My Chat GPT doesn’t do images :(. But here’s some nice ASCII art it made for me:
It’s indistinguishable from the posters!
16K resolution.
Godzilla’s Dump 💩
Maybe it’s taking a picture of Godzilla’s face and shoulders, converting it to black and white (not grayscale), and then doing an ASCII representation of that. A dark Godzilla on a light background would look sort of like that after an unsophisticated conversion to black and white.
I doubt it’s doing any of that. It just predicts text
I’ve lost track of which versions just generate text and which ones generate pictures too.
GPT-4 can accept images, but not generate them. However it can go to Dall E 3 to generate and help you prompt it
I wondered if it was starting with the top but then it’s length limits kicked in and it decided the response was getting too long, so it jumped to the conclusion.
Godzilla, eaten by a boa.
That picture gets more disturbing the longer you look.
This is Where’s Waldo: Chernobyl Edition
Enjoy the wonders of acute iodine deficiency due to radioactive effects!
When I tried it, it sent me an absolutely insane (and invalid) base64 PNG, before handing it off to dalle to make the actual image:
Also dall-e has no respect for city intersections
Found him!
Are those birds or airplanes? Yes
The most dashing couple at the entire beach
Damn, look at the legs on her!
That person on the blue beach chair got brutally ravaged by some creature, or was the sacrifice in a dark ritual
deleted by creator
Dude’s like 15 feet tall.
lol, the Waldo being obvious isn’t the weird part. Take a look at those messed-up people.
The funnest part of a Where’s Waldo drawing to me was all of the interesting detail in the other things that were going on in these scenes. It’s funny that not only did it miss the main purpose of the drawing style, but it composed an image that actually looks worse when you look at it on the detail level.
