This turned into a minor blog post, don't mind me:
Stable diffusion works best on single character scenes in standard poses. Pinups basically. It's also pretty good at backgrounds.
The issue is that it doesn't reliably understand relative conditional statements or adjectives. So if you prompt it "a blue ball on top of a red box", it will give you that... sometimes - but you'll also get random combinations of red, blue, ball and box. It gets worse the more adjectives and conditionals you add in.
In the case of multiple characters it's almost impossible to apply the conditionals correctly. If you say "a woman with tan skin and red hair putting bunny ears on a kneeling woman with short blonde hair wearing a red leather bustier", you're gonna get red hair on both of them a because that's a common thing and you have the "red" token in there twice. It's also going to screw up normal features twice as much because there are more things in the scene. Even getting a single character that looks good often requires rolling the dice dozens of times because random bits will be screwed up.
I have done some multiple character scenes by inpainting each part individually, but the problem is you end up with a slightly different style and lighting on each part. Plus it's very time consuming. The patchwork look is a problem even on single character composite images, it's easy to accidentally stray into something that looks like a collage or that un-tooned homer simpson meme. The recent gold dress pinup kind of strays into that territory.
Dall-E is better at comprehension but it's proprietry and too large of a model to run on consumer hardware at this time. I'm generally not interested in AI models that I can't run locally and I'm especially disinterested in corporate mandated artificial brain damage. Even if you're not trying to make edgy stuff, unfiltered models are just better because they have a more complete understanding of the world. Even stable diffusion has fallen into the "trust and safety" trap and it looks like future developments will have to be underground.
The control net extension, which I used to make the latest Alison pic, is a major improvement, but it still doesn't solve multiple characters or animations. I think the possibility is there. I could see something being added like a segmentation map where each segment could be given different prompts. Temporal stability has been shown to be possible in things like nvidia's styleGAN, and some newer text-to-video models. At some point you will be able to go from a sketch animation to a perfect render. The capability in the AI model is there, it just needs to be activated appropriately. Similar to how chat-gpt is an activation layer on top of gpt-3.
I've done a lot of AI tinkering instead of drawing lately, and some people don't like it - but I hope everyone can appreciate that this an existential crisis in art. Lots of people are in "anger" and "denial" stages of grief. I've had some truly bizarre discussions on other forums where I try to demonstrate SD's ability to generate backgrounds and they will start picking apart some 3 pixel high blob of a bush in the distance because it's not an exact technical drawing. Like, have you ever seen a painting by a person? Bob Ross? The guy just smooshed his brush on the canvas and it looks great. A bunch of people were upset that netflix made an anime short using AI for the backgrounds - but tons of anime have been using crappily filtered stock photographs and 3D models for backgrounds for decades, AI could only improve this situation. Even big budget titles frequently use painted over photographs because even among artists, very few people can generate an accurate scene entirely from their mind.
A big problem is that a lot of people are walking around without any comprehension of what they're looking at or reading or listening to. They just make value judgements based on surface level traits that, in the past, have reliably served as proxies for quality. There's a bunch of big words here? Must be wr
I appreciate the cracker jack uniform look however her rear looks so inviting, I'd be lying if I said I wouldn't want to take off as soon as we're in quarters.
What sells this panel is the way her facial expressions quickly transition from stunned shock at having such a huge cock shoved into her open mouth to resigned acceptance to just beginning to actually enjoy the sensation of sucking cock -- until the next milestone for her cums when he ejaculates a huge load of his man-gravy down her throat and she has to swallow as much of it all down as she can in one gulp and not choke in the process!!!
To the admin: Please return to this series -- this character is second to Allison on my list of favorites of yours; so, I'd love to see anything more you do with her in the future. Maybe have her give him a blowjob while he's in a business meeting, switching points-of-view where you see her under the table deep-throating his cock but also scenes of what's going on in the office while he's head. Alternately, maybe he's giving a presentation while she's hidden inside the podium polishing his knob the whole time, unbeknownst to the others in the meeting ' til he cums, giving her a huge facial in the process(...or maybe they do know?)
Well, I guess that answers her question about what they will be doing until her father's ship shows up. By then, she should be locked into that body for at least a year...
Holy shit im a girl body inspect order: 1. Breasts 2. Face / mouth 3. Breasts again 4. Ass 5. Critical re-inspection of breasts 6. Crotch 7. Final breast review (with potential for subsequent audits)
Holy shit im a girl body inspect order: 1. Breasts 2. Face / mouth 3. Breasts again 4. Ass 5. Critical re-inspection of breasts 6. Crotch 7. Final breast review (with potential for subsequent audits)
This character reminds me of the Trill symbiont beings from the Star Trek universe (as introduced in the Deep Space Nine series) -- might this one have been so-influenced, or is the similarity coincidental?
That's it, Alison, show how good a little you can be for your daddy and worship his well-endowed cock and demonstrate for him what an accomplished cocksucker you are and swallow as much of his epic load as you can and let him anoint you with a copious facial with what of his offered man-milk your mouth can't swallow!
I hope that we someday get to see Alison get spit-roasted like this by Torin and another male demon (or maybe Valochar winds up being his tag-team partner, instead) -- same for Matilda and her Entry-Level comic boss and a business partner of his for whom this 3-way with Maddy is what closes the contract deal negotiated between said boss and him
I like the earlier commenter's suggestion (penultimate to this one of mine) for animation of Alison's body in order to further sell this image. Now that AI image manipulation has gotten so much better in recent years at rendering bodily animation, could you re-revisit this piece and add some motion that compliment her facial expressions as they evolve from embarrassed self-conscious nervousness to growing admiration of her gen-swapped feminine form and libido emerging from said admiration as demonstrated by her poses in front of a floor-to-ceiling mirror going from almost an adolescent shy virginal girly affectation through clumsily flirtatious coquette to a full-on sultry temptress who's wholly aware of her seductive powers, with her shifting weight on her hips and running her hands up and down her body, turning left and right checking out, as best she can, what she looks like from the side and rear-views, and maybe she even bounces on her tiptoes (or, perhaps she's wearing a pair of extra high-heeled stilettos, which she sashays exaggeratedly while prancing girlishly towards and away from said mirror, catching backwards glances at her backside, admiring the way her shapely naked butt cheeks bounce to the rhythm of her suggestive walk, shown-off as they are by the thongback of those dainty panties that she's modeling. Maybe she even caresses her extra-busty bra-cradled tits, pressing them together to check out her amazing cleavage -- perhaps leaning forward suggestively to further escaate this effect
I dunno why I didn't think of this before, but this image of Matilda in bee girl cosplay reminds me of Final Fantasy's gender-bending Cloud Strife as a Honey Bee Inn dancer!
