Imagen Video
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 Brain
- Organisation type
- Industry
- Country
- United States of America
- Published
- 5 October 2022
- Authors
- Jonathan Ho, William Chan, Chitwan Saharia, Jay Whang, Ruiqi Gao, Alexey Gritsenko, Diederik P. Kingma, Ben Poole, Mohammad Norouzi, David J. Fleet, Tim Salimans
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Video
- Task
- Video generation, Text-to-video
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
- 11.6B
- Training data
- tokens
Figure 6 summarizes the entire cascading pipeline of Imagen Video. In total, we have 1 frozen text encoder, 1 base video diffusion model, 3 SSR (spatial super-resolution), and 3 TSR (temporal superresolution) models – for a total of 7 video diffusion models, with a total of 11.6B diffusion model parameters
We train our models on a combination of an internal dataset consisting of 14 million video-text pairs and 60 million image-text pairs, and the publicly available LAION-400M image-text dataset.
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
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Likely above 10²³ FLOP
- Yes
- Record confidence
- Confident
- Citations
- 2,019
Sources
Where this record came from and when it was last checked.
- Reference
- Imagen Video: High Definition Video Generation with Diffusion Models
- Last updated
- 25 May 2026
What the numbers mean
What this model is
Imagen Video was published by Google Brain, in United States of America, in October 2022. industry is the category the publisher falls under.
It works in Video, and is recorded as doing video generation, Text-to-video.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Answers
Imagen Video — common questions
What is Imagen Video used for?
Imagen Video works in Video, and is recorded as handling video generation, Text-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 Imagen Video?
None. Imagen Video 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 Imagen Video open source?
No. Imagen Video has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Imagen Video have?
Imagen Video has 11.6B parameters. Figure 6 summarizes the entire cascading pipeline of Imagen Video. In total, we have 1 frozen text encoder, 1 base video diffusion model, 3 SSR (spatial super-resolution), and 3 TSR (temporal superresolution) models – for a total of 7 video diffusion models, with a total of 11.6B diffusion model parameters. 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 Imagen Video?
Imagen Video was published by Google Brain, based in United States of America, categorised as industry.
When was Imagen Video released?
Imagen Video was published in October 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
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.