OpenAI Officially Releases 'Sora' Video Generation Model

OpenAI has announced the official launch of its 'Sora' video generation model.

Earlier this year, we introduced Sora⁠, our model that can create realistic videos from text, and shared our initial research progress⁠ on world simulation. Sora serves as a foundation for AI that understands and simulates reality—an important step towards developing models that can interact with the physical world. We developed a new version of Sora—Sora Turbo— that is significantly faster than the model we previewed in February. We're releasing it today as a standalone product at Sora.com to ChatGPT Plus and Pro users.

Users can generation videos that are up to 1080p in resolution and up to 20 seconds long in widescreen, vertical, or square aspect ratios. You can also upload your own assets to extend, remix, and blend, or generate entirely new content from text.


OpenAI has created a new interface to make it easier to prompt Sora. A storyboard tool lets you precisely specify inputs for each frame. There's also Featured and Recent feeds that are updated with creations from the community.

ChatGPT Plus users can generate up to 50 videos at 480p resolution or fewer videos at 720p each month. The new $200/month Pro plan includes 10x more usage, higher resolutions, and longer durations. New plans designed around Sora will be available early next year.

Notably, Sora-generated content has C2PA metadata, which will identify a video as coming from Sora. There's also visible watermarks and OpenAI says it has developed an internal search tool that uses technical attributes of generations to help verify if content came from Sora. Additionally, OpenAI says its blocking inappropriate content from being generated and limiting uploads of people at launch.

Check out the videos below for more details!


Read More