Imagen Video

GPTKB entity

Statements (33)
Predicate Object
gptkbp:instanceOf text-to-video model
gptkbp:announced 2022
gptkbp:arXivID 2210.02303
gptkbp:author gptkb:William_Chan
gptkb:Chitwan_Saharia
gptkb:Jay_Whang
gptkb:Mohammad_Norouzi
gptkb:Sergio_Guadarrama
gptkb:Andrea_Tagliasacchi
gptkb:Jonathan_Ho
gptkb:Tim_Salimans
gptkb:Ben_Poole
Ruoming Pang
David J. Fleet
Tomas Pfister
gptkbp:basedOn diffusion model
gptkbp:developedBy gptkb:Google_Research
https://www.w3.org/2000/01/rdf-schema#label Imagen Video
gptkbp:input text prompt
gptkbp:language English
gptkbp:maxDuration 5.3 seconds
gptkbp:notableFor high-quality text-to-video synthesis
gptkbp:notablePublication Imagen Video: High Definition Video Generation with Diffusion Models
gptkbp:output gptkb:DVD
gptkbp:refreshRate 24 fps
gptkbp:relatedTo gptkb:Phenaki
gptkb:Imagen
gptkbp:resolution 1280x768
gptkbp:status research prototype
gptkbp:uses cascade of video diffusion models
gptkbp:website https://imagen.research.google/video/
gptkbp:bfsParent gptkb:Make-A-Video
gptkbp:bfsLayer 6