Latest Breaking News & Hot Updates Around USA OR All Over World

Meta Introduces ‘Make-A-Video’ AI System That Generates Videos From Nothing But TEXT Prompts

0

Meta Introduces Artificial Intelligence System That Generates Videos From Nothing But TEXT Prompts – With Some Creepy, Surreal Results

  • Meta’s New Artificial Intelligence Can Generate Video Clips From Nothing But Text
  • The AI ​​system, called Make-A-Video, is trained with a combination of existing captioned images and unlabeled videos
  • So far, it’s yielding results that are impressive, but often look creepy or surreal
  • Some of the video clips feature a convincing spaceship landing on Mars, a ballerina dancing atop a skyscraper, and an astronaut floating in space.

Advertisement

Meta debuted a new type of art-generating AI that can create videos from nothing but text prompts — with results that are eerie, surreal, and impressive.

The artificial intelligence system announced Thursday, called Make-A-Video, uses existing captioned images to learn more about the world and how it is described, and uses untagged videos to determine how the world moves.

The resulting videos range from surreal to stylized and creepy to convincing.

Mark Zuckerberg’s company hasn’t announced when the system will be available to the public or whether there will be any restrictions — but there is a signup form people can fill out if they want to test Make-A-Video in the future.

Meta debuted a new type of art-generating AI that can create videos from nothing but text prompts – with results that are eerie, surreal and impressive

The artificial intelligence system announced Thursday, called Make-A-Video, uses existing captioned images to learn more about the world and how it is described and uses untagged videos to determine how the world moves.

The artificial intelligence system announced Thursday, called Make-A-Video, uses existing captioned images to learn more about the world and how it is described and uses untagged videos to determine how the world moves.

Advances in using AI to create on-demand videos pose all sorts of ethical dilemmas — not to mention the possibility of deepfakes and misinformation.

Meta noted that all content generated by the new system will be watermarked to “help viewers know that the video is AI-generated and not a captured video.”

“Our goal is to eventually make this technology available to the public, but for now we will continue to analyze, test and trial Make-A-Video to ensure that every step of its release is safe and intentional,” the tech giant said.

A video clip shows a fairly realistic-looking spaceship landing on Mars.

Another shows an astronaut floating in space from different points of view.

Mark Zuckerberg's company hasn't announced when the system will be available to the public or whether there will be any restrictions — but there's a signup form people can fill out if they want to test Make-A-Video in the future.

Mark Zuckerberg’s company hasn’t announced when the system will be available to the public or whether there will be any restrictions — but there’s a signup form people can fill out if they want to test Make-A-Video in the future.

Meta noted that all content generated by the new system will be watermarked to

Meta noted that all content generated by the new system will be watermarked to “help viewers know that the video is AI-generated and not a captured video.”

Mark Zuckerberg's Meta Deposits Billions of Dollars to Create Virtual Worlds Where People Can Shop, Work and Have Fun

Mark Zuckerberg’s Meta Deposits Billions of Dollars to Create Virtual Worlds Where People Can Shop, Work and Have Fun

Two other videos look quite surreal.

One shows a ballerina performing ‘a beautiful and difficult dance on the roof of a very tall skyscraper’ with an illuminated cityscape behind her.

Another shows a blue unicorn “flying over a mystical land.”

“Meta AI is committed to developing responsible AI and the safe use of this state-of-the-art video technology,” the company wrote.

“Our research takes the following steps to reduce the creation of harmful, biased or misleading content.”

“In all aspects, spatial and temporal resolution, text fidelity and quality, Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures,” the researchers write in a paper explaining the system.

Previous AI systems that generate still images from text have produced strange results.

Craiyon AI, another popular non-Meta text-to-image system, has created several images of what humans might look like if humans all joined the metaverse.

Each has an augmented reality headset merged with their face.

Those images were first created when The US Sun asked the AI ​​these questions about humans in the metaverse.

A number of tech companies, including Zuckerberg’s, are collapsing tens of billions of dollars into creating virtual worlds where people can shop, work and be entertained.

The footage comes after another AI working in the same way produced bizarre images of the “last selfie ever taken” that showed apocalyptic scenes of humans before nuclear explosions, with rotting flesh and utter devastation behind it.

Craiyon AI, another popular non-Meta text-to-image system, has created several images of what humans might look like if humans all joined the metaverse.  Each has an augmented reality headset merged with their face

Craiyon AI, another popular non-Meta text-to-image system, has created several images of what humans might look like if humans all joined the metaverse. Each has an augmented reality headset merged with their face

Advertisement

Leave A Reply

Your email address will not be published.