OpenAI launched Sora, its artificial intelligence model that creates videos based on text. But the company warned there are limitations<\/b>
\nOpenAI has finally launched Sora, its artificial intelligence model that creates videos based off of text. The company, led by CEO Sam Altman, warned on Monday that the new tool was released with \u201cmany limitations\u201d that may affect the videos users create.
ChatGPT Plus subscribers, who pay $20 per month for the service, will now be able to create up to 50 videos at 480p resolution; those videos will last up to 5 seconds. And those who pay for the new ChatGPT Pro subscription, which runs $200 per month, will have \u201cunlimited generations\u201d and be able to create 20-second videos with 1080p resolution.
Beyond text prompts, Sora will also be able to create videos based on \u201cimages and video inputs.\u201d
But for now, only a \u201csubset\u201d of users will be able to create new videos based on pictures and videos of real people, OpenAI clarified on Monday, due to the \u201cpotential for abuse.\u201d Images of children will also not be allowed to generate new videos during this trial period, OpenAI said, as the company settles its \u201capproach to safety.\u201d
Here\u2019s a look at a few of the examples OpenAI shared on Sora\u2019s website; a screenshot of a video of bears roaming and a screenshot of a video of two old men in shiny hats:
OpenAI first introduced Sora back in February. It will be available to American users and \u201cmost countries internationally,\u201d per the company\u2019s YouTube livestream on Monday, but there is \u201cno timetable\u201d for its release in the U.K. or other parts of Europe.
\u201cThe version of Sora we are deploying has many limitations,\u201d OpenAI said in its Monday blog post announcing Sora\u2019s release. \u201cIt often generates unrealistic physics and struggles with complex actions over long durations. Although Sora Turbo is much faster than the February preview, we\u2019re still working to make the technology affordable for everyone.\u201d
In a review back in February, Bloomberg pointed out that Sora \u2014 like other text-to-video AI models \u2014 had some obvious constraints. They noted how Sora \u201cstruggles with stray body parts and a mixed understanding of physics.\u201d
The company\u2019s official entry into the text-to-video space comes with a fair amount of competition. Google released its Veo model last week, and Meta unveiled its text-to-video AI tool in October, just to name a few of the major tech companies in the space. Stability AI, which specializes in audio and visual content based on text prompts, also received a vote of confidence in September when James Cameron joined its board.
You can check the new tool out for yourself at Sora.com.<\/p>\n