LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models

IF 11.6 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE International Journal of Computer Vision Pub Date : 2024-12-23 DOI:10.1007/s11263-024-02295-1
Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, Yuwei Guo, Tianxing Wu, Chenyang Si, Yuming Jiang, Cunjian Chen, Chen Change Loy, Bo Dai, Dahua Lin, Yu Qiao, Ziwei Liu
{"title":"LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models","authors":"Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, Yuwei Guo, Tianxing Wu, Chenyang Si, Yuming Jiang, Cunjian Chen, Chen Change Loy, Bo Dai, Dahua Lin, Yu Qiao, Ziwei Liu","doi":"10.1007/s11263-024-02295-1","DOIUrl":null,"url":null,"abstract":"<p>This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously (a) accomplish the synthesis of visually realistic and temporally coherent videos while (b) preserving the strong creative generation nature of the pre-trained T2I model. To this end, we propose <b>LaVie</b>, an integrated video generation framework that operates on cascaded video latent diffusion models, comprising a base T2V model, a temporal interpolation model, and a video super-resolution model. Our key insights are two-fold: (1) We reveal that the incorporation of simple temporal self-attentions, coupled with rotary positional encoding, adequately captures the temporal correlations inherent in video data. (2) Additionally, we validate that the process of joint image-video fine-tuning plays a pivotal role in producing high-quality and creative outcomes. To enhance the performance of LaVie, we contribute a comprehensive and diverse video dataset named <b>Vimeo25M</b>, consisting of 25 million text-video pairs that prioritize quality, diversity, and aesthetic appeal. Extensive experiments demonstrate that LaVie achieves state-of-the-art performance both quantitatively and qualitatively. Furthermore, we showcase the versatility of pre-trained LaVie models in various long video generation and personalized video synthesis applications. Project page: https://github.com/Vchitect/LaVie/.</p>","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"20 1","pages":""},"PeriodicalIF":11.6000,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Computer Vision","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s11263-024-02295-1","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously (a) accomplish the synthesis of visually realistic and temporally coherent videos while (b) preserving the strong creative generation nature of the pre-trained T2I model. To this end, we propose LaVie, an integrated video generation framework that operates on cascaded video latent diffusion models, comprising a base T2V model, a temporal interpolation model, and a video super-resolution model. Our key insights are two-fold: (1) We reveal that the incorporation of simple temporal self-attentions, coupled with rotary positional encoding, adequately captures the temporal correlations inherent in video data. (2) Additionally, we validate that the process of joint image-video fine-tuning plays a pivotal role in producing high-quality and creative outcomes. To enhance the performance of LaVie, we contribute a comprehensive and diverse video dataset named Vimeo25M, consisting of 25 million text-video pairs that prioritize quality, diversity, and aesthetic appeal. Extensive experiments demonstrate that LaVie achieves state-of-the-art performance both quantitatively and qualitatively. Furthermore, we showcase the versatility of pre-trained LaVie models in various long video generation and personalized video synthesis applications. Project page: https://github.com/Vchitect/LaVie/.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
求助全文
约1分钟内获得全文 去求助
来源期刊
International Journal of Computer Vision
International Journal of Computer Vision 工程技术-计算机:人工智能
CiteScore
29.80
自引率
2.10%
发文量
163
审稿时长
6 months
期刊介绍: The International Journal of Computer Vision (IJCV) serves as a platform for sharing new research findings in the rapidly growing field of computer vision. It publishes 12 issues annually and presents high-quality, original contributions to the science and engineering of computer vision. The journal encompasses various types of articles to cater to different research outputs. Regular articles, which span up to 25 journal pages, focus on significant technical advancements that are of broad interest to the field. These articles showcase substantial progress in computer vision. Short articles, limited to 10 pages, offer a swift publication path for novel research outcomes. They provide a quicker means for sharing new findings with the computer vision community. Survey articles, comprising up to 30 pages, offer critical evaluations of the current state of the art in computer vision or offer tutorial presentations of relevant topics. These articles provide comprehensive and insightful overviews of specific subject areas. In addition to technical articles, the journal also includes book reviews, position papers, and editorials by prominent scientific figures. These contributions serve to complement the technical content and provide valuable perspectives. The journal encourages authors to include supplementary material online, such as images, video sequences, data sets, and software. This additional material enhances the understanding and reproducibility of the published research. Overall, the International Journal of Computer Vision is a comprehensive publication that caters to researchers in this rapidly growing field. It covers a range of article types, offers additional online resources, and facilitates the dissemination of impactful research.
期刊最新文献
SLIDE: A Unified Mesh and Texture Generation Framework with Enhanced Geometric Control and Multi-view Consistency LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models FusionBooster: A Unified Image Fusion Boosting Paradigm AutoStory: Generating Diverse Storytelling Images with Minimal Human Efforts Noise-Resistant Multimodal Transformer for Emotion Recognition
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1