Meet ‘Loab’, the latest example of AI-generated art crawling the internet (sorry in advance for the nightmares)

0

Just in time for Halloweena macabre image of a woman with sunken eyes and bloody cheeks, known only as “Loab“, haunts the internet. In an even weirder twist of digital fate, the creepy avatar was created by artificial intelligence (AI), hinting that its darkness emanates from an eerie, horror-infused wave of emerging consciousness.

The story goes like this: Loab was first “discovered” in April 2022 by user @Supercomposite, while experimenting with an unidentified AI image generator. In a now viral thread job On Twitter last week, Supercomposite describes the creation of the “first AI-generated cryptid”, and the persistence and consistency of its image, through several different prompts and text and image combinations. Since then, Loab iterations have come online in droves.

The character is just the latest example of the emerging genre of AI art. The movement’s significance has led to fierce debate in artistic circles, with some claiming it creates an “ethical and copyright black hole”, given that AIs are trained on databases of real art, that is, hand-drawn and illustrated works made by humans.

Loab the AI-generated image generated by Twitter Supercomposite user

Recently, an image made on the open-access platform Midjourney won first prize at the Colorado State Fair, sparking a tidal wave of fury from human artists who complained that the AI ​​was speeding up the “death of art”.

Thanks to a proliferation of online programs like Slab, Mid Road and Steady broadcast, anyone can now help develop these machine learning systems. Users enter descriptive text and image prompts, and the AI ​​produces associated images based on that input.

Although the program that released Loab to the world has not been identified, Supercomposite offered insight into the algorithmic prompts that helped generate the viral figure. Using what’s called a “negatively weighted” input, in which the AI ​​”tries to make the image as different from the prompt as possible,” Supercomposite fed the program the phrase “Brando::- 1”, referencing actor Marlon Brando, and received an image of a silhouetted skyline logo with the words “DIGITA PNTICS”.

“I was wondering,” Supercomposite wrote: “is the opposite of this logo, in turn, going to be a picture of Marlon Brando? So the phrase “DIGITA PNTICS skyline logo ::-1” was entered as a prompt and wWhat came out, according to Supercomposite, were several “disgusting images, all of the same devastated-looking older woman.” And so, Loab was born.

Combining Loab’s original footage with other AI-generated imagery, like a heavenly scene of angelic characters made by Supercomposite’s unnamed friend, yielded some truly nightmarish results.

“By a sort of emergent statistical accident”, Supercomposite wrote, “something about this woman is adjacent to extremely bloody and gruesome images in the distribution of global AI knowledge.”

Through all of Supercomposite’s experiments with the AI, Loab has appeared again and again, sometimes in more playful but always unsettling scenes. In an image posted to Twitter, Loab stands in front of a Pride flag; in another, she poses with a puppet.

What makes Loab so frightening, perhaps, is his persistence. “The images resulting from crossing Loab with other images can in turn be crossed with other images,” explained Supercomposite. “The AI ​​can latch onto Loab’s idea so well that it can persist through generations of this kind of crossover, without using the original image.” Wherever she comes from, Loab is here to stay.

Follow Artnet News on Facebook:


Want to stay one step ahead of the art world? Subscribe to our newsletter to receive breaking news, revealing interviews and incisive reviews that move the conversation forward.

Share.

About Author

Comments are closed.