OpenAI unveils Sora, a hyper-realistic video generator

The publisher of ChatGPT chatbot and DALL-E image generator, OpenAI, has unveiled a new tool called Sora, capable of creating hyper-realistic videos that can last up to a minute, using a simple text command, a major innovation in the field of artificial intelligence (AI).

This new platform is still being tested, but that doesn't stop the California startup from showing it off in some videos.

The program can create videos up to one minute long While maintaining visual quality and respecting user requestOpenAI said on its website.

[Sora peut] Create complex scenes with multiple characters, specific types of movements, and fine details.

In addition to text, the tool can also create a video from a still image, or even expand existing videos.

Offered to a limited number of people

Sam Altman, head of OpenAI, made the announcement on the social network Provides a limited number of creators with access to this new toolduring the experimental phase.

The director also invited netizens to submit suggestions for creating videos, of which he broadcast the most relevant videos a few moments later on the platform.

Among these videos we see two dogs playing in the snow in the mountains. Another video shows an imaginary animal, half duck and half dragon, flying in front of a magnificent sunset, with a hamster wearing sports clothes on its back.

[Sora sert de base à] Programs capable of understanding and simulating the real world.

OpenAI hopes that Sora It will be an important step in achieving artificial general intelligenceArtificial general intelligence, a highly autonomous system that would outperform humans at most economically profitable tasks.

Still work to do

OpenAI stated that the current model of the platform has flaws, including confusion between left and right or the inability to maintain visual continuity throughout the video.

For example, a person may take a bite of a cookie, but afterwards there may not be any bite marks on the cookie.“, explains the editor.

By unveiling this new tool, the company emphasized that the issue of security is a major challenge and that simulations will be organized with Internet users who will be challenged to produce crashes or create inappropriate content, in order to better define the limits of the platform. .

We will engage policymakers, educators and artists around the world to understand their concerns and target positive use cases for this new technologysaid OpenAI.

Meta, Google, and Runway AI, which is working on similar text-to-video applications (Convert text to videoin English), samples have already been provided.