Generated by Sora OpenAI's text-to-video model 26

Wait for it. Our new model Sora can be prompted with text, images, or video inputs, but we can also use Sora to gradually interpolate between two input videos, creating seamless transitions between videos with entirely different subjects and scene compositions. In this example, the video in the center interpolates between the corresponding videos on the top and bottom. 

These three videos were generated by Sora without modification.

*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 of what AI capabilities are on the horizon.