VideoPoet
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Google Research,Carnegie Mellon University (CMU),Google DeepMind
- Organisation type
- Industry,Academia,Industry
- Country
- United States of America
- Published
- 21 December 2023
- Authors
- Dan Kondratyuk, Lijun Yu, Xiuye Gu, José Lezama, Jonathan Huang, Grant Schindler, Rachel Hornung, Vighnesh Birodkar, Jimmy Yan, Ming-Chang Chiu, Krishna Somandepalli, Hassan Akbari, Yair Alon, Yong Cheng, Josh Dillon, Agrim Gupta, Meera Hahn, Anja Hauth, David Hendon, Alonso Martinez, David Minnen, Mikhail Sirotenko, Kihyuk Sohn, Xuan Yang, Hartwig Adam, Ming-Hsuan Yang, Irfan Essa, Huisheng Wang,…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Video, Language, Audio
- Task
- Video generation, Audio generation, Text-to-video, Image-to-video, Video-to-video
- Approach
- Self-supervised learning
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 8B
- Training data
- 2,000,000,000,000 tokens
Biggest model has 8B parameters; there are also experiments with 300M and 1B models.
Section 5.1: "We train on a total of 1B image-text pairs and ∼270M videos (∼100M with paired text, of which ∼50M are used for high-quality finetuning, and ∼170M with paired audio) from the public internet and other sources, i.e. around 2 trillion tokens across all modalities."
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
- Citations
- 474
Sources
Where this record came from and when it was last checked.
- Reference
- VideoPoet: A Large Language Model for Zero-Shot Video Generation
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
VideoPoet was published by Google Research,Carnegie Mellon University (CMU),Google DeepMind, in United States of America, in December 2023. The organisation is categorised as industry,Academia,Industry.
It works in Video, Language, Audio, and is recorded as doing video generation, Audio generation, Text-to-video, Image-to-video, Video-to-video.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Training and provenance
The training set ran to roughly 2,000,000,000,000 tokens.
Answers
VideoPoet — common questions
How many parameters does VideoPoet have?
VideoPoet has 8B parameters. Biggest model has 8B parameters; there are also experiments with 300M and 1B models. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
Who created VideoPoet?
VideoPoet was published by Google Research,Carnegie Mellon University (CMU),Google DeepMind, based in United States of America, categorised as industry,Academia,Industry.
When was VideoPoet released?
VideoPoet was published in December 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is VideoPoet used for?
VideoPoet works in Video, Language, Audio, and is recorded as handling video generation, Audio generation, Text-to-video, Image-to-video, Video-to-video. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run VideoPoet?
None. VideoPoet is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Is VideoPoet open source?
No. VideoPoet has not had its weights published, so it exists only as a service controlled by its owner.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.