It’s been 10 months since OpenAI revealed Sora, its generative text-to-video AI model, ushering in a wave of similar generative models over the following months. Earlier this week, the company officially released Sora to ChatGPT Plus and Pro users. This version of Sora can generate videos up to 20 seconds in length, up to 1080p resolution, and in several different aspect ratios.
“Earlier this year, we introduced Sora, our model that can create realistic videos from text, and shared our initial research progress on world simulation,” reads OpenAI’s release. “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.”
The company states that this released version is “Sora Turbo,” and is “significantly faster” than the version previewed at the beginning of the year. As for availability, ChatGPT Plus users will be able to generate up to 50 videos at 480p resolution monthly, or fewer videos at 720p. Pro users will have access to “10x more usage,” in addition to 1080p resolution and longer duration videos. While Sora is now available in many parts of the world, a European release is still being awaited. “We are working to expand access further in the coming months,” says OpenAI.
The following was originally published February 20, 2024:
OpenAI was already seen as the catalyst behind the AI boom with its release of ChatGPT. Last week, the research company introduced Sora, a new AI model that can create photorealistic video from text prompts. According to OpenAI, the videos shown above were 100% generated from text prompts using Sora, with no modifications made. The company states that the model “can generate videos up to a minute long while maintaining visual quality and adherence to the user’s prompt.”
Google rebrands its AI offerings, releases Gemini Advanced to the public
For instance, the prompt for one video reads “Several giant wooly mammoths approach treading through a snowy meadow, their long wooly fur lightly blows in the wind as they walk, snow covered trees and dramatic snow capped mountains in the distance, mid afternoon light with wispy clouds and a sun high in the distance creates a warm glow, the low camera view is stunning capturing the large furry mammal with beautiful photography, depth of field.”
Sora is not widely available yet, but OpenAI has made the model available to some visual artists and other professional creatives for the purposes of receiving feedback to improve the product. As AI continues to raise ethics questions, the company has also made the program available to security specialists to conduct testing for risk assessment.
