We generated the worst visions of geek horror and video games with the artificial intelligence DALL E mini


Unless you live in a cave, you’ve probably seen some funny AI-generated images of DALL·E mini lately.

The phenomenon is so popular that the New Yorker even refers to it in his June 13 cartoon. Our friends from the Sac de chips also took part in the web trend with very strange things. Hard to escape it.

For those scratching their heads: DALL E mini is an artificial intelligence model designed by Boris Dayma to generate images from any text. The model learns by looking at millions of images on the web with their associated captions. Some concepts are learned from memory, but the model can also learn to create unique images that don’t exist by combining multiple ideas.

It gave us a great idea: why not write some bullshit related to video games and geek culture to see what happens? For science, yes.

Here are the creations of Pèse sur Start, made with DALL·E mini.

Bruce Willis on a Chocobo

Han Solo taking a bath with Chewbacca

Crash Bandicoot on bike

Lady Dimitrescu at Costco

Kirby with a shotgun

Lara Croft eats cheese

Kratos holding a butterfly

weed smoking grogu

Diddy Kong dance GTA V

Ganondorf drinking a beer

Link taking the train

Lickitung in a roller coaster

Geralt in a field of flowers

Battle between Cloud Strife and Tom Nook

Hulk does his grocery shopping

Dragon Ball but at Coachella

Red Dead Redemption but in Quebec

If Vin Diesel was in Elden Ring

Waluigi driving a school bus

Tom Nook smokes a cigar

Pikachu fume un bong

Terminator takes a shower

Super Mario under the influence

Wario, President of the United States

Sonic in the toilet

Snorlax + pain

Ninja turtles eat sushi

If you want to try DALL·E mini, just visit his site and write something fun. You have to be patient, however, because the popularity of the tool sometimes causes web traffic jams.

SEE ALSO

entertainment" data-player-id="player-15e1fff4">

s

Leave a Replay