Midjourney introduces first new image generation model in over a year
(arstechnica.com)
from Powderhorn@beehaw.org to technology@beehaw.org on 06 Apr 2025 02:55
https://beehaw.org/post/19284387
from Powderhorn@beehaw.org to technology@beehaw.org on 06 Apr 2025 02:55
https://beehaw.org/post/19284387
The comment section on the cover art is alone worth the price of admission.
threaded - newest
Still can’t into fingers
Her hands might look creepy as shit, but she’s got a winning hand of cards there, with that 21 of S̶̭͉̀̅ͅp̷̪̆́͗a̸̢̢̚ͅd̸͔̍͊̚u̷͓͔̥͒b̴̬́͂e̶̝̫̤̾à̴̱̮̱r̶̗̀̀̚m̴͖̮̔̑o̸̜̓̏̎ņ̷̝͎̚͠d̴͕͊s̸̺̾
Beneath an image of strange fucking hands.
That’s not a handout photo from Midjourney, so it’s entirely possible that with so many problems, it was used intentionally to convey the state of the art in a way words can’t on this topic.
I’ve definitely engaged in some editorial shenanigans when I knew a source was full of shit but didn’t have the option of spiking. I’ve also intentionally run such pieces with a recast angle subtly calling out the bullshit.
I know that when I’m playing cards in a dress that’s melted into my skin, with my favorite half-bracelet draped over my wrist, I love to intimidate my opponent by flashing them two face cards. Who wouldn’t be shaken by the Kinmb of Back of Card and the Quing of 21s? Especially when I’ve already played my oversized red card.
Haha, thanks for the good chuckle. I read this before proceeding to the article.
You can tell it’s not our intrepid card player’s first rodeo, though! The dress melting technique was adjusted to leave the perfect slot for a pendant. That had to be a tweak from a later refinement.
There’s a lot going on with the shapes in that image. It seems like a good example of how the algorithms parse a scene.
She’s obviously playing modded Balatro