OpenAI has debuted a generative video model called Sora that could be a game changer. In OpenAI’s demonstration clips, Sora depicts both fantasy and natural scenes with photorealistic intensity that makes the images appear to be photographed. Although Sora is said to be currently limited to one-minute clips, it is only a matter of time until that expands, which suggests the technology could have a significant impact on all aspects of production — from entertainment to advertising to education. Concerned about Sora’s disinformation potential, OpenAI is proceeding cautiously, and initially making it available only to a select group to help it troubleshoot.

In an interview with The New York Times, Open AI researchers Tim Brooks and Bill Peebles said Sora is not being publicly released, but will be shared “with a small group of academics and other outside researchers who will ‘red team’ it, a term for looking for ways it can be misused.”

OpenAI says on the Sora page it is “also granting access to a number of visual artists, designers, and filmmakers to gain feedback on how to advance the model to be most helpful for creative professionals.”

Sora can quickly generate not only images but also sound and text. “Eye-popping” is a term used to describe Sora by NYT, which concedes Sora “could speed the work of seasoned moviemakers, while replacing less experienced digital artists entirely.” NYT also registers concerns, such as it becoming “a quick and inexpensive way of creating online disinformation, making it even harder to tell what’s real on the Internet.”

OpenAI chose the name Sora, Japanese for “sky,” because it evokes limitless potential. Ensuring that potential will be used for good is the challenge. University of Washington Professor Oren Etzioni, who is also the founder of the non-profit True Media, tells NYT he is “absolutely terrified that this kind of thing will sway a narrowly contested election.”

OpenAI is watermarking Sora-generated clips but admits they can be removed.

MIT Technology Review says that with Sora, OpenAI “has pushed the envelope of what’s possible with text-to-video generation.”

Related:
Why OpenAI’s Sora Isn’t Ready to Replace Hollywood, Variety, 2/16/24