- OpenAI recently debuted its new Sora tool for generating AI videos based on user prompts.
- Right now, the beta is only accessible to certain content creators and safety experts.
- But the samples posted on OpenAI's website look impressive.
AI videos just got a whole lot more realistic.
Open AI, creators of ChatGPT, announced on Thursday their new Sora tool, which generates short AI videos based on user prompts.
The tool is not yet available to the public. But there are plenty of examples of the technology that are already floating around the internet.
OpenAI CEO Sam Altman was taking requests from users on X, formerly Twitter, posting generated videos of everything from a grandmother cooking homemade gnocchi to a monkey playing chess in a park (requested by Mr. Beast).
And the company provided dozens of photo-realistic videos, along with their prompts, as proof-of-concept.
Here are some of the best examples, along with the prompts OpenAI says it used to generate the videos.
(If you want to see the full high-rez versions of the videos, check out Sora's website)
OpenAI showed off reflections in a cityscape.
A scene of a snowy street in Tokyo showed off the impressive tech.
With Sora, OpenAI said you can create origami underwater.
Woolly mammoths look like they survived the Ice Age.
Sora created an aerial image of the Amalfi Coast that looked photo-realistic.
Even stylized animations were impressive.