Computers cannot imagine things because they have no eyes, right? Wrong.
This is because imagination in computers comes from processing data, not sensory organs. And when a computer is equipped with AI that keeps on learning from new data, their imagination can be a blend of surrealism, and reality. And OpenAI showed just that.
When the company announced ChatGPT and created an arms race where tech companies race to make better and more advanced generative AI products, OpenAI shocked the AI industry when it announced Sora.
This reaffirmed its position as a trailblazer, leaving pretty much everyone else behind its business dust.
But fast forward, as others are playing catching up, OpenAI seemingly live in the past, by keeping Sora in beta.
It even annoyed developers and early testers.
Now, the wait is finally over.
Now you can generate entirely new videos from text, bring images to life, or extend, remix, or blend videos you already have. We’ve developed new interfaces to allow easier prompting, creative controls, and community sharing: https://t.co/HMcAKwaCCw pic.twitter.com/gtMiFkT6GB
— OpenAI (@OpenAI) December 9, 2024
After annoying beta testers and had them leaked Sora, OpenAI finally give the public an official release of the AI.
In a dedicated webpage on its website:
"Our video generation model is rolling out at sora.com."
"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."
And this is where Sora's late arrival is not too much in vain.
In the third day of its '12 Days of OpenAI,' OpenAI revealed that it's giving Sora a new interface, with a wide range of features.
As first shared in its technical report, users of Sora can generate videos up to 1080p resolution, up to 20 seconds long, and in widescreen, vertical or square aspect ratios.
"You can bring your own assets to extend, remix, and blend, or generate entirely new content from text," explain OpenAI.
OpenAI has developed the new interface to make it easy for users to prompt Sora with text, images and videos. Then, there is the storyboard tool that lets users customize the inputs for every frame.
"We also have Featured and Recent feeds that are constantly updated with creations from the community," OpenAI added.
And to at least make up Sora's extremely late arrival, OpenAI is also introducing what it calls Sora Turbo.
Since previewing Sora in February, we’ve been building Sora Turbo—a significantly faster version of the model to put in your hands. We’re releasing it today as a standalone product to Plus and Pro users. https://t.co/Ap7ad7HR7X
— OpenAI (@OpenAI) December 9, 2024
Initially, Sora is included as part of users' ChatGPT Plus account at no additional cost.
With the subscription, users can generate up to 50 videos at 480p resolution or fewer videos at 720p each month.
But for those who wish to utilize Sora to the fullest capacity, the Pro plan includes 10x more usage, higher resolutions, and longer durations.
"We hope this early version of Sora will enable people everywhere to explore new forms of creativity, tell their stories, and push the boundaries of what’s possible with video storytelling," said OpenAI.