Quicksand Fans

I wonder if you can try an AI Remake of the scene from Ikki Tousen Xtreme Xecutor?

sixgunsloaded wrote:...

Some more renders of Susan using my current formula.

the top one is my favorite

~slowly picks jaw up off floor~
These last few batches have been just amazing! 'Wow' barely even covers it anymore. Nearly everything we could hope for in a visual medium, there for the asking, if you know how to ask properly. Which you very clearly do!
And the 'Susans' are the best yet! Gorgeous, all of them! I'm finding it difficult to pick a favorite here since they're all 'Susan'. lol
"Ransom" and "Tar" remind me a little of Eliza Dushku. I love the look of the tar tentacles and the way the black glop is clinging to her.
The expressions and the appearance of thrashing about in "Finaltrap" and "Ransom" are my favorites in that regard. It'd be way cool to see how it handles one of the earlier "Ransom" frames where you can still see her torn pantyhose.
It's pretty funny how it changed the sinking oil lamp in "Finaltrap" to a sinking whiskey bottle. Like she staggered out of the tomb drunk and now she's getting her comeupance for disturbing it. lol
In "Hiddenjungle" I really love what it did with her shirt! It's like she's already floundered shoulder-deep and barely managed to claw her way back up a little. Sorta like in the movie.
I certainly wouldn't call any of these bad because they're all beautiful, but if I had to pick a least favorite, I'd probably go with "Horrible" simply because of what it did to her right eye. I'm assuming that was because of lack of detail in that area in the original?
All are fantastic though! It's very cool watching this medium mature rapidly in the right hands. Thank you!

Small breakthrough today. AI is limited in what it can render from source images due to how complex artwork can be with different subjects and layers. A few people have been wanting to see more renders of Quicksand Artist. I've done some single-character ones shared earlier, but the more iconic ones have been elusive. There are no shortcuts for these - they have to be painstakingly built from scratch layer by layer.

I've recreated The Babysitter. Note that I've edited this version to comply with QSF rules, but I have also recreated the background faithfully in the final version.

and with the version found on DA, it was easy to just crop out the offending part of the image

She's sinking in butterscotch pudding! Tasty, anyway you look at it!

so how does the AI handle pictures from other angles? most of the subjects in the pictures are facing the camera straight on or with a slight angle, but nothing from behind. does the AI not handle it well or are there just not enough source materials to go off of?

Mage.Space released some new fine-tuned Stable Diffusion models. This set is made using the LifeLike model.

So, these models - how are they made? How is such realism achieved? I noticed these last 3 characters all look very similar. Do they use a 3d figure with a morphable mesh, or are they, like, generated from an accumulated library of real faces and physiques? I've read that these AI companies pull from sources all over the internet, referencing both photographic and cgi imagery. (Many times without permission from the original sources. But that's a different discussion.)
Just fascinating because they are so life-like compared to any polygonal figures I've come across, except maybe for Project MetaHuman for Unreal Engine 5.
All gorgeous images too, by the way! Thanks!