English
Related papers

Related papers: HASTE: Training-Free Video Diffusion Acceleration …

200 papers

We explore the role of attention mechanism during inference in text-conditional diffusion models. Empirical observations suggest that cross-attention outputs converge to a fixed point after several inference steps. The convergence time…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Haozhe Liu , Wentian Zhang , Jinheng Xie , Francesco Faccio , Mengmeng Xu , Tao Xiang , Mike Zheng Shou , Juan-Manuel Perez-Rua , Jürgen Schmidhuber

This paper introduces EasyAnimate, an efficient and high quality video generation framework that leverages diffusion transformers to achieve high-quality video production, encompassing data processing, model training, and end-to-end…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Jiaqi Xu , Kunzhe Huang , Xinyi Zou , Yunkuo Chen , Bo Liu , MengLi Cheng , Jun Huang , Xing Shi

Video generation models have demonstrated remarkable performance, yet their broader adoption remains constrained by slow inference speeds and substantial computational costs, primarily due to the iterative nature of the denoising process.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Xin Zhou , Dingkang Liang , Kaijin Chen , Tianrui Feng , Xiwu Chen , Hongkai Lin , Yikang Ding , Feiyang Tan , Hengshuang Zhao , Xiang Bai

Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling. Existing training-free accelerators - step reduction, feature caching, and sparse attention - enhance inference speed but typically rely on a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Wangbo Zhao , Yizeng Han , Zhiwei Tang , Jiasheng Tang , Pengfei Zhou , Kai Wang , Bohan Zhuang , Zhangyang Wang , Fan Wang , Yang You

State-of-the-art super-resolution (SR) algorithms require significant computational resources to achieve real-time throughput (e.g., 60Mpixels/s for HD video). This paper introduces FAST (Free Adaptive Super-resolution via Transfer), a…

Computer Vision and Pattern Recognition · Computer Science 2017-08-18 Zhengdong Zhang , Vivienne Sze

Leveraging the natural spatiotemporal energy decay in video diffusion offers a path to efficiency, yet relying solely on rigid static masks risks losing critical long-range information in complex dynamics. To address this issue, we propose…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Yongji Long , Shijun Liang , Jintao Li , Yun Li

Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sampling. Recent methods reduce cost by compressing width, depth, or sampling steps, but…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Yutong Wang , Yunke Wang , Tianfan Xue , Yu Qiao , Yaohui Wang , Xinyuan Chen , Chang Xu

The scalability of high-fidelity video diffusion models (VDMs) is constrained by two key sources of redundancy: the quadratic complexity of global spatio-temporal attention and the computational overhead of long iterative denoising…

Computer Vision and Pattern Recognition · Computer Science 2025-12-08 Xinjian Wu , Hongmei Wang , Yuan Zhou , Qinglin Lu

Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover that attention heads in AR video diffusion transformers serve functionally distinct roles…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jiahao Tian , Yiwei Wang , Gang Yu , Chi Zhang

Video diffusion transformers (DiTs) suffer from prohibitive inference latency due to quadratic attention complexity. Existing sparse attention methods either overlook semantic similarity or fail to adapt to heterogeneous token distributions…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Haoyue Tan , Shengnan Wang , Yulin Qiao , Juncheng Zhang , Youhui Bai , Ping Gong , Zewen Jin , Cheng Li

Diffusion Transformers (DiTs) with 3D full attention power state-of-the-art video generation, but suffer from prohibitive compute cost -- when generating just a 5-second 720P video, attention alone takes 800 out of 945 seconds of total…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Peiyuan Zhang , Yongqi Chen , Runlong Su , Hangliang Ding , Ion Stoica , Zhengzhong Liu , Hao Zhang

Diffusion Transformers (DiTs) have become a leading backbone for video generation, yet their quadratic attention cost remains a major bottleneck. Sparse attention reduces this cost by computing only a subset of attention blocks. However,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Xuanyi Zhou , Qiuyang Mang , Shuo Yang , Haocheng Xi , Jintao Zhang , Huanzhi Mao , Joseph E. Gonzalez , Kurt Keutzer , Ion Stoica , Alvin Cheung

Text-to-image generation models, especially Multimodal Diffusion Transformers (MMDiT), have shown remarkable progress in generating high-quality images. However, these models often face significant computational bottlenecks, particularly in…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Hanling Zhang , Rundong Su , Zhihang Yuan , Pengtao Chen , Mingzhu Shen Yibo Fan , Shengen Yan , Guohao Dai , Yu Wang

Video understanding in multimodal language models remains limited by context length: models often miss key transition frames and struggle to maintain coherence across long time scales. To address this, we adapt Native Sparse Attention (NSA)…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Enxin Song , Wenhao Chai , Shusheng Yang , Ethan Armand , Xiaojun Shan , Haiyang Xu , Jianwen Xie , Zhuowen Tu

Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 David Junhao Zhang , Mutian Xu , Chuhui Xue , Wenqing Zhang , Xiaoguang Han , Song Bai , Mike Zheng Shou

Recently, Diffusion Transformers (DiTs) have emerged as a dominant architecture in video generation, surpassing U-Net-based models in terms of performance. However, the enhanced capabilities of DiTs come with significant drawbacks,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Junyi Wu , Zhiteng Li , Zheng Hui , Yulun Zhang , Linghe Kong , Xiaokang Yang

While diffusion language models (DLMs) offer a promising alternative to autoregressive models (ARs), existing open-source DLMs suffer from high inference latency. This bottleneck is mainly due to the attention's quadratic complexity with…

Computation and Language · Computer Science 2025-09-30 Zeqing Wang , Gongfan Fang , Xinyin Ma , Xingyi Yang , Xinchao Wang

Diffusion Transformers (DiTs) have achieved state-of-the-art performance in generative modeling, yet their high computational cost hinders real-time deployment. While feature caching offers a promising training-free acceleration solution by…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Fanpu Cao , Yaofo Chen , Zeng You , Wei Luo

Diffusion Transformer(DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency challenges. In this paper, we exploit the inherent temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Zhihang Yuan , Rui Xie , Yuzhang Shang , Hanling Zhang , Siyuan Wang , Shengen Yan , Guohao Dai , Yu Wang

Generating realistic videos with diffusion transformers demands significant computation, with attention layers the central bottleneck; even producing a short clip requires running a transformer over a very long sequence of embeddings, e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Sankeerth Durvasula , Kavya Sreedhar , Zain Moustafa , Suraj Kothawade , Ashish Gondimalla , Suvinay Subramanian , Narges Shahidi , Nandita Vijaykumar