OpenAI is rolling out its new video generation model sora.com.
The new AI-video-generation tool will be made available to ChatGPT Plus and Pro users today.
With the new AI, users can generate videos up to 1080p that are 5-20 seconds long in a variety of widescreen, vertical or square aspect ratios.
The new AI also allows users to bring in their own assets to extend, remix, and blend with the option to also generate entirely new content from text.
These features were released in a live stream on Monday where Will Peebles, a member of OpenAI’s technical staff and research lead on Sora, said despite Sora’s current limitations, they can’t wait to see what people create with it.
“This early version of Sora will make mistakes — it’s not perfect, but it’s already at the point where we think it’s going to be really useful for augmenting human creativity,” he said.
Other features of Sora that have been shared include a storyboard interface allowing users to create sequences of videos and loop and re-cut options that allow creators to further tweak and edit their videos and scenes.
While being rolled out, Sora was having major capacity issue this morning.
Credits are required to create videos with the new AI, with the amount varying depending on length and resolution of the video.