Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387156659> ?p ?o ?g. }
- W4387156659 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." @default.
- W4387156659 created "2023-09-30" @default.
- W4387156659 creator A5005626854 @default.
- W4387156659 creator A5006394426 @default.
- W4387156659 creator A5010087030 @default.
- W4387156659 creator A5023000066 @default.
- W4387156659 creator A5023785888 @default.
- W4387156659 creator A5025976462 @default.
- W4387156659 creator A5026280700 @default.
- W4387156659 creator A5032015275 @default.
- W4387156659 creator A5035480324 @default.
- W4387156659 creator A5052798964 @default.
- W4387156659 creator A5055183049 @default.
- W4387156659 creator A5061091490 @default.
- W4387156659 creator A5061935529 @default.
- W4387156659 creator A5063212137 @default.
- W4387156659 creator A5070296642 @default.
- W4387156659 creator A5072508861 @default.
- W4387156659 creator A5072861783 @default.
- W4387156659 creator A5076720384 @default.
- W4387156659 creator A5086484914 @default.
- W4387156659 creator A5090351350 @default.
- W4387156659 date "2023-09-26" @default.
- W4387156659 modified "2023-09-30" @default.
- W4387156659 title "LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models" @default.
- W4387156659 doi "https://doi.org/10.48550/arxiv.2309.15103" @default.
- W4387156659 hasPublicationYear "2023" @default.
- W4387156659 type Work @default.
- W4387156659 citedByCount "0" @default.
- W4387156659 crossrefType "posted-content" @default.
- W4387156659 hasAuthorship W4387156659A5005626854 @default.
- W4387156659 hasAuthorship W4387156659A5006394426 @default.
- W4387156659 hasAuthorship W4387156659A5010087030 @default.
- W4387156659 hasAuthorship W4387156659A5023000066 @default.
- W4387156659 hasAuthorship W4387156659A5023785888 @default.
- W4387156659 hasAuthorship W4387156659A5025976462 @default.
- W4387156659 hasAuthorship W4387156659A5026280700 @default.
- W4387156659 hasAuthorship W4387156659A5032015275 @default.
- W4387156659 hasAuthorship W4387156659A5035480324 @default.
- W4387156659 hasAuthorship W4387156659A5052798964 @default.
- W4387156659 hasAuthorship W4387156659A5055183049 @default.
- W4387156659 hasAuthorship W4387156659A5061091490 @default.
- W4387156659 hasAuthorship W4387156659A5061935529 @default.
- W4387156659 hasAuthorship W4387156659A5063212137 @default.
- W4387156659 hasAuthorship W4387156659A5070296642 @default.
- W4387156659 hasAuthorship W4387156659A5072508861 @default.
- W4387156659 hasAuthorship W4387156659A5072861783 @default.
- W4387156659 hasAuthorship W4387156659A5076720384 @default.
- W4387156659 hasAuthorship W4387156659A5086484914 @default.
- W4387156659 hasAuthorship W4387156659A5090351350 @default.
- W4387156659 hasBestOaLocation W43871566591 @default.
- W4387156659 hasConcept C103910844 @default.
- W4387156659 hasConcept C111472728 @default.
- W4387156659 hasConcept C111919701 @default.
- W4387156659 hasConcept C11413529 @default.
- W4387156659 hasConcept C138885662 @default.
- W4387156659 hasConcept C147297375 @default.
- W4387156659 hasConcept C154945302 @default.
- W4387156659 hasConcept C162324750 @default.
- W4387156659 hasConcept C167966045 @default.
- W4387156659 hasConcept C176217482 @default.
- W4387156659 hasConcept C21547014 @default.
- W4387156659 hasConcept C26517878 @default.
- W4387156659 hasConcept C2779530757 @default.
- W4387156659 hasConcept C31972630 @default.
- W4387156659 hasConcept C38652104 @default.
- W4387156659 hasConcept C39890363 @default.
- W4387156659 hasConcept C41008148 @default.
- W4387156659 hasConcept C65483669 @default.
- W4387156659 hasConcept C98045186 @default.
- W4387156659 hasConceptScore W4387156659C103910844 @default.
- W4387156659 hasConceptScore W4387156659C111472728 @default.
- W4387156659 hasConceptScore W4387156659C111919701 @default.
- W4387156659 hasConceptScore W4387156659C11413529 @default.
- W4387156659 hasConceptScore W4387156659C138885662 @default.
- W4387156659 hasConceptScore W4387156659C147297375 @default.
- W4387156659 hasConceptScore W4387156659C154945302 @default.
- W4387156659 hasConceptScore W4387156659C162324750 @default.
- W4387156659 hasConceptScore W4387156659C167966045 @default.
- W4387156659 hasConceptScore W4387156659C176217482 @default.
- W4387156659 hasConceptScore W4387156659C21547014 @default.
- W4387156659 hasConceptScore W4387156659C26517878 @default.
- W4387156659 hasConceptScore W4387156659C2779530757 @default.
- W4387156659 hasConceptScore W4387156659C31972630 @default.
- W4387156659 hasConceptScore W4387156659C38652104 @default.
- W4387156659 hasConceptScore W4387156659C39890363 @default.
- W4387156659 hasConceptScore W4387156659C41008148 @default.
- W4387156659 hasConceptScore W4387156659C65483669 @default.
- W4387156659 hasConceptScore W4387156659C98045186 @default.
- W4387156659 hasLocation W43871566591 @default.
- W4387156659 hasOpenAccess W4387156659 @default.
- W4387156659 hasPrimaryLocation W43871566591 @default.
- W4387156659 hasRelatedWork W2038316300 @default.
- W4387156659 hasRelatedWork W2059612401 @default.
- W4387156659 hasRelatedWork W2068162367 @default.
- W4387156659 hasRelatedWork W2111667101 @default.
- W4387156659 hasRelatedWork W2348820921 @default.
- W4387156659 hasRelatedWork W2415044327 @default.
- W4387156659 hasRelatedWork W2574246024 @default.
- W4387156659 hasRelatedWork W2789578481 @default.