paper-with-me

홈 › Papers

Real-Time Video Generation with Pyramid Attention Broadcast

2024-08-22 · Xuanlei Zhao, Xiaolong Jin, Kai Wang, Yang You

We present Pyramid Attention Broadcast (PAB), a real-time, high quality and training-free approach for DiT-based video generation. Our method is founded on the observation that attention difference in the diffusion process exhibits a U-shaped pattern, indicating significant redundancy. We mitigate this by broadcasting attention outputs to subsequent steps in a pyramid style. It applies different broadcast strategies to each attention based on their variance for best efficiency. We further introduce broadcast sequence parallel for more efficient distributed inference. PAB demonstrates up to 10.5x speedup across three models compared to baselines, achieving real-time generation for up to 720p videos. We anticipate that our simple yet effective method will serve as a robust baseline and facilitate future research and application for video generation.

📄 PDF Abstract BibTeX arXiv:2408.12588

Code (1)

NUS-HPC-AI-Lab/VideoSys 공식 구현 pytorch

Tasks

Video Generation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation

2026-05-13 · Jiayu Chen, Junbei Tang, Wenbiao Zhao, Maoliang Li 외 arxiv

Autoregressive video generation enables streaming and open-ended long video synthesis, but still suffers from long-term degradation caused by accumulated errors. Existing KVCache strategies usually apply unified historic…

Video Generation

UniVid: Pyramid Diffusion Model for High Quality Video Generation

2026-03-14 · Xinyu Xiao, Binbin Yang, Tingtian Li, Yipeng Yu 외 arxiv

Diffusion-based text-to-video generation (T2V) or image-to-video (I2V) generation have emerged as a prominent research focus. However, there exists a challenge in integrating the two generative paradigms into a unified m…

Text-to-Video Generation

MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing

2021-11-24 · Jiashuo Yu, Ying Cheng, Rui-Wei Zhao, Rui Feng 외

Recognizing and localizing events in videos is a fundamental task for video understanding. Since events may occur in auditory and visual modalities, multimodal detailed perception is essential for complete scene comprehe…

audio-visual event localizationVideo Understanding

PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation

2025-12-03 · Xiaolong Li, Youping Gu, Xi Lin, Weijie Wang 외 arxiv

Attention mechanisms are the core of foundation models, but their quadratic complexity remains a critical bottleneck for scaling. This challenge has driven the development of efficient attention mechanisms, with sparsity…

Computational Efficiency

Visualizing the Passage of Time with Video Temporal Pyramids

2022-08-25 · Melissa E. Swift, Wyatt Ayers, Sophie Pallanck, Scott Wehrwein

What can we learn about a scene by watching it for months or years? A video recorded over a long timespan will depict interesting phenomena at multiple timescales, but identifying and viewing them presents a challenge. T…