Four theories that explain the standard vibe of AI Art
The image makers are stuck in a pattern.
This is Atlantic Intelligence, a newsletter in which our writers help you wrap your mind around artificial intelligence and a new machine age. Sign up here.
At this point, AI art is about as noteworthy as the email inviting you to save 10 percent on a new pair of jeans. On the one hand, it’s amazing that computer programs can synthesize images based on any text prompt; on the other, these images are common enough that they have become a new type of digital junk, polluting social media feeds and other online spaces with no particular payoff for users.
But their sheer spam power isn’t just a matter of volume—these images also tend to look pretty similar. As my colleague Caroline Mimbs Nyce writes in a new story The Atlantic Ocean“Two years into the generative-AI boom, the creations of these programs seem technically advanced … but they are stuck with a distinct aesthetic.” By default, these models tend to produce images with bright, saturated colors; beautiful and almost cartoonish people; and dramatic lighting. Caroline spoke to experts who gave her four theories as to why that is.
Ultimately, their reporting suggests that while technology companies are competing to offer more compelling image generators, in the end the products aren’t all that different—the situation is more “Pepsi vs. Coke” than “Toyota vs. Mercedes.” Maybe people will just use the image generator that is most convenient. That may explain why companies like X, Google and Apple are so eager to build these models into existing platforms: image generators are no longer magic, but a function to be controlled.
Why does AI art look like this?
By Caroline Mimbs Nyce
This week, X launched an AI image generator, allowing paying subscribers of Elon Musk’s social platform to create their own art. So-naturally, some users seem to have immediately taken pictures of Donald Trump flying a plane to the World Trade Center; Mickey Mouse wielding an assault rifle, and another of him enjoying a cigarette and some beer on the beach; and so on. Some of the images people have created using the tool are deeply disturbing; others are just weird, or even kind of funny. They depict wildly different scenarios and characters. But somehow they all look alike, with unmistakable features of AI art that have emerged in recent years through products like Midjourney and DALL-E.
Read the full article.
What to read next
- Trump finds a new one Benghazi: Earlier this week, Donald Trump falsely claimed that Kamala Harris had “AI’d” a photo of a crowd at one of her campaign rallies — claiming, in other words, that she had doctored or outright fabricated an image to exaggerate the number of people who to encourage her. As Matthew Kirschenbaum writes for The Atlantic OceanTrump’s use of the term may have less to do with the technology per se and more to do with giving his supporters something to post about — a way to license them to follow his lead by using the text boxes on their own to fill in screens.”
PS
AI art can actually be at its best with an audience of one. “Approaching generative imagers to produce a desired result can just backfire on their potential,” wrote Ian Bogost for The Atlantic Ocean last year. “AI can take shape outside your mind, quickly and with little cost: any concept, whatever, output visually in seconds. The results are not images that are used as media, but ideas that are captured in a photo. “
– Damon
#theories #explain #standard #vibe #Art
