Lumiere
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,Weizmann Institute of Science,Tel Aviv University,Technion - Israel Institute of Technology
- Organisation type
- Industry,Academia,Academia,Academia
- Country
- United States of America, Israel
- Published
- 23 January 2024
- Authors
- Omer Bar-Tal, Hila Chefer, Omer Tov, Charles Herrmann, Roni Paiss, Shiran Zada, Ariel Ephrat, Junhwa Hur, Guanghui Liu, Amit Raj, Yuanzhen Li, Michael Rubinstein, Tomer Michaeli, Oliver Wang, Deqing Sun, Tali Dekel, Inbar Mosseri
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Video, Vision
- Task
- Video generation, Text-to-video, Image-to-video
- Approach
- Self-supervised learning
- Base model
- Imagen
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
- Epochs
- 200
We train our T2V model on a dataset containing 30M videos along with their text caption. The videos are 80 frames long at 16 fps (5 seconds). The base model is trained at 128×128 and the SSR outputs 1024 × 1024 frames. 30M videos * 80 frame/video = 2.4B
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.
- Record confidence
- Confident
- Citations
- 477
Sources
Where this record came from and when it was last checked.
- Reference
- Lumiere: A Space-Time Diffusion Model for Video Generation
- Last updated
- 25 May 2026
What the numbers mean
About this model
Lumiere was published by Google Research,Weizmann Institute of Science,Tel Aviv University,Technion - Israel Institute of Technology, in the country recorded as United States of America, during January 2024. The category the publisher falls under is industry,Academia,Academia,Academia.
It works in the domain of Video, Vision, and is recorded as performing the task of video generation, Text-to-video, Image-to-video.
Its starting point was an existing base model, Imagen. Most models at this scale are adapted from an existing base rather than built from nothing.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Answers
Lumiere — common questions
Lumiere— 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.
Lumiere— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Lumiere— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
Lumiere— who created it?
It was published by Google Research,Weizmann Institute of Science,Tel Aviv University,Technion - Israel Institute of Technology, based in United States of America, an organisation categorised as industry,Academia,Academia,Academia.
Lumiere— when was it released?
It was published in January 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.
Lumiere— what is it used for?
It works in the domain of Video, Vision, and is recorded as handling the task of video generation, Text-to-video, Image-to-video. These are the areas it was designed around; they describe intent rather than a hard boundary.
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.