OpenAI released its text-to-video generation software Sora to the public Monday.
The video tool, which relies on the same generative artificial intelligence that powers ChatGPT, can turn a plain-language text prompt into loops of artificially created video.
OpenAI first showed off the feature in February of 2024, when it gave a limited set of filmmakers and artists access to test.
Now, anyone with a paid ChatGPT account will be able to experiment with the feature. ChatGPT Plus users are limited to 720p resolution and five-second clips. ChatGPT Pro subscribers get full 1080p resolution and longer duration videos.
Other features will let users remix videos, string together separate prompts to create sequenced scenes like a film, and turn still images into animated clips.
RELATED STORY | OpenAI debuts Sora, a tool to make instant videos from written prompts
"We’re introducing our video generation technology now to give society time to explore its possibilities and co-develop norms and safeguards that ensure it’s used responsibly as the field advances," Open AI wrote in a blog post.
Sora videos will display optional watermarks and will include metadata that shows it was AI-generated. OpenAI says it will initially limit the ability to upload footage of humans and will continue to block materials that could enable the creation of sexual deepfakes or child sexual abuse material.