FlashVideo：一种用于文本到视频生成中快速推理的框架
FlashVideo: A Framework for Swift Inference in Text-to-Video Generation
AI总结：
本文提出FlashVideo框架，首次将RetNet架构应用于文本到视频生成，将推理时间复杂度从O(L^2)降至O(L)，并结合无冗余帧插值方法，使推理效率较传统自回归模型提升9.17倍。
摘要：
在不断发展的机器学习领域，基于自回归的transformer模型和扩散模型在视频生成方面取得了显著进展，以合成动态且逼真的场景而闻名。然而，这些模型通常面临推理时间过长的问题，即使生成如GIF等短视频片段也是如此。本文介绍了FlashVideo，一种专为快速文本到视频生成量身定制的新型框架。FlashVideo首次成功将RetNet架构应用于视频生成，为该领域带来了独特的方法。借助基于RetNet的架构，对于长度为L的序列，FlashVideo将推理的时间复杂度从O(L^2)降低到O(L)，显著加快了推理速度。此外，我们采用了一种无冗余的帧插值方法，提高了帧插值的效率。我们的综合实验表明，与传统基于自回归的transformer模型相比，FlashVideo实现了9.17倍的效率提升，其推理速度与基于BERT的transformer模型处于同一数量级。
英文摘要：
In the evolving field of machine learning, video generation has witnessed significant advancements with autoregressive-based transformer models and diffusion models, known for synthesizing dynamic and realistic scenes. However, these models often face challenges with prolonged inference times, even for generating short video clips such as GIFs. This paper introduces FlashVideo, a novel framework tailored for swift Text-to-Video generation. FlashVideo represents the first successful adaptation of the RetNet architecture for video generation, bringing a unique approach to the field. Leveraging the RetNet-based architecture, FlashVideo reduces the time complexity of inference from $\mathcal{O}(L^2)$ to $\mathcal{O}(L)$ for a sequence of length $L$, significantly accelerating inference speed. Additionally, we adopt a redundant-free frame interpolation method, enhancing the efficiency of frame interpolation. Our comprehensive experiments demonstrate that FlashVideo achieves a $\times9.17$ efficiency improvement over a traditional autoregressive-based transformer model, and its inference speed is of the same order of magnitude as that of BERT-based transformer models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
