Our video model Sora is capable of creating videos from text, images, and other videos, but is also capable of changing just one element of a video, like these examples where just one variable is changed in each of these generations. These videos were generated by our AI video model, Sora, without modification. What would you like to see us make with Sora next? *Sora is not yet available to the public. We’re sharing our research progress early to learn from feedback and give the public a sense o

‘air head’ was born out of @shy kids experimentation with OpenAI’s text-to-video model, Sora. “sunny, our balloon-headed boy, embodies the bluesky feeling of boundless potential that we felt when we first began using the tool. our heads filled with so many ideas, it felt like they might POP. 🎈” - shy kids #sora #madewithsora #openai #airhead #shortfilm #🎈#shykids