English
Related papers

Related papers: Adaptive Hybrid Caching for Efficient Text-to-Vide…

200 papers

Diffusion models have proven to be highly effective in image and video generation; however, they encounter challenges in the correct composition of objects when generating images of varying sizes due to single-scale training data. Adapting…

Computer Vision and Pattern Recognition · Computer Science 2024-09-23 Lanqing Guo , Yingqing He , Haoxin Chen , Menghan Xia , Xiaodong Cun , Yufei Wang , Siyu Huang , Yong Zhang , Xintao Wang , Qifeng Chen , Ying Shan , Bihan Wen

Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT…

Diffusion Transformer (DiT) has exhibited impressive generation capabilities but faces great challenges due to its high computational complexity. To address this issue, various methods, notably feature caching, have been introduced.…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Zhen Zou , Feng Zhao

Diffusion Transformers have recently demonstrated unprecedented generative capabilities for various tasks. The encouraging results, however, come with the cost of slow inference, since each denoising step requires inference on a transformer…

Machine Learning · Computer Science 2024-11-19 Xinyin Ma , Gongfan Fang , Michael Bi Mi , Xinchao Wang

Diffusion Transformer (DiT) models have achieved unprecedented quality in image and video generation, yet their iterative sampling process remains computationally prohibitive. To accelerate inference, feature caching methods have emerged by…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Guantao Chen , Shikang Zheng , Yuqi Lin , Linfeng Zhang

Diffusion models have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. These models face two fundamental challenges: strict temporal dependencies…

Machine Learning · Computer Science 2025-09-16 Jiacheng Liu , Chang Zou , Yuanhuiyi Lyu , Fei Ren , Shaobo Wang , Kaixin Li , Linfeng Zhang

The increased model capacity of Diffusion Transformers (DiTs) and the demand for generating higher resolutions of images and videos have led to a significant rise in inference latency, impacting real-time performance adversely. While prior…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Xibo Sun , Jiarui Fang , Aoyu Li , Jinzhe Pan

Diffusion Transformers (DiT) have shown strong performance in video generation tasks, but their high computational cost makes them impractical for resource-constrained devices like smartphones, and practical on-device generation is even…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Yushu Wu , Yanyu Li , Anil Kag , Ivan Skorokhodov , Willi Menapace , Ke Ma , Arpit Sahni , Ju Hu , Aliaksandr Siarohin , Dhritiman Sagar , Yanzhi Wang , Sergey Tulyakov

We introduce TurboDiffusion, a video generation acceleration framework that can speed up end-to-end diffusion generation by 100-200x while maintaining video quality. TurboDiffusion mainly relies on several components for acceleration: (1)…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Jintao Zhang , Kaiwen Zheng , Kai Jiang , Haoxu Wang , Ion Stoica , Joseph E. Gonzalez , Jianfei Chen , Jun Zhu

We present LeMiCa, a training-free and efficient acceleration framework for diffusion-based video generation. While existing caching strategies primarily focus on reducing local heuristic errors, they often overlook the accumulation of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Huanlin Gao , Ping Chen , Fuyuan Shi , Chao Tan , Zhaoxiang Liu , Fang Zhao , Kai Wang , Shiguo Lian

Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Shikang Zheng , Jingkai Huang , Jiacheng Liu , Guantao Chen , Lixuan , Yuqi Lin , Peiliang Cai , Linfeng Zhang

Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial…

Computer Vision and Pattern Recognition · Computer Science 2022-06-24 Jonathan Ho , Tim Salimans , Alexey Gritsenko , William Chan , Mohammad Norouzi , David J. Fleet

Feature caching has emerged as an effective strategy to accelerate diffusion transformer (DiT) sampling through temporal feature reuse. It is a challenging problem since (1) Progressive error accumulation from cached blocks significantly…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Junxiang Qiu , Lin Liu , Shuo Wang , Jinda Lu , Kezhou Chen , Yanbin Hao

Text-to-video diffusion models deliver impressive results but remain slow because of the sequential denoising of 3D latents. Existing approaches to speed up inference either require expensive model retraining or use heuristic-based step…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Joel Mathew Cherian , Ashutosh Muralidhara Bharadwaj , Vima Gupta , Anand Padmanabha Iyer

High-resolution video generation, while crucial for digital media and film, is computationally bottlenecked by the quadratic complexity of diffusion models, making practical inference infeasible. To address this, we introduce HiStream, an…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Haonan Qiu , Shikun Liu , Zijian Zhou , Zhaochong An , Weiming Ren , Zhiheng Liu , Jonas Schult , Sen He , Shoufa Chen , Yuren Cong , Tao Xiang , Ziwei Liu , Juan-Manuel Perez-Rua

Current video generation models perform well at single-shot synthesis but struggle with multi-shot videos, facing critical challenges in maintaining character and background consistency across shots and flexibly generating videos of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Xiangyang Luo , Qingyu Li , Xiaokun Liu , Wenyu Qin , Miao Yang , Meng Wang , Pengfei Wan , Di Zhang , Kun Gai , Shao-Lun Huang

Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency is largely due to the fixed tokenization process, which uses…

Computer Vision and Pattern Recognition · Computer Science 2026-02-20 Dahye Kim , Deepti Ghadiyaram , Raghudeep Gadde

Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In this paper, we identify that a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Shai Yehezkel , Shahar Yadin , Noam Elata , Yaron Ostrovsky-Berman , Bahjat Kawar

Diffusion Transformers (DiT) have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. To solve this problem, feature caching has been proposed to accelerate…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Jiacheng Liu , Chang Zou , Yuanhuiyi Lyu , Junjie Chen , Linfeng Zhang

Diffusion Transformers (DiTs) achieve state-of-the-art results in text-to-image, text-to-video generation, and editing. However, their large model size and the quadratic cost of spatial-temporal attention over multiple denoising steps make…

Machine Learning · Computer Science 2025-09-24 Muhammad Adnan , Nithesh Kurella , Akhil Arunkumar , Prashant J. Nair