NewsTech

OpenAI Finally Launches Sora, Its World-Leading AI Video Generator

In a livestream on the morning of Monday, December 9, OpenAI announced that it will officially launch Sora, its AI video generator.

“We don’t want the world to just be text,” OpenAI CEO Sam Altman said. He also said the move is “Critical to our AGI roadmap.”

Screenshot via Livestream

Sora will be located at Sora.com, a separate location from ChatGPT. Sora is included in a ChatGPT Plus account, and does not require another account or payment.

Sora is a highly anticipated video generator. It has taken months to launch.

Sora is designed to deeply understand the world and its physics. The launch includes a new Turbo version, which the team said will roll out later in the day on the 9th.

Sora will generate videos up to 20 seconds, in a variety of different aspect ratios and resolutions.

Storyboard

OpenAI also announced Storyboard, which allows users to direct a video by specifying characters and actions.

Storyboard essentially allows users to specify the exact story and visuals they’d like to see in their end product. That gives it a huge leg up over tools like Luma or Runway, which are essentially one-shot generation tools.

Image to Video

Sora also includes image to video capabilities. From an uploaded image, the platform can turn a single image into a video, inferring the kinds of actions one might want to see happen from a given image.

During the livestream, the OpenAI team generated videos of a wooly mammoth walking in the desert.

Screenshot via livesteam

Remix and Recut

The OpenAI team also demonstrated a Remix and Recut feature.

Remix allows creators to take one version of a video and update it with new ideas. For example, the team showed the process of transforming the mammoth clip into a clip of mammoth robots.

Recut breaks apart a clip and then rebuilds it, based on sections that a creator selects.

Blend

The Blend function in Sora takes in two videos and combines them together into a totally new scene.

I’ve tested thousands of ChatGPT prompts over the last year. As a full-time creator, there are a handful I come back to every day. I compiled them into a free guide, 7 Enormously Useful ChatGPT Prompts For Creators. Grab a copy today!

Thomas Smith

Thomas Smith is a food and travel photographer and writer based in the San Francisco Bay Area. His photographic work routinely appears in publications including Food and Wine, Conde Nast Traveler, and the New York Times and his writing appears in IEEE Spectrum, SFGate, the Bold Italic and more. Smith holds a degree in Cognitive Science (Neuroscience) and Anthropology from the Johns Hopkins University.

Leave a Reply

Back to top button

Discover more from Bay Area Telegraph

Subscribe now to keep reading and get access to the full archive.

Continue reading