiacheng Liu, Haowen Xu +3Diffusion Model Inference AccelerationDiffusion Models

    Shanghai Jiao Tong University

  20. Relational Feature Caching for Accelerating Diffusion Transformers

    Feb 23, 2026Byunggwan Son, Jeimin Jeon, Jeongwoo Choi +1Diffusion Model CachingDiffusion Model Inference Acceleration

    Yonsei University · Korea Institute of Science and Technology (KIST)

  21. SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models

    Feb 22, 2026Jiwoo Chung, Sangeek Hyun, MinKyu Lee +5Diffusion Model CachingDiffusion Model Inference Acceleration

    Sungkyunkwan University · NAVER Cloud

  22. MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanations

    Feb 21, 2026Changlu Guo, Anders Nymark Christensen, Anders Bjorholm Dahl +1Counterfactual Image GenerationCounterfactual Explanations

    Technical University of Denmark, Denmark

  23. DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers

    Feb 19, 2026Dahye Kim, Deepti Ghadiyaram, Raghudeep GaddeDiffusion Model Inference AccelerationDiffusion-Based Image Generation

    Boston University · Amazon

  24. Fast and Scalable Analytical Diffusion

    Feb 18, 2026Xinyi Shang, Peng Sun, Jingyu Lin +1Diffusion ModelsDiffusion Model Inference Acceleration

    University College London · Mohamed bin Zayed University of Artificial Intelligence · Zhejiang University +2

  25. CHAI: CacHe Attention Inference for text2video

    Feb 18, 2026Joel Mathew Cherian, Ashutosh Muralidhara Bharadwaj, Vima Gupta +1T2V GenerationEfficient Video Generation

    Georgia Institute of Technology.

  26. B-DENSE: Branching For Dense Ensemble Network Supervision Efficiency

    Feb 17, 2026Cherish Puniani, Tushar Kumar, Arnav Bendre +2Diffusion Model DistillationDiffusion-Based Image Generation

    Indian Institute of Technology, Roorkee Roorkee, Uttarakhand, India

  27. SLA2: Sparse-Linear Attention with Learnable Routing and Quantization-aware Training

    Feb 13, 2026Jintao Zhang, Haoxu Wang, Kai Jiang +6Sparse AttentionDiffusion Model Inference Acceleration

    Tsinghua University · UC Berkeley

  28. Learn from Your Mistakes: Self-Correcting Masked Diffusion Models

    Feb 12, 2026Yair Schiff, Omer Belhasin, Roy Uziel +6Masked Diffusion ModelsDiffusion Language Model Decoding

    Cornell · NVIDIA

  29. General and Efficient Steering of Diffusion Models

    Feb 11, 2026Qingsong Wang, Mikhail Belkin, Yusu WangDiffusion Model GuidanceActivation Steering

    Halıcıoğlu Data Science Institute, University of California San Diego, La Jolla, CA, USA

  30. Stable Velocity: A Variance Perspective on Flow Matching

    Feb 5, 2026Donglin Yang, Yongxing Zhang, Xin Yu +5Flow MatchingImage Generation

    University of Hong Kong, Hong Kong · University of British Columbia, Canada · Vector Institute for AI, Toronto, Canada +2