Skip to content
AI.info

Model Tracker

Make-A-Video

Make-A-Video is an AI model made by Meta. Meta released it on 29 September 2022. It takes text, image, video and returns video.

Meta

Released
29 September 2022 — ai.meta.com, read 16 October 2026
Status
Not confirmed: The official pages describe Make-A-Video as a research system and work in progress, but do not state a status that maps unambiguously to the register’s status values.
Takes
Text, Image, Video — ai.meta.com, read 16 October 2026
Returns
Video — ai.meta.com, read 16 October 2026
Open weights
Not confirmed: The official pages share research details but do not state whether the model weights are open or provide downloadable weights.
Licence
Not confirmed: The official pages do not name a licence for the model.
Context window
Not confirmed: The official pages do not state a context window.
Longest answer
Not confirmed: The official pages do not state a standard maximum output-token limit.
Knowledge cutoff
Not confirmed: The official pages do not state a knowledge-cutoff date.
API price, input
Not confirmed: The official pages do not publish a standard API input price.
API price, output
Not confirmed: The official pages do not publish a standard API output price.
Where
Not confirmed: The official site invites people to express interest in future releases; it does not confirm availability through the register’s API, app, weights, or cloud categories.
Parameters
Not confirmed: The official pages do not publish a parameter count.
Model card
Not confirmed: The official pages link to a research paper, but do not provide or identify a model card or system card.

Questions

When was Make-A-Video released?

Meta released Make-A-Video on 29 September 2022.

What does Make-A-Video take and return?

Make-A-Video takes text, image, video and returns video.

More from Meta

Sources

  1. Introducing Make-A-Video: An AI system that generates videos from text (read 16 October 2026)
  2. Make-A-Video (read 16 October 2026)

All of the Model Tracker