VideoPoet

VideoPoet
DeveloperGoogle
ReleaseFebruary 8, 2024; 2 years ago (2024-02-08)
TypeLarge language model

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

VideoPoet received a Best Paper Award at ICML 2024.

References

  1. 1 2 Krithika, K. L. (December 20, 2023). "Google Unveils VideoPoet, a New LLM for Video Generation". Analytics India Magazine. Retrieved April 29, 2024.
  2. ↑ 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].
  3. ↑ "Google has introduced VideoPOET breaking new ground in coherent video generation". Gizmochina. December 21, 2023.
  4. 1 2 "VideoPoet". Google Research. Retrieved April 29, 2024.
  5. ↑ Franzen, Carl (December 20, 2023). "Google's new multimodal AI video generator VideoPoet looks incredible". VentureBeat.
  6. ↑ "ICML 2024 Awards". icml.cc. Retrieved October 11, 2026.