Model Tracker

Emu Video

Emu Video is an AI model made by Meta. Meta released it on 16 November 2023. It takes text, image and returns video.

Released: 16 November 2023 — ai.meta.com, read 16 October 2026
Status: Not confirmed: The maker calls this fundamental research, but does not state a status matching the register's enum.
Takes: Text, Image — ai.meta.com, read 16 October 2026
Returns: Video — ai.meta.com, read 16 October 2026
Open weights: Not confirmed: The maker's page does not state whether Emu Video's weights are open.
Licence: Not confirmed: No licence for Emu Video is stated on the maker's page.
Context window: Not confirmed: The maker describes video dimensions and duration, but does not publish a context window in tokens.
Longest answer: Not confirmed: The maker describes video dimensions and duration, but does not publish a standard maximum output limit in tokens.
Knowledge cutoff: Not confirmed: The maker's page does not state a knowledge cutoff.
API price, input: Not confirmed: The maker's page does not publish a standard API input price for Emu Video.
API price, output: Not confirmed: The maker's page does not publish a standard API output price for Emu Video.
Where: Not confirmed: The maker describes Emu Video as fundamental research, but does not state availability through any of the register's listed channels.
Parameters: Not confirmed: The maker's page does not publish a parameter count for Emu Video.
Model card: Not confirmed: No model card for Emu Video is identified on the maker's page.

Questions

Meta released Emu Video on 16 November 2023.

Emu Video takes text, image and returns video.