Phenaki

Closed weights University College London (UCL),University of Michigan,Google Brain 1.8B parameters October 2022

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
University College London (UCL),University of Michigan,Google Brain
Organisation type
Academia,Academia,Industry
Country
United Kingdom of Great Britain and Northern Ireland, United States of America
Published
5 October 2022
Authors
Ruben Villegas, Mohammad Babaeizadeh, Pieter-Jan Kindermans, Hernan Moraldo, Han Zhang, Mohammad Taghi Saffar, Santiago Castro, Julius Kunze, Dumitru Erhan

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
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
1.8B

Unless specified otherwise, we train a 1.8B parameter Phenaki model on a corpus of ∼15M textvideo pairs at 8 FPS mixed with ∼50M text-images plus ∼400M pairs of LAION-400M [41] (more details in Appendix B.3). The model used in the visualisations in this paper was trained for 1 million steps at a batch size of 512, which took less than 5 days. In this setup 80% of the training data came from the video dataset and each image dataset contributed 10%.

Training data
tokens

Unless specified otherwise, we train a 1.8B parameter Phenaki model on a corpus of ∼15M textvideo pairs at 8 FPS mixed with ∼50M text-images plus ∼400M pairs of LAION-400M [41] (more details in Appendix B.3). The model used in the visualisations in this paper was trained for 1 million steps at a batch size of 512, which took less than 5 days. In this setup 80% of the training data came from the video dataset and each image dataset contributed 10%.

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.

Foundation model
Yes
Why it is tracked
SOTA improvement

"To the best of our knowledge, this is the first time a paper studies generating videos from time variable prompts" They don't claim any absolute SOTA results

Citations
545

Sources

Where this record came from and when it was last checked.

Reference
Phenaki: Variable Length Video Generation From Open Domain Textual Description
Last updated
25 May 2026

What the numbers mean

Background

Phenaki was published by University College London (UCL),University of Michigan,Google Brain, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during October 2022. It comes out of an organisation categorised as academia,Academia,Industry.

It works in the domain of Video, and is recorded as performing the task of 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.

Training and provenance

Its inclusion criterion: sOTA improvement.

Answers

Phenaki — common questions

01

Phenaki— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

02

Phenaki— how many parameters does it have?

It has a parameter count of 1.8B. Unless specified otherwise, we train a 1.8B parameter Phenaki model on a corpus of ∼15M textvideo pairs at 8 FPS mixed with ∼50M text-images plus ∼400M pairs of LAION-400M [41] (more details in Appendix B.3). The model used in the visualisations in this paper was trained for 1 million steps at a batch size of 512, which took less than 5 days. In this setup 80% of the training data came from the video dataset and each image dataset contributed 10%. 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.

03

Phenaki— who created it?

It was published by University College London (UCL),University of Michigan,Google Brain, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as academia,Academia,Industry.

04

Phenaki— when was it released?

It 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.

05

Phenaki— what is it used for?

It works in the domain of Video, and is recorded as handling the task of video generation, Text-to-video. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

Phenaki— what GPU do I need to run it?

None. This 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.

Source

Original publication

Record last updated 25 May 2026

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.