Imagen 3
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 DeepMind
- Organisation type
- Industry
- Country
- United States of America
- Published
- 14 May 2024
- Authors
- Jason Baldridge, Jakob Bauer, Mukul Bhutani, Nicole Brichtova, Andrew Bunner, Kelvin Chan, Sergio Gómez Colmenarejo, Sander Dieleman, Yuqing Du, Zach Eaton-Rosen, Hongliang Fei, Yilin Gao, Evgeny Gladchenko, Mandy Guo, Alex Haig, Will Hawkins, Hexiang (Frank) Hu, Huilian Huang, Tobenna Peter Igwe, Christos Kaplanis, Siavash Khodadadeh, Ksenia Konyushkova, Karol Langner, Eric Lau, Shixin Luo, Soňa …
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Image generation
- Task
- Image generation, Text-to-image
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.
- Training data
- tokens
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- Google TPU v4,Google TPU v5e
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
- Hosted access (no API)
- 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
- Unknown
Sources
Where this record came from and when it was last checked.
- Reference
- Imagen 3: our highest quality text-to-image model
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Imagen 3 was published by Google DeepMind, in United States of America, in May 2024. The organisation is categorised as industry.
It works in Image generation, and is recorded as doing image generation, Text-to-image.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Answers
Imagen 3 — common questions
How many parameters does Imagen 3 have?
No parameter count has been published for Imagen 3, which is why no memory or speed figure appears on this page.
Who created Imagen 3?
Imagen 3 was published by Google DeepMind, based in United States of America, categorised as industry.
When was Imagen 3 released?
Imagen 3 was published in May 2024. 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 Imagen 3 used for?
Imagen 3 works in Image generation, and is recorded as handling image generation, Text-to-image. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
What GPU do I need to run Imagen 3?
None. Imagen 3 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 3 open source?
No. Imagen 3 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.