VideoPoet
Jump to navigation
Jump to search
| 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 | |
| Initial release | February 8, 2024 |
| Repository |
|
| Engine | |
| Type | Large language model |
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.
References
[edit | edit source]- ^ a b Lua error in Module:Citation/CS1/Configuration at line 2172: attempt to index field '?' (a nil value).
- ^ Lua error in Module:Citation/CS1/Configuration at line 2172: attempt to index field '?' (a nil value).
- ^ Lua error in Module:Citation/CS1/Configuration at line 2172: attempt to index field '?' (a nil value).
- ^ a b Lua error in Module:Citation/CS1/Configuration at line 2172: attempt to index field '?' (a nil value).
- ^ Lua error in Module:Citation/CS1/Configuration at line 2172: attempt to index field '?' (a nil value).
External links
[edit | edit source]- Error creating thumbnail: File missing Media related to Lua error in Module:Commons_link at line 62: attempt to index field 'wikibase' (a nil value). at Wikimedia Commons
