OpenAI
, creator of ChatGPT and the DALL-E image generator, presented a new tool called
"Sora"
, capable of creating, from a simple text instruction,
cinema-quality videos of up to one minute in length
, a revolutionary innovation in the field of
artificial intelligence
.
Created based on previous searches in the DALL-E and ChatGPT models, this new platform
ma
is still in the testing phase
, said this Thursday the Californian
start-up
allied with Microsoft, which presented some videos to show its first progress.
What is Sora and how does it work?
Sam Altman, CEO of OpenA.
(Photo: Bloomberg)
According to the first advances shared by Open IA on its website and then widely disseminated on the social network "X", this technology can
create clips of up to one minute in length
"with visual quality and respecting user demand."
Sora can "generate
complex scenes with multiple characters
, specific movements and precise details," the company said.
It also allows you
to create a video from a still image
, says the artificial intelligence (AI) giant.
Likewise, it has the ability to
lengthen existing videos
.
Sam Altman
, number one at OpenAI, published on his X account that Sora will be offered
"access to a limited number of creators"
, within the framework of an experimental stage.
He also invited users to make proposals to generate videos, after which
he shared some examples
.
Among these videos, you can see images of two dogs climbing through the snow on a mountain.
Another clip shows how an imaginary animal begins to fly before a magnificent sunset.
A hamster wearing sports clothes rides on his back.
Sora is a basis for
"programs capable of understanding and simulating the real world
," explains the start-up, which hopes that this will be an "important stage in the realization of AGI", Artificial General Intelligence, a
highly autonomous
system that
would outperform humans
in most economically profitable tasks.
For its part, OpenAI warned that the "current model" of the platform
has "defects"
, such as a confusion between left and right or the impossibility of maintaining visual continuity throughout the length of the video.
"For example, a person may eat a cookie, but then the cookie may not exhibit a bite," he exemplified.
The company stated that security is a key issue in this development and stated that it will organize simulations with users who will be asked to try to cause errors or create inappropriate content, in order to better define the limits of the platform.
"We will engage political decision makers, educators and artists around the world to
understand their concerns and identify positive use cases
for this new technology," OpenAI said.
Meta, Google and Runway AI
, which work on similar applications, known as "text-to-video", that is, they allow a written idea to be converted to video, also presented samples of their progress.
Hollywood screenwriters at war with artificial intelligence
Photo: EFE
In May 2023, the mecca of American cinema came to a complete halt.
The
scriptwriters
started a
strike
, which the actors joined in mid-July, to demand better remuneration and
regulation of the use of artificial intelligence
(AI).
This unprecedented protest in Hollywood since 1960 ended in September in the case of the screenwriters, who achieved a salary agreement and protections against the use of AI.
The actors, concerned by fears that studios will use technology to
clone their voices and images
to reuse in perpetuity without compensation or consent, resumed filming in November.
In addition to better salaries, the strike managed to impose restrictions on the use of AI.
The production of American films and series was paralyzed for almost six months by the protest, which cost the country's economy at least $6 billion.
SL