OpenAI and Sam Altman have announced the release of Sora 2, a video generation feature that users can interact with to make high-quality production content. The new feature, which for now has been rolled out on a limited use basis to users in North America.
Sam Altman penned an article on his blog, talking about what the new feature is meant to do for users and also highlighting the possibility of misuse to create harmful content.
“It is easy to imagine the degenerate case of AI video generation that ends up with us all being sucked into an RL-optimized slop feed. The team has put great care and thought into trying to figure out how to make a delightful product that doesn’t fall into that trap, and has come up with a number of promising ideas. We will experiment in the early days of the product with different approaches,” wrote Altman.
ChatGPT Pro users will have access to the paid version of Sora 2 Pro while Sora 2 will remain free initially as the team continues to experiment with the technology.
Multiple users are using the technology, creating different kinds of videos at a hyper-real level. One user on X tested Sora 2 to create an anime video featuring famous characters from One-Punch Man, Dragon Ball Z, Attack on Titan, and other popular series.