UniPi
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
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,Massachusetts Institute of Technology (MIT),University of California (UC) Berkeley,Georgia Institute of Technology,University of Alberta
- Organisation type
- Industry,Academia,Academia,Academia,Academia
- Country
- United States of America, Canada
- Published
- 31 January 2023
- Authors
- Yilun Du, Mengjiao Yang, Bo Dai, Hanjun Dai, Ofir Nachum, Joshua B. Tenenbaum, Dale Schuurmans, Pieter Abbeel
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Video, Robotics, Vision
- Task
- Video generation
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
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
- Open — downloadable
- Model access
- Open weights (unrestricted)
- Training code
- Open source
https://github.com/flow-diffusion/AVDC MIT License
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Unknown
- Citations
- 503
Sources
Where this record came from and when it was last checked.
- Reference
- Learning Universal Policies via Text-Guided Video Generation
- Last updated
- 25 May 2026
What the numbers mean
Background
UniPi was published by Google DeepMind,Massachusetts Institute of Technology (MIT),University of California (UC) Berkeley,Georgia Institute of Technology,University of Alberta, in United States of America, in January 2023. It comes out of industry,Academia,Academia,Academia,Academia.
It works in Video, Robotics, Vision, and is recorded as doing video generation.
The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold.
Answers
UniPi — common questions
What is UniPi used for?
UniPi works in Video, Robotics, Vision, and is recorded as handling video generation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
Where can I download UniPi?
The weights for UniPi are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
What GPU do I need to run UniPi?
We cannot say. UniPi has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
Is UniPi open source?
Its weights are published, so UniPi can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
How many parameters does UniPi have?
No parameter count has been published for UniPi, which is why no memory or speed figure appears on this page.
Who created UniPi?
UniPi was published by Google DeepMind,Massachusetts Institute of Technology (MIT),University of California (UC) Berkeley,Georgia Institute of Technology,University of Alberta, based in United States of America, categorised as industry,Academia,Academia,Academia,Academia.
When was UniPi released?
UniPi was published in January 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.
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.