OpenAI has just released Sora, a generative AI tool capable of creating realistic videos. This is part of the company's "12 Days of OpenAI" event.
In a post issued last 9 December, OpenAI said that the text-to-video generator is available for public use. An account must be made to use Sora, though sign-ups have been temporarily disabled due to heavy traffic.
"This is a critical part of our AGI roadmap," OpenAI CEO Sam Altman said during the company’s live stream.
According to the OpenAI team, Sora will be made available to Plus and Pro subscribers in the U.S. and around the world starting 9 December.
The model is capable of generating videos in resolutions ranging from 480p to 1080p in lengths from 5 to 20 seconds, from either text prompts or reference images. It’s also capable of editing and extending existing video clips.
ChatGPT Plus subscribers will be allowed up to 50 clip generations at up to 720p per month, and fewer videos at higher resolutions, each five seconds long. Pro users will be allowed unlimited generations at all resolutions and durations as long as 20 seconds. In addition to editing tools, Sora also offers a "storyboard" feature that will enable creators to combine multiple prompts into a single cinematic scene.
The public launch of the tool comes as the entertainment industry grapples with deployment of technology potentially capable of slashing productions costs.
Mainstream adoption in Hollywood has been slow but steady, with Lionsgate in September announcing a partnership with Runway in a deal that will see the New York-based AI startup train a new generative AI model on company content, which will be used to assist with behind-the-scenes production processes. This was followed by James Cameron joining the board of directors for Stability AI — creator of Stable Diffusion, an image- and video-focused model that is among those being closely watched by many in Hollywood, particularly in the visual effects industry — in a major coup for the company.
0 comments
Post a Comment