
"On Tuesday, OpenAI announced the release of Sora 2, an audio and video generator to succeed last year's Sora. Along with the model, the company also launched a linked social app called Sora, where users can be able to generate videos of themselves and their friends to share on a TikTok-style algorithmic feed. OpenAI's work on a new social platform was previously reported by Wired."
"The Sora app comes with an "upload yourself" feature called "cameos," which allows users to drop themselves into any Sora-generated scenes. In order to use their own likeness in a generated video, users will have to upload a one-time video-and-audio recording to verify their identity and capture their appearance. This feature also allows users to share their "cameos" with their friends, allowing them to give other users the permission to include their likeness in videos that they generate, including videos of multiple people together."
OpenAI released Sora 2, an audio and video generator paired with a linked social app named Sora that offers a TikTok-style algorithmic feed for generated clips. Sora 2 improves physics fidelity to avoid unrealistic object morphing and teleportation, producing more realistic actions like rebounds. Public clips show beach volleyball, skateboarding, gymnastics, and diving scenes. The app includes 'cameos,' a one-time video-and-audio upload to verify likeness and capture appearance, and allows users to grant friends permission to include their likeness in multi-person videos. The Sora iOS app launches in the U.S. and Canada, with plans to expand.
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]