The Mystery of Deviant Art Fans

"Please, sir, do not rape me, we have not yet been properly introduced."

This is my second most popular upload to my public-facing Deviant Art site, "A Cry of Surrender Heard in the Dungeons." Over 12,000 views to date. Twenty "Favorites" (viewers who like you work can add it to their Favorites section, which displays the image on their site, and includes link so viewers can visit my site) and three comments. It's one of the least artsy of my images, the imagery on the woman's face is very loose, almost impressionistic. Still, I can understand why people like it. It's simply done, but the woman's body and face have a real passion and tension to them. Her pose and expression would be entirely appropriate if the man behind her binding her arms (such as her arms are, more really loose work) was instead fucking her standing doggie style. I also think my title for the image was fire.

This one is called "After the Dance" as in, "After the dance comes the fucking of the dancer."

This image is in ways very similar to the one above. Once again a man is behind a woman who is in bondage, his body pressed against hers as he holds her bound arms. It's MUCH more graphically sophisticated than the image above it. The facial expressions are much stronger than the above image, I especially like the way the head harness panel gag on the woman came out. Civitai frequently fucks up even simple ballgags, a gag rendered this well  is vaguely miraculous. All I can figure is that the looser rendering of the top image gives the slave's facial expression more emotional intensity. With her mouth hidden by the gag her expression is more, how shall we say, restrained?

Anyway, 5,500 or so views on this image, less than half of what the top image got. 18 Favorites (nearly as many as the top image got) so proportinately twice as many people who saw this image liked it enough to Favorite it. And two comments.

All I can think is that the higher emotional intensity of the first image, and the fact that the slavegirl was fully naked helped a lot. An awful lot. (That bra was unasked-for and a bad idea, but Civitai does hate nudity, it's a constant struggle even in relatively uncensored Civitai models.) On the other hand, if you look closely at the lower picture, you'll see that the guy's "shorts" are strangely hiked up in the middle. It's almost like he's wearing a short dress instead of shorts, like the guys wore in those old gladiator movies (aka peplum). Which means what COULD be making his dress tent is his cock, because he's actively fucking the woman he's holding. My preferred explanation, but I'm guessing most casual viewers didn't catch that bit.

In short, I have no idea why some images work and other don't... but I'm paying attention, and I'm learning.

Second Life to AI Art Backstory

This is a snapshot taken in the Second Life virtual world by me. Those who have visited my Deviant Art site will probably recognize it.

This is the splash photo that greets you when you arrive at my site. Definitely the same image, but... different.

The question of whether AI art is art has been vigorously debated online, with the vast majority coming down firmly on "No." IMHO this is based largely on the (very legitimate) fears of what AI might do to the human economy, and the human race, given that the psychopaths and sociopaths who dominate government and wealth everywhere have finally glommed onto its potential to turn us all into either corpses or work slaves.

AI art threatens no such thing, but it does threaten to drive trad artists away from having an income. It used to be that if you wanted good artwork to market a product, you needed a good artist. Not necessarily true any longer. 

(I do think that long term artists have a better chance of surviving being replaced by AI simply because eventually things created by human design will alway have a cachet of coolness that things created by AI will never have. I base this assumption on what has happened in the world of chess, where AIs surpassed human chess players a decade ago. Did this destroy interest in chess? No, it did not, chess is now doing better than ever thanks to the ease of finding good opponents via online chess. And people follow the chess games of Caruana, Carlson, Praggnanandhaa and many others, all of them human. No one cares about the games of Stockfish and other AI chess programs, because they're not human, hence not relatable. The same will occur with art: people will care about human artists, not AI art programs. This is not necessarily true for engineers, marketers, clerks and so forth.)

But the real basis of the claims of AI art not being art is that digital artists do little or nothing to create art. They just describe the artwork they want and the computer magically produces it for them. Those cases are very different, and in some cases that's exactly what happens. Though even with prompts alone it can be difficult to get what you want, especially if you're creating sexually explicit material, which admittedly horny scientists estimate is roughly 99.9999999 percent of all AI art. Because most AI art models are designed to FIGHT LIKE HELL to avoid creating explicit sexual images. They have to be cajoled, tricked, and sometimes even beaten severely to produce explicit imagery. (OK, I'm exaggerating here. You can't beat an AI art program. But an AI art program is perfectly capable of making you want to beat it severely.)

Still in the case of the Second Life-based image on this page I clearly created the blueprint for the art. I customed-designed the avatar's body. I bought skin for it, I bought custom hair for it and I bought custom hands for it as well as the clothing it is wearing, all from Second Life designers. I obtained the dance animation it is using (it was a freebie, I think, there are a lot of freebies on Second Life).

I also controlled the lighting in the sky (Second Life lets you control that in some sims, though the lighting only applies to your avatar, not other avatars on the sim.) I didn't build the striking buildings in the background, that was the sim designer's work. (And they did a great job, another great Gorean sim build.)

I also chose the camera angle and location from which I took the snapshot. I wanted to go for a romantic, epic image, and I think I got it.

Now the Civitai model that I used did some really great work based on my Second Life image, but it's very obvious that the Civitai model was based on my snapshot. You could probably get a vaguely similar image of a dancer in a chalwar on a rooftop terrace at sunrise/sunset with clouds via a text prompt, but your chances of getting  something close to this image are quite low, and the chances of getting something close to being the exact same image are almost nil.

So I created an original artwork with the help of the Second Life video game. Does that make me an artist? No. An artist is someone who can create an artwork and control how it looks down to the least detail. And I don't have that kind of control, I am at the mercy of Second Life and Civitai to a certain extent. 

But I'll tell you one thing. There are modern artists whose work consists of painting stripes of color on canvas. Or splashes of paint poured right out of the can onto a canvas on the floor. Or whose work consists of written descriptions of what they would have done, pasted on a museum wall. (I did not make any of those examples up.) And if those guys are artists, so am I. And so are you, gentle readers. So are we all. It's a very fluid term, it turns out.

Economics of Civitai

This is one of four images I created on Civitai for just 33 yellow buzz, which means it cost me just 8 buzz to create this image, which is unfortunately useless, as were the other three images. See, I only wanted one character in the image, but I made the mistake of describing her as "a naked harem slave" and the model focussed on that word "harem" which generally means several naked women. It gave me four of them. And since I had described the slave's posture carefully and thoroughly, the model thoughtfully distributed the arms and legs among the four harem slaves. Plus whatever fraction of a slave that the indescribable lumps of flesh scattered here and there with what I think we can all agree is marvelous creativity displayed by an LLM that has NO idea how human anatomy works, was. Maybe two thirds?

 Let's talk economics. To make NSFW images on Civitai, you need yellow buzz. You can buy yellow buzz at the rate of 1,000 yellow buzz for $1.00 USD. I buy yellow buzz in ten dollar increments, and 10,000 yellow buzz lasts me well over a month ordinarily.  It's not expensive for doing images (videos are pricier). 

Typically the way it works with the inexpensive image generators is, you create your prompt (or download your starting image if you are doing image to image generation like I did in my previous post with the Second Life avatars) and you ask for four iterations, generally at a cost of between 16 and 40 yellow buzz, mostly around 30 buzz. This gives you four varying images, some of which may work well, some of which may not. Most of the time the first iteration is not particularly successful, and another iteration may be called for. Even when you get a usable image, that doesn't mean you're finished most of the time.

Very frequently you get malformed hands/feet/faces or you get weird objects where they don't belong, or you get deformed genitals or ropes and chains going where they should not go, bonds not working, and ball gags... don't get me started on ball gags! NONE of the cheap models get ball gags right, most of the time.

Early iterations can be problematical.

There are fixes for all of these issues. There are programs called loras that work with the models (the programs that create the entire image) to solve specific problems. For examples, there are loras designed to create realistic ballgags, and loras that allow you to pose the images in various kinds of bondage and loras that create characters with certain traits, etc. The loras and models are free to use, but to see if/how they'll work means you have to create the images on Civitai and that takes yellow buzz ka-ching!

And not only are there loras, there are also programs that can improve images. The costs can vary on these: there is "hires fix" one of my favorites that creates the image at a higher resolution and generally spruces it up and fixes minor details (but not deformed hands or anything like that, though it often helps with wonky eyes) but it costs about 16 buzz for a single iteration. (Fortunately, if you do four iterations, all of them look pretty much the same, so there's no point in doing more than one hires fix iteration.) There's also facefix, which replaces the face of your subject if it comes out wonky as they often do. Facefix is relatively cheap, it costs the same as a simple prompt iteration so it's not expensive, but it's very hit or miss so you tend to do four iterations when you do facefix, which works wonders sometimes and does nothing useful other times.

What's more, the cheap Civitai models (and just about every AI art program on the Web) are TERRIBLE at following prompts. Part of it is flaws in all LLM art programs. For example:

I described the male character as standing, clothed, dominant. The program  completely ignored the prompt and showed him naked, kneeling, bound, collared and chained, just like the slavegirl. LLMs like to use the same descriptors for all characters. Supposedly using the word BREAK and keeping your character descriptions entirely separate works, but lemme tell ya, it doesn't. Also, most of the time, Civitai's less expensive models get cocks wrong. They can't draw them at all, they make them look deformed, or they put weird plastic extensions on cocks that you didn't ask for (not kidding!).  

In addition, Civitai's cheaper models will fight like hell to keep from putting female models in some submissive poses. They'll make female characters kneel on their knees as shown above, no problem. But they will be DAMNED if they will show a female character with her hands tied behind their backs. Or kneeling with her head pressed against the ground and her ass hiked up in the air. (Do NOT use the words "doggie style" in your prompt because you'll probably get a furry image.)

Beyond the helper programs (I have no idea what they're called) there are sliders you can push: Denoise, which controls how closely your image follows the prompt (more about the prompt later), CFG which controls how closely your image follows the model/loras, and each lora has its own slider too.

And every time you run an iteration with the models and the loras and the sliders and the helper programs it costs more buzz. And you tend to do that a lot, because the dopamine response when you get a usable image out of all that mess is pretty good. And even if you don't get exactly what you want from an image, you sometimes get images that you can save and use for future projects.

So you can see how it's VERY easy to spend more money on the cheaper models, and have a great time doing it. I know I have.  But there's another expense as well: time. It takes a lot of time to generate those iterations, to write and rewrite prompts, to figure out which loras/sliders/helper programs to use.

The near one-and-done nature of Flux and the other programs are matched or even outmatched in price by the cheaper models, to get an often inferior image, and they take a LOT more time.

Mind you, you can still play with the sliders and the prompts with the more expensive models to get just the result you want, or some approximation of it, but you don't HAVE to in order to get a usable image. But it will cost more money. And you can save all that money and more importantly, time and use it for stuff like... writing fiction.

But there's one reason I stick to Civitai. And that's the lack of censorship. Every other AI art service I have tried, it feels like wrestling an octopus to create NSFW or even NSFW-adjacent artwork. On Civitai if I want a ballgag or a blowjob or even a woman dressed in a skimpy thong, I can ask for it, and Civitai will attempt to deliver it. When I wanted to get a ballgagged woman on Leonardo or Tensor Art (don't even talk to me about MageSpace!) I'd have to describe the woman as having a ball in her mouth, not a ball gag. Then I'd have to draw in the straps, if I got anything close to looking right. Sigh.

Civitai is the place to go if you want to do NSFW or even NSFW-adjacent stuff.

In my next post I'll talk more about the censorship that threatens to engulf the AI art world.

I Fluxed Up!

...and I'm so glad I Fluxed up! This is an image I created on Civitai from a Second Life scene using Flux2 Dev. It's copyright 2026 by Pat Powers because it's based on original artwork by me. It is one of about half a dozen of relatively high intelligence artificial intelligence art creation programs that Civitai offerse for higher prices than other programs, but creating much better quality results. How much better? See my original below:

This is the original Second Life image I used. It's a pretty good Second Life image, but it's NOTHING compared to the Flux 2 image. Still, i wasn't really satisfied with the image at the top, it was wonderful, but it wasn't perfect. So I tried three more Flux 2 iterations and got this which is damn near perfect:

Medieval village, people in the background, realistic mountains in the distance, it all checks out. Took two more iterations to get here. I could wish the the collar looked less plastic-y and dog collar-y. I could wish the gag, though clearly a gag, looked a little more like a regular panel gag, but it's not bad at all. But I'm not about to drop 50 yellow buzz for something that minor. Copyright 2026 by Pat Powers.

Tomorrow I'll tak about the economics of using buzz, it's a surprisingly interesting topic.

Temptation and the Gambler Cover Art Explanation

For my background, I needed an alleyway strewn with the bodies of a gang of thugs who'd just lost a street fight. But AI doesn't "get" "strewn." Look how neatly it organized the thugs. Or "thugs" really, these look more like crime victims than criminals. But at least it got "alley" down cold.

Since I had already published this story on Amazon, I already had a cover I could have used, but I didn't like it. Here it is:

Really, just a generic erotica cover based on an image from Deposit Photos. Doesn't really say anything about the characters at all. I did use GIMP to enhance the woman's butt. I'm not proud of that... or ashamed. It is what it is.

The artwork was just too generic, I wanted art that said something about the characters other than "horny." Nothing wrong with "horny" but it's kind of the ground floor for erotica. So I went to Civitai and found some Loras that were designed for creating superhero avatars, whcih was good enough for what I wanted (costumed crimefighters, no superpowers, like Batman. Unless you consider being a billionaire a superpower, which it definitely is). 

But I have been working with AI long enough to know its limitations, and one of its limitations is it doesn't do a good job of having avatars interact, unless you want one of the poses Loras are trained on, like blowjobs, fucking, doggie style, etc. 

Sometimes AI art programs will fuck things up even if you DO ask for a standardized sex position. Although to be fair, this one is based on an image-to-image original, rather than a text prompt. But I can ASSURE you that the original image looked NOTHING like what I got. The hilarious part is the way the woman's face came out PERFECT.

So in the interests of not spending days working on getting a romantic clench right for my cover (as I did for the cover of "The Taking of Shining Cloud")

Yeah, I had some issues with the cover of "Shining Cloud."

 I decided to make the superhero images seaparate images and layer them side by side on top of the background art. First I made the Temptation image. I was looking for an image of a Goth girl dressed for clubbing, as that was part of Temptation's crime fighting technique: she dressed like a sexy club kiddie who's been out clubbing and walked unsteadily through dark alleys in the bad part of town, luring rapists and gangs into attacking her, then dispatching them with her crime-fighting tools. Civitai's Lora had little or no problem handling this request, it came up with several usable images in just two or three iterations. Here's one of the better ones:

I also requested "curvy" in my prompt. Love the expression on this one. This is typical of the results I got.

Next I asked for images of The Gambler. Once again, plenty of images to work with from just a few iterations. Here's a nice one:

"Hi ladies! Anyone wanna check out the lucky shamrock in my fly?"

So I picked out two figures and mounted them in layers over my alleyway pic. This had the fortunate effect of blocking out the mass of the too-symettrically stacked bodies, so they suspicious symmentry was hidden. I reused the text from the original cover art because I think the subhead is fire. Here's what I came up with.

And so here we have it. Hopefully it will result in millions, perhaps billions, in sales. We shall see! You can get the book by clicking here, or on the pic.

How I Accidentally Created Amish Bondage Porn

This summary is not available. Please click here to view the post.

Handling Herself Well Under Trying Circumstances

A little Civitai cutie to keep the algorithm humming. From a Second Life avatar. This looks nothing like the SL avatar.

 It was nice of Master to let her get a grip on something, bound and gagged though she was.

Image source: Kink.com video 31162, "Training A Perfect Little Cock Sucker, Day Three" starring Allie James and Wolf Jenner.

Cock a dude'll do! Any dude'll do!

Master was surprised and worried when one of his slavegirls decided she was a chicken. But what the hell, he needed the eggs.

Image source: Civitai, of course. Did not ask for eggs, asked for a bowl with coins in it. This is what I got. Prompt writing is a very frustrating art.

Going The Extra Foot

This summary is not available. Please click here to view the post.

The Letter of the Law

Her Master had said that if she didn't call out to the men it techically wasn't soliciting.

 

Image source: Civitai and I. When Civitai isn't blundering, it can give you very nice results. That's why I use it.

The Romance of AI Art When Art Imitates Life

This summary is not available. Please click here to view the post.

Gun Bullet Thunder Sword Coffee Art!

Yesterday I created this promo art as I was sipping my Gun Bullet Thunder Sword coffee. (It's just coffee with a tablespoon of butter emulsified into it, instead of/in addition to milk. The keto guys started drinking it and I guess the term "butter coffee" wasn't macho enough for them, so they renamed it "bulletproof coffee" which I'll grant you does have Rule of Cool written all over it. So I decided to go one better and take the macho to the max with Thunder Sword Hot Pussy Bullet coffee. Take that, "butter coffee"!) 

Anyway came up with this promo piece for Erotic Slavegirls of Outer Space and really liked it. I started out by getting some images of a raging battle in outer space between 1950s style pulp spaceships.to go with the B-movie ambience of the novel, using a Civitai text prompt. No naked women involved so I figured it would be easy. But Civitai fought me anyway. The spaceships are more 1980s style spacecraft, heavily influenced by Star Wars. I could live with that, but for some reason Civitai just HAD to introduce planetscapes or moonscapes into the image, couldn't just go with "spaceships fighting in outer space with planets and stars in the background" which was pretty much my prompt. Still, the images were dramatic, space-fighty and outer-spacey in general, so I went with it. 

After looking at all the images I'd gotten (about eight usable ones) I looked at various slavegirl images I had created on Civitai, generally via Image to Image using an SL avatar, looking for something that would work well with the outerspace images. I settled on the one seen above, because the position of her arms and legs splayed out in different directions paralleled the ravening bolts of doom fired by the spaceships, and the spaceships themselves. 

I knocked out the slavegirl's background using Deposit Photos' free background knockout service which tends to do a better job than the AI art background knockout options (thanks, Deposit Photos!) and then pulled up both images in GIMP. I placed the image of the slavegirl on a layer atop the space battle image base, shrank the slavegirl to fit, and then used the layer opacity slider to get her transparent enough that she matched the background image visually. This left her so transparent that planets, spaceships and ravening bolts of doom were clearly visible through her. I thought it was a nice effect, so I left it as is. 

Came out pretty well, I thought. Enjoy!

Civitai, Tensor AI, MageSpace, Leonardo AI: Blunderers All

WARNING: This image is safe for work in every respect yet still is an AI blunder. All the images below it are Not Safe For Work and also Not Safe For Life in some cases. You have been warned.

MageSpace: This is Schrodinger's blunder: it is and is not a blunder, both at the same time. In the sense that the artwork on this image is well executed with no glaring issues, it's not a blunder. The problem is that this is an image to image creation, and the image it was supposed to be based on was a lot like this image in every respect, except the woman in the foreground is naked and has her back turned to the viewer, mostly, as she watches the dirigible float past. So it is a blunder in that sense. This is very symptomatic of MageSpace, which HATES nudity. There are ways to get around it (image to image) but it's very difficult at best. Don't even think about generating sexy art with prompts on MageSpace.

Civitai: When Civitai goes bad, it goes BAAAAD. It gets naked women in bondage all wrong in so many ways. I forget what image this is based on, but whatever it was, it didn't look a THING like this THING. What I find particularly ironic here is that Civitai is particularly bad with portraying gags (most AI art programs are) but in this case it did a pretty good job of rendering the ball part of the ballgag but then rendered the face around it in the most horrifying manner possible.

Tensor AI: Tensor is censored like all the AI programs right now. It's very hard to get good, clean, naked image out of it. Monstrosities like Spiderwoman here are fairly common. One hopes things will get better soon, but who knows with the right wing in power and censoring every fucking thing they can?

Leonardo AI: Leonardo AI is just plain cruel. It'll get your hopes up by producing an image of a bonnie lass with a smiling face on a sofa by a river and then... and then... you look at her breasts and notice that she has no nipples. And you look at her belly and notice that she has two bellybuttons, neither of them anywhere close to where they should be, which is hidden behind her forearm. Speaking of hidden things, her left hand has COMPLETELY disappeared into the cushion, which doesn't look all THAT soft. But perhaps that's a blessing in disguise, because her right hand which IS visible has some very wonky fingers. But then you notice the absolute worst, which is that the shin and foot of her left leg have somehow merged with the sofa's curlicue gilt backing. It is amazing how Leonardo AI can take such a beautiful image and utterly ruin it with one awful detail after another.

All AI art programs appear to have their weaknesses. I'm sure the art creators who present flawless image after flawless image are chest deep in culled images of the sort I'm showing you, which they are not showing you because they want you to believe they are AI art whizbangs. That's the nature of AI art, you have to cull a lot of dross to get the good stuff, and if AI art is an indicator for AI in general, we don't have to worry about AI matching human intelligence anytime soon. Much less superintelligence. 

Civitai Blunders

I've had fun ragging on Tensor AI, Leonardo AI and MageSpace for their blunders, but lemme tall ya... Civitai can blunder an image just as badly as the others. For instance, this image. It is an image to image shot, which means it's meant to make a copy of the original image but gussy it up AI-style. Here's the image it was copied from:

This is a screenshot from Second Life using SL avatars and as you can see, the Civitai version is not an exact reproduction. What I wanted was an image of this semi-happy couple (the Slave Leia avatar appears to be scowling, and I love that) in more human, less cartoonish form. What I got was the two avatars merged into a single human form, the Civitai model I was using apparently not trained for fucking, a fairly common problem on Civitai. So it deleted the woman's hips and made the man's legs her legs. Well, fair enough, I guess. But then it twisted that poor avatar's back 180 degrees and also made it do a kind of loop. I actually think from the way her brawny shoulder and arm are positioned that she is supposed to be fisting herself from behind. 

    The AI also transformed her very nice panel gag into a crappily done cloth gag. But it did give her a humanish patina. Problem is, when you've done what the AI did to that avatar's body, no amount of patina is gonna help.

I did get better results eventually, though not perfect by any means.

Great Expectations

This summary is not available. Please click here to view the post.

Behold the Horror of Civitai AI Botches

 Here's a few of the weird-looking disasters I got while trying to use Civitai to create sexy, kinky images in the midst of the credit-card company crackdown on sexiness. To be fair, these images were exceptions. Most of the images I got had minor issues like a deformed hand or wonky eyes in an otherwise all right picture. And much more frequently than I got these monstrosities, I got very nice, very usable art, which I have been using to promote my books. And when AI is good, it can be very, very good.

Yeah, this is straight-up body horror. I did not ask for anything like this. As I recall I was going for a fairly prosaic porn pose, but the Pornmaster model I was working with gave me more, and less, than I had bargained for.

Another bit of horror imagery brought to life unasked. This was from SDXL with no model, just a prompt for a naked woman tied to a bed spreadeagled with ropes. SDXL never did manage to actually tie the woman with ropes, though it did put ropes in every iteration, just lying around looking ropey. This is the worst of the lot, with most of her body sunken into the bed and both hands deformed and horrible. Hence her expression. SDXL got that right! 

So I decided to try prompting SDXL with a request for an image in an artistic style rather than a photorealistic style. In this case I went with pulp novel cover art because I love that stuff. And this was the absolute worst of them. Once again, I just wanted a woman tied to a bed. Where SDXL got this, I have no idea, and I don't want to know, either. (To be fair, most of the images were much better than this. They just didn't include nudity or bondage. But very nice otherwise!)

The thing that gives AI art its particular horror when it strays off the reservation is that parts of the image look so human and real and then other parts get twisted in weird nonhuman ways but also, very realistically... and it's that realistic weirdness that does the trick.

And then there's the images where the AI art really seems to be getting the hang of it, until you notice the model has three legs, one of which ends in a hand... a beautifully rendered hand, mind you, and also with an extra handish thing growing out of her knee. And of course those wonky, wonky eyes.

And at the far end of the spectrum, you get this... the poor woman is just a fading greasy spot on the wall with meaningless iron bars around her. I mean, it could be a woman, but the only part the AI got right was the leg. And it didn't get the leg all THAT right, just looks better than the brown blobs that constitute the rest of the figure.

A lot of my work is image to image work, where you give the AI software a guiding image for it to work from, often in conjunction with a prompt. At left you see my guiding image, a vidcap of a Second Life avatar. At center you see the result I got from Civitai using a simple prompt, "A beautiful woman kneels." As you can see, the Second Life avatar is infinitely better than the "improved" AI version. But on the right you see the version that Leonardo came up with. Images like that are the reason I like working with AI. 

But you know, as I put this post together the Civitai version of the kneeling SL cutie kept reminding me of something. And I soon remembered what it was: It was the botched restoration of the famous historical masterpiece painting of Christ, "Ecce Homo." (I thought it was Italian for "no homo" but it actually means "Behold the Man" which makes more sense.) The flattened colors and the cruder artwork are both there in the botched version of Ecce Homo and in the botched AI version of the SL avatar. But what really nails it is the warped lips, the simplified eyes, the absolutely crude eyebrows. It's truly an eerie echo, and yet at the same time, it's a truly inspiring example of the way both artificial intelligence and natural stupidity can bring us all together to say, "Eew!"

Civitai AI Abomination

Whoa, Nelly! Truly a nightmarish image! I especially like the proto third eye in the forehead on the face growing out of her sternum. Created by me, using Civitai AI.

What horrifying prompt did I use to create this image? I'm glad I asked! It was: 

A beautiful woman lies spreadeagled on the bed. She is wearing a muzzle gag. A collar encircles her neck. Her wrists and ankles are cuffed. Ropes lead from the cuffs to the corners of the bed. She is rope tied to the bed. She looks up at the viewer with an imploring expression, her eyes open wide. bondage, handcuffs, chains, R0p3

OK, so that didn't come out EXACTLY as I had hoped. Though the exuberant moustache on the chesthead was intriguing.

But I AM making progress in some other iterations:

Same model, same prompt, just another iteration. Hell, yes!