DALL-E is an open-source artificial intelligence that will draw nine images based on what it learned on the internet. Enter in any prompt and the AI spits out the graphics. Examples from the developer’s site include “a baby daikon radish in a tutu walking a dog” and “a baby hedgehog in a cape staring at its reflection in a mirror.” The internet has wasted no time putting DALL-E through its paces.
Columbo in Marvel vs Capcom 2 pic.twitter.com/NIRcdCWjjU— Ismael Bergara (@Calavera145) June 6, 2022
The AI’s job is to do something many of us do every day—look at images on the internet. It also reads the captions and learns what is probably in the image based on that. Now it can draw images based on text. The more specific the prompt, the more amusing the results are. The one below is “Star Wars movie poster in the style of Salvador Dali.” And they’re perfect.
This one was particularly beautiful pic.twitter.com/POUL7Gejry— Paul Adamson (@Paulywoggsvoice) June 8, 2022
In between failed attempts because the site was experiencing so much traffic, I entered “Snoopy playing with other dogs” as a prompt. The results weren’t nearly as cute as I was hoping. While it clearly knows who Snoopy is, it’s closer to a Picasso painting than anything else.
Nerdist‘s very own Dan Casey got much better results with “baby yoda eating pizza.” Proving Grogu is literally cute under any and all circumstances.
The developer, Boris Dayma, is documenting the program’s progress on his Twitter account. Give him a hand by taking the artificial intelligence on a training run. It’s for the good of the data after all, but it’s also a hoot. So says the “Gay pride coyote” below.
Next up, I’m trying “manatees with Elizabethan collars swimming with rabbits.”
Melissa is Nerdist’s science & technology staff writer. She also moderates “science of” panels at conventions and co-hosts Star Warsologies, a podcast about science and Star Wars. Follow her on Twitter @melissatruth.