OpenAI’s day three announcement is a big one: the long-awaited release of the company’s text to video model, Sora. The model can generate videos up to 20 seconds long in 1080p based on text prompts or uploaded images, and can be “remixed” through additional user prompts. Sora will be available to users in the U.S. and abroad (except in the EU) to ChatGPT Pro and Plus subscribers starting today. They also confirmed a faster version of the model called Sora Turbo.
CEO Sam Altman said that ChatGPT Plus members will get 50 video generations a month, while ChatGPT Pro users will get unlimited generations in their “slow queue mode” and 500 “normal” generations per month.
