$Δ$ -DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers

3 June 2024

Peng Ye

Tao Chen

ArXiv (abs)PDF HTML HuggingFace (1 upvotes)

Papers citing "$Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers"

50 / 65 papers shown

Title
SplitFlux: Learning to Decouple Content and Style from a Single Image Yitong Yang Y Samuel Wang Changshuo Wang Yongjun Zhang Ziyang Chen Shuting He 16 0 0 19 Nov 2025
PipeDiT: Accelerating Diffusion Transformers in Video Generation with Task Pipelining and Model Decoupling S. Wang Qiang Wang Shaohuai Shi VGen 68 0 0 15 Nov 2025
TIMERIPPLE: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space Wenxuan Miao Yulin Sun Aiyue Chen Jing Lin Yiwu Yao Yiming Gan Jieru Zhao Jingwen Leng Mingyi Guo Yu Feng 56 0 0 15 Nov 2025
StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation Tianrui Feng Z. Li Shuo Yang Haocheng Xi Muyang Li ... S. Han Maneesh Agrawala Kurt Keutzer Akio Kodaira Chenfeng Xu VGen 44 0 0 10 Nov 2025
Test-Time Iterative Error Correction for Efficient Diffusion Models Yunshan Zhong Yanwei Qi Yuxin Zhang 48 0 0 09 Nov 2025
Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration Yunghee Lee Byeonghyun Pak Junwha Hong Hoseong Kim 132 0 0 06 Nov 2025
LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation Huanlin Gao Ping Chen Fuyuan Shi C. Tan Zhaoxiang Liu Fang Zhao Kai Wang Shiguo Lian DiffM VGen 72 0 0 30 Oct 2025
ETC: training-free diffusion models acceleration with Error-aware Trend Consistency Jiajian Xie Hubery Yin Chen Li Zhou Zhao Shengyu Zhang DiffM 128 0 0 28 Oct 2025
A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation Jiacheng Liu Xinyu Wang Yuqi Lin Zhikai Wang P. Wang ... Zexuan Yan Zhengyi Shi Chang Zou Yue Ma Linfeng Zhang 195 0 0 22 Oct 2025
FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching Jiacheng Liu Peiliang Cai Qinming Zhou Yuqi Lin Deyang Kong ... Haowen Xu Chang Zou J. Tang S. Zheng Linfeng Zhang 40 1 0 09 Oct 2025
Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generation Johanna Sommer John Rachwan Nils Fleischmann Stephan Günnemann Bertrand Charpentier 68 1 0 06 Oct 2025
Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers Shikang Zheng Guantao Chen Qinming Zhou Yuqi Lin Lixuan He Chang Zou Peiliang Cai Jiacheng Liu Linfeng Zhang 52 1 0 05 Oct 2025
FlashOmni: A Unified Sparse Attention Engine for Diffusion Transformers Liang Qiao Yue Dai Y. Huang Hongyu Kan Jun Shi Hong An 60 0 0 29 Sep 2025
RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer Wangbo Zhao Yizeng Han Zhiwei Tang Jiasheng Tang Pengfei Zhou Kai Wang Bohan Zhuang Zinan Lin Fan Wang Yang You 96 1 0 26 Sep 2025
Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation Yue Ma Zexuan Yan Hongyu Liu H. Wang Heng Pan ... H. Shum Zhifeng Li Wei Liu Linfeng Zhang Qifeng Chen VGen 135 3 0 20 Sep 2025
BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching Hanshuai Cui Zhiqing Tang Zhifei Xu Zhi Yao Wenyi Zeng Weijia Jia VGen 154 0 0 17 Sep 2025
SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching Jiacheng Liu Chang Zou Yuanhuiyi Lyu Fei Ren Shaobo Wang Kaixin Li Linfeng Zhang DiffM 136 3 0 15 Sep 2025
Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching Zhixin Zheng Xinyu Wang Chang Zou Shaobo Wang Linfeng Zhang 28 2 0 12 Sep 2025
SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling Fanjiang Ye Zepeng Zhao Yi Mu Jucheng Shen Renjie Li ... Aditya Akella Arvind Krishnamurthy T.S. Eugene Ng Zhengzhong Tu Y. X. R. Wang DiffM VGen 63 0 0 25 Aug 2025
DiCache: Let Diffusion Model Determine Its Own Cache Jiazi Bu Pengyang Ling Yujie Zhou Yibin Wang Yuhang Zang Tong Wu Dahua Lin DiffM 179 3 0 24 Aug 2025
OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models Huanpeng Chu Wei Wu Guanyu Fen Yutao Zhang DiffM 124 381 0 22 Aug 2025
MixCache: Mixture-of-Cache for Video Diffusion Transformer Acceleration Yuanxin Wei Lansong Diao B. Chen Shenggan Cheng Zhengping Qian Wenyuan Yu Nong Xiao W. Lin Jiangsu Du DiffM VGen 57 0 0 18 Aug 2025
A Survey on Diffusion Language Models Tianyi Li Mingda Chen Bowei Guo Zhiqiang Shen 128 22 0 14 Aug 2025
LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation Wenhui Song Hanhui Li Jiehui Huang Panwen Hu Yuhao Cheng Long Chen Yiqiang Yan Xiaodan Liang DiffM VGen 54 1 0 11 Aug 2025
HierarchicalPrune: Position-Aware Compression for Large-Scale Diffusion Models Young D. Kwon Rui Li Sijia Li Da Li S. Bhattacharya Stylianos I. Venieris VLM 73 2 0 06 Aug 2025
Forecasting When to Forecast: Accelerating Diffusion Models with Confidence-Gated TaylorKnowledge-Based Systems (KBS), 2025 Xiaoliu Guan Lielin Jiang Hanqi Chen X. Zhang Jiaxing Yan Guanzhong Wang Yi-Hsueh Liu Zetao Zhang Yu Wu 156 1 0 04 Aug 2025
Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers Wongi Jeong Kyungryeol Lee H. Seo Se Young Chun 130 2 0 11 Jul 2025
Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Model Anirud Aggarwal Abhinav Shrivastava M. Gwilliam 292 0 0 18 Jun 2025
Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation Bowen Zheng Tianming Yang VLM 179 2 0 11 Jun 2025
MagCache: Fast Video Generation with Magnitude-Aware Cache Zehong Ma Longhui Wei Feng Wang Shiliang Zhang Q. Tian 157 6 0 10 Jun 2025
Astraea: A Token-wise Acceleration Framework for Video Diffusion Transformers Haosong Liu Yuge Cheng Zihan Liu Aiyue Chen Aiyue Chen ... Yiwu Yao Chen Chen Jingwen Leng Yu Feng Minyi Guo VGen 411 0 0 05 Jun 2025
Chipmunk: Training-Free Acceleration of Diffusion Transformers with Dynamic Column-Sparse Deltas Austin Silveria Soham V. Govande Daniel Y. Fu 146 2 0 03 Jun 2025
Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation Muhammad Adnan Nithesh Kurella Akhil Arunkumar Shiyang Chen DiffM VGen 198 1 0 31 May 2025
Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape Ruichen Chen Keith G. Mills Liyao Jiang Chao Gao Di Niu VGen 292 1 0 28 May 2025
One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion ModelsComputer Vision and Pattern Recognition (CVPR), 2025 S. Li Lei Wang Kai Wang Tao Liu J. Xie Joost van de Weijer Fahad Shahbaz Khan Shiqi Yang Yaxing Wang Zhiqiang Wang 174 4 0 28 May 2025
RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy Aiyue Chen Bin Dong Jingru Li Aiyue Chen Kun Tian Jing Lin Gongyi Wang VGen 207 2 0 27 May 2025
Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning Yu Zhang Jialei Zhou Xinchen Li Tao Gui Zhongwei Wan Tianyu Wang Duoqian Miao Changwei Wang LongBing Cao DiffM 193 4 0 25 May 2025
dKV-Cache: The Cache for Diffusion Language Models Xinyin Ma Runpeng Yu Gongfan Fang Xinchao Wang DiffM 317 45 0 21 May 2025
Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT AccelerationComputer Vision and Pattern Recognition (CVPR), 2025 Haipeng Fang Sheng Tang Juan Cao Enshuo Zhang Fan Tang Tong-Yee Lee 197 2 0 16 May 2025
Aquarius: A Family of Industry-Level Video Generation Models for Marketing Scenarios Huafeng Shi Jianzhong Liang Rongchang Xie Xian Wu Cheng Chen Chang Liu VGen 197 0 0 14 May 2025
Accelerating Diffusion Transformer via Increment-Calibrated Caching with Channel-Aware Singular Value DecompositionComputer Vision and Pattern Recognition (CVPR), 2025 Zhiyuan Chen Keyi Li Yifan Jia Le Ye Yufei Ma DiffM 217 1 0 09 May 2025
Classic Video Denoising in a Machine Learning World: Robust, Fast, and ControllableComputer Vision and Pattern Recognition (CVPR), 2025 Xin Jin Simon Niklaus Zhoutong Zhang Zhihao Xia Chunle Guo Yuting Yang J. Chen Chongyi Li VGen 231 1 0 04 Apr 2025
DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers Hao Zhang R. Su Zhihang Yuan Pengtao Chen Mingzhu Shen Yibo Fan Shengen Yan Guohao Dai Yu Wang 223 8 0 28 Mar 2025
U-REPA: Aligning Diffusion U-Nets to ViTs Yuchuan Tian Hanting Chen Mengyu Zheng Yuchen Liang Chao Xu Yunhe Wang 206 5 0 24 Mar 2025
Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer Qingyu Shi Jianzong Wu Jinbin Bai Jing Zhang Lu Qi Xuelong Li Yunhai Tong 215 1 0 21 Mar 2025
FasterCache: Training-Free Video Diffusion Model Acceleration with High QualityInternational Conference on Learning Representations (ICLR), 2024 Zhengyao Lv Chenyang Si Junhao Song Zhenyu Yang Ping Luo Yu Qiao Kwan-Yee K. Wong VGen DiffM 310 36 0 13 Mar 2025
OminiControl2: Efficient Conditioning for Diffusion Transformers Zhenxiong Tan Qiaochu Xue Xingyi Yang Songhua Liu Xinchao Wang DiffM 187 18 0 11 Mar 2025
From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers Jiacheng Liu Chang Zou Yuanhuiyi Lyu Junjie Chen Linfeng Zhang DiffM 275 21 0 10 Mar 2025
FEB-Cache: Frequency-Guided Exposure Bias Reduction for Enhancing Diffusion Transformer Caching Zhen Zou Hu Yu 205 1 0 10 Mar 2025
Q&C: When Quantization Meets Cache in Efficient Image Generation Xin Ding Xiaochen Li Haotong Qin Zhibo Chen DiffM MQ 282 1 0 04 Mar 2025