Sora: AI Generated Video from Text

February 15, 2024

OpenAI recently announced Sora, an AI model that’s capable of producing videos based on text input only.

Video from text isn’t really a new thing, in terms of AI. I’ve seen mentions of short videos amounting to a few seconds that have been generated from text prompts. But the video examples being shared today are leaps and bounds from those smaller video framents I’ve seen to date.

A few examples:

Spaceman with a red knit helmet.

Aerial view of Santorini.

The level of detail is pretty incredible, even if there are issues here and there in the background. Difficult to wrap my head around the fact that all of the videos here don’t actually exist, and were generated by text commands interpreted by a machine.

I’m a bit excited and terrified, to see where this will go.

[via MetaFilter]