| 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 (2024-02-08) |
| Type | Large language model |
VideoPoet is a large language model developed by Google Research in 2023 for video making.1234 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
References
- Krithika, K. L. (December 20, 2023). "Google Unveils VideoPoet, a New LLM for Video Generation". Analytics India Magazine. Retrieved April 29, 2024.
- Kondratyuk, Dan; Yu, Lijun; Gu, Xiuye; Lezama, José; Huang, Jonathan; Hornung, Rachel; Adam, Hartwig; Akbari, Hassan; Alon, Yair; Birodkar, Vighnesh; Cheng, Yong; Chiu, Ming-Chang; Dillon, Josh; Essa, Irfan; Gupta, Agrim; Hahn, Meera; Hauth, Anja; Hendon, David; Martinez, Alonso; Minnen, David; Ross, David; Schindler, Grant; Sirotenko, Mikhail; Sohn, Kihyuk; Somandepalli, Krishna; Wang, Huisheng; Yan, Jimmy; Yang, Ming-Hsuan; Yang, Xuan; Seybold, Bryan; Jiang, Lu (December 21, 2023). "VideoPoet: A Large Language Model for Zero-Shot Video Generation". arXiv:2312.14125 [cs.CV].
- "Google has introduced VideoPOET breaking new ground in coherent video generation". Gizmochina. December 21, 2023.
- "VideoPoet". Google Research. Retrieved April 29, 2024.
- Franzen, Carl (December 20, 2023). "Google's new multimodal AI video generator VideoPoet looks incredible". VentureBeat.