Movie Gen 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
- Meta AI
- Organisation type
- Industry
- Country
- United States of America
- Published
- 4 October 2024
- Authors
- Adam Polyak, Amit Zohar, Andrew Brown, Andros Tjandra, Animesh Sinha, Ann Lee, Apoorv Vyas, Bowen Shi, Chih-Yao Ma, Ching-Yao Chuang, David Yan, Dhruv Choudhary, Dingkang Wang, Geet Sethi, Guan Pang, Haoyu Ma, Ishan Misra, Ji Hou, Jialiang Wang, Kiran Jagadeesh, Kunpeng Li, Luxin Zhang, Mannat Singh, Mary Williamson, Matt Le, Mitesh Kumar Singh, Peizhao Zhang, Peter Vajda, Quentin Duval, Rohit Gir…
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
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
- 30B
- Training data
- 3,400,000,000 tokens
30B
O(1B) images O(100M) videos, each with 256 frames ~= 25M images
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 1.7 × 10²⁴ FLOP
- How it was established
- Operation counting
Model size = 30B Broken down by training stage (table 3): 256px T2I: samples seen = 1.94E9; sample token length = 256; flops = 6ND = 8.94E22 256px T2I/V: samples seen = 3.95E8; sample token length = 8192; flops = 6ND = 5.82E23 768px T2I/V: samples seen = 7.38E7; sample token length = 73,728; flops = 6ND = 9.79E23 Total flops = 1.65E24
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
- NVIDIA H100 SXM5 80GB
- Chips used
- 6,144
- Wall-clock time
- 331 hours (13.8 days)
- Power draw
- 8.5 MW
54 hours for 256px T2I 128 hours for 256px T2I/V 149 hours for 768px T2I/V
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
- Why it is tracked
- Training cost
- Record confidence
- Confident
BOTE estimate of cost is ~$3 million
Sources
Where this record came from and when it was last checked.
- Reference
- Movie Gen: A Cast of Media Foundation Models
- Last updated
- 28 November 2025
What the numbers mean
What this model is
Movie Gen Video was published by Meta AI, in United States of America, in October 2024. It comes out of industry.
It works in Video, Vision, and is recorded as doing video generation, Text-to-video, Image-to-video.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
How it was trained
Producing it required around 1.7 × 10²⁴ FLOP of arithmetic, on NVIDIA H100 SXM5 80GB, which is a statement about the training budget rather than about inference.
It was trained on about 3,400,000,000 tokens of text.
Its inclusion criterion is training cost.
Answers
Movie Gen Video — common questions
How many parameters does Movie Gen Video have?
Movie Gen Video has 30B parameters. 30B. 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 Movie Gen Video?
Movie Gen Video was published by Meta AI, based in United States of America, categorised as industry.
When was Movie Gen Video released?
Movie Gen Video was published in October 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 Movie Gen Video used for?
Movie Gen Video works in Video, Vision, and is recorded as handling video generation, Text-to-video, Image-to-video. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train Movie Gen Video?
Around 1.7 × 10²⁴ FLOP, on NVIDIA H100 SXM5 80GB. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
What GPU do I need to run Movie Gen Video?
None. Movie Gen 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 Movie Gen Video open source?
No. Movie Gen Video 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.