VideoPoet

VideoPoet is a large language model developed by Google Research in 2023 for video making.^[1][2][3][4] It can be asked to animate still images.^[5] The model accepts text, images, and videos as inputs, with a program to add feature for any input to any format generated content.^[4] VideoPoet was publicly announced on December 19, 2023.^[1] It uses an autoregressive language model.

VideoPoet
"A dog eating popcorn at the cinema" "A teddy bear with a cap, sunglasses, and leather jacket playing drums" Example videos generated by the model from texts
Developer(s)	Google
Initial release	February 8, 2024; 17 months ago (2024-02-08)
Type	Large language model