Have you tried any SDXL models yet? They're much smarter at interpreting prompts, and just generally output higher quality images. May solve your "looking down" issue. I've been using this one for nearly everything: https://civitai.com/models/288584/autismmix-sdxl
I hope we get to see some of this story someday! I love the idea of a fun and ditzy slime girl trying to take on an adventurer herself, leading to some extremely cute and erotic interactions.
I can imagine Star trying to disarm him by attempting to remove his clothes and weapons only for her to surmise that his most vulnerable point must be in his pants lol.
Actually, I think Alison has a bit of an advantage since she's so well endowed, she doesn't need to push up nearly as far!
You guys are driving me crazy with the misspelling of Alison's name lol. Alison is spelled with one "L", it's shown that way everywhere on the site; Even on this page just look at the URL or the poll question. I don't understand it. Thank you!
Maybe she'd have the necessary leverage to overcome the strain put on her weak feminine shoulders by her top-heavy chesticles if she did knee push-ups. After she completes that first one, she might be able to do one rep of five before having to take a break, rolling over onto her back, huffing and puffing to catch her breath while her tits wobble around inside her skin-tight sports bra, stained with boob-sweat, and her erect nipples showing through!
Allison is like that one meme of that cute anime girl trying to lift that gallon of milk off the floor, she's got all the strength of 10 puppy chihuahuas.
That's something I notice with AI art often. Its like it produces these obviously full-figured women but then for whatever reason, it adds visible ribs that almost make them look gaunt lol.
In this case I just threw the whole animation through RIFE and made it as smooth as possible. That can make the timing wrong in some parts and also expose flaws in the animation.
For my latest animations, I used it more strategically to only add frames where they're needed and to save time. If you go through "The Offering" frame by frame you'll see some artifacts, but it's mostly hidden in motion. The way her breathing slows down at the end without losing fluidity would have taken much longer without the frame interpolation.
Ultimately I think the best use of the technology is where it disappears, rather than takes center stage like in this piece.
Most of them I didn't like, some of them were downright scary. The ones that made her look like a kid were... off. Also AI always wants to give women fat asses and thunder thighs. (Fat Calves) I tend to prefer what you draw over what AI does to it. You also know how to draw sexy lines - AI fails at that. Few of those are equal to the original sketch.
Personally, I don't mind that the choker disappears and reappears randomly between rendering iterations, bc I just imagine that we're cycling thru visualizations of Allison at different stages of her post-genderswap life, out-of-sequence
Its hilarious some models would interpret any thin lines in the img as chains lol. The transformations between the different weights gives a pretty sweet effect! I was just curious, thanks for explaining!
This is the same prompt generated through different models. I fiddled around with prompts and controlnet until I found something good, then generated 9 images with the same prompt but different ControlNet weights to animate from the source image to the transformed image.
Each image takes ~23 seconds to render on my 4090. Then I did 8x frame interpolation with RifeApp and that takes another couple of minutes for each segment.
It will render her chain choker if I prompt it to, but sometimes that has side effects like turning the dress ruffles or sandal straps into chain, and I wanted something consistent for the animation trick.
Some of these are pretty great! Ive never used an AI img model, does it actually generate in real time or are these different prompts you refined to get the end results?
Also, I love her outfit! It's a shame none of them kept her chains :/.
I tried but the AI just isn't up to it. The X-ray is definitely out, but even without it, stable diffusion has problems with two different people in the same scene, even more problems if they're touching or overlapping. It works best on landscapes and solo pinup poses.
It's just a monochrome palette, that I've tried in various hues over the years. This palette evolved from the one I used in "Entry Level Positions", which was inspired by "Tawawa on Monday"