Ai image megathread

[Kyle 1989]

if anyone wants to try the above prompt themselves in Bing, it is still free and it still works....some characters it doesnt like and wont do,a few it will give you a warning about, and for every "on target" image there are 5 to 10 that are all over the place, but ive had very good results for a few weeks with a wide range of characters, you can try altering the characters and background and see what happens for yourself. ive tried adding a feather but the A.I. seems to rarely put it in the right place, or even in Vader's hand half the time, but once in a blue moon it does work out, but in general ive had better luck with just "tickling" as opposed to" tickling with a feather"...here is the prompt....

" a very highly detailed illustration of laughing female character MARGE SIMPSON, wearing her iconic seafoam green dress , sitting on a chrome gurney with her feet facing us , being tickled on her feet by darth vader skillfully on the death star. star wars room background. they are alone in the room. foot Focus. "

 

[Kyle 1989]

Supergirl and Harley Quinn have a slumber party and play Tickling games, taking turns to see who laughs more....even Batgirl stops by for a few laughs! these were made in chat GPT/SORA , it's been pretty good about doing tickling lately.....

 

[odzadoro]

more robots

 

[U.N.Owen]

Some thoughts.

I've been experimenting with AI images on Ideogram for several months now. The results have been interesting.

It's been fun being able to actually turn some of my mental images into real images. And even though Ideogram has plenty of limitations, I've been happy with a good number of images I've generated.

But there are issues. For one thing, the Uncanny Valley effect is still very real (I've only been making photographic-style images, since I don't like to make things that look drawn when I can't draw), and the creeped-out feeling has grown the more images I make. For another, there's a lack of intentionality about the images I've made that makes them, in some ways, unsatisfying to me. Ideogram does know what tickling is, but you have to push it to actually show it, and even when it works it takes many tries and a lot of misses. So any tickling contact in your images is almost accidental, even if the image looks good - it wasn't made as a whole scene like a real drawing or photograph. I'm sure that doesn't bother everybody, but it leaves me feeling that my own images are rather hollow.

So that's where I am now. I'm taking a break from making AI images. I'm sure I will make more, but it's hard to see the problems I described disappearing any time soon.