In February this year, OpenAI introduced Sora, its generative AI model that can create realistic videos from text prompts. Sora initially launched into private beta testing.
Now the company has launched a new version of Sora called “Sora Turbo” that it says is significantly faster than the model it previewed in February and released it as a standalone product at Sora.com to ChatGPT Plus and Pro users.
Users can generate videos up to 1080p resolution, up to 20 seconds long, and in widescreen, vertical, or square aspect ratios. They can also bring their own assets to extend, remix, and blend or create entirely new content from text.
How much is it?
Sora is included for Plus account holders at no additional cost, allowing up to 50 videos at 480p resolution or fewer videos at 720p each month. The Pro plan includes 10x more usage, higher resolutions, and longer durations. OpenAI says it's working on tailored pricing for different types of users, which they plan to make available early next year.
Is it any good?
You tell me! Check out this video I posted to LinkedIn earlier today depicting myself as a hero. Also check out Sora's Explore page which showcases recent videos from other users.
OpenAI admits that there are limitations to Sora at the moment, including often generating unrealistic physics and struggling with complex actions over long durations.
The company wrote, “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.”