One thing I've noticed after seeing a bunch of Stable Diffusion images pop up on Pixiv is that it seems to have a distinctive style. Obviously not unique to neural nets but it does make me wonder how much of that is due to a biased choice of input images or published outputs and how much is part of the trained core. Basically all the women have this "polished porcelain doll" type look which to me somehow feels more like a "lack of style" to be honest. I'm sure part of it is selection bias from knowing human artists with a very distinct style (Shadman or Dandon Fuga anyone?) but even the similar-looking human-drawn images often feel bland and forgettable.
AI in the NSFW world ? \ Test : Using NovelAi to generate NSFW image
- Thread starter cornxxx
- Start date
Was playing around with stable diffusion. I say if you can retouch the art you could make a full AI anime waifu AVN. It can't do western art to save it's life. So western artist rejoice, your job is safe (for now).
I'll take AI art over the crappy DAZ3D models any day.
Hi, i will like to know how you got those AI images? Did you use your image as a prompt and added a few things, im curious about what tags you added or what you did to make it look that good!
I'm in the same boat.
I spend several hours editing my images on a graphics tablet / photoshop. I'm not an artist but there's an unreasonable amount of hate towards AI that those of us who edit are going to be roped into the same boat as people who just pump out whatever and go with it.
Last edited:
I'm 100% positive AI art will replace traditional methods for visuals (3D and 2D).
That goes for many art forms.
It's just adaptation. You'll still need to figure how to make art, backgrounds, etc.
I don't think AI will be able to efficiently create an environment out of nothing and pair it with character on various angles successfully.
Pretty much a glimpse into a future.
4-6 guys in a couple of months.
Watch full mini movie. It's awesome.
My guess precision for hands, smaller details etc. Will be perfected in a year or two.
In 5 year technique to create games/animation or even movies will be widely used.
Why?
Top visuals, top creativity, fast, stable (no mood swings, always can be counted on) and most importantly, cheap.
Anybody will be able to create avatar movie by himself and a couple of friends in his backyard and green screen.
That goes for many art forms.
It's just adaptation. You'll still need to figure how to make art, backgrounds, etc.
I don't think AI will be able to efficiently create an environment out of nothing and pair it with character on various angles successfully.
Pretty much a glimpse into a future.
4-6 guys in a couple of months.
Watch full mini movie. It's awesome.
My guess precision for hands, smaller details etc. Will be perfected in a year or two.
In 5 year technique to create games/animation or even movies will be widely used.
Why?
Top visuals, top creativity, fast, stable (no mood swings, always can be counted on) and most importantly, cheap.
Anybody will be able to create avatar movie by himself and a couple of friends in his backyard and green screen.
- Sep 13, 2016
- 3,540
- 7,058
- Feb 16, 2021
- 101
- 297
- Sep 13, 2016
- 3,540
- 7,058
what all these renders have in common is they're not adding anything significant to the original. if you had rendered the game with the first image, then tell your subs you used months to re-render everything with the AI, they'd be incredibly angry for wasting so much time with negligible improvement.
ie. the AI is only adding another layer of work without adding content. more work in a job that already burns out 99% of devs before v.03.
I'm sure many of us have already done the same basic mistake by re-doing old renders which for some small reason bother us. and after using days or even weeks to fix that issue, NOBODY but us can tell how it improved. yes the result is technically better, but not so much that people would notice. could've used all that time to make new content instead.
ie. the AI is only adding another layer of work without adding content. more work in a job that already burns out 99% of devs before v.03.
I'm sure many of us have already done the same basic mistake by re-doing old renders which for some small reason bother us. and after using days or even weeks to fix that issue, NOBODY but us can tell how it improved. yes the result is technically better, but not so much that people would notice. could've used all that time to make new content instead.
- Jul 30, 2017
- 2,086
- 3,237
Too bad you didn't add a poll to the thread with your question. I would vote yes. AI generated art and NSFW porn definitely do have a strong future IMO.
Pretty easy, though I haven't used it in a while.
Try starting with these prompts:
Cowgirl
(1girl, 1boy, penis:1.25),[full_body],nsfw,(girl on top, breasts, navel, spread legs, pussy, ceiling, looking at viewer:1.6), (pussy, sex:1.3).
Missionary
(1girl, 1boy, penis:1.25),[full_body],nsfw,(missionary, on_back, breasts, navel, spread legs, pussy, on_back, looking at viewer:1.6), (pussy, sex:1.3)
From Behind
(1girl, 1boy, penis:1.25),[full_body],nsfw,(pov,sex_from_behind,ass,back,pussy,looking_away:1.6), (pussy, sex:1.3)
To be honest, I like your drawings much more. Let's take a look at the last photo, for example, a man lifts a girl's skirt, the girl is shocked, and her friend next to her gives a surprised reaction when she sees that she has no panties. so there's a storytelling here. In the AI drawing, all these details are lost and they all look alike, far from being original.Do you think that AI has a future in the NSFW world?
Either in a hentai that would have been partially generated by an AI or in a game with an AI that would have generated
graphics part such a sprites/drawings ?
A few months ago, this seemed obviously impossible to me as I guess everyone else, it seems that today with the technological progress this thought could change.
Today I'd like to talk about this.
It's been several years now that I'm passionate about AI, especially in a technological way, but apart from a few projects that stood out like the creation of autonomous text with GPT-3, we didn't really think that AI could more or less revolutionize the world of NSFW (at least in this context of NSFW, in reality it has helped a lot in other areas such as SEO for example).
In short, as you probably noticed especially this year 2022 has been rich in the development of this niche, with the arrival of several impressive project this year, I speak obviously of the generation of image that can be realized with only one sentence.
We finally had the arrival of "DALL E2" which was quickly copied by several alternative such as the most known "Midjourney" or more economically "DALL mini".
But obviously always in the context of NSFW, even if Midjourney & Dall E2 proposed beautiful and impressive images, the images of anime and manga characters remained sometimes to be desired and obviously the NSFW tags were blacklisted not allowing to create all the things what we wanted.
But still thinking maybe this business will develop in the years to come, I discovered a new project, the NovelAI one (You must be registered to see the links)
It's been 1 day now that I know this project, so what I can say about it is that it's also an AI that generates images like Dall E2 / MidJourney but only this Ai is directly inspired by Manga and Anime characters, allowing more and more successful images in this context, and of course what I noticed is that NSFW terms are not blacklisted!
So I'd like to know your opinion on it, in this context I'll show you some pictures of my curent work in progress game that have been really drawn by me (so a human)
and what the AI of NovelAi has reformed these images
HERE IS THE ORIGINAL IMAGE MADE BY ME FOR MY GAME ( SO DRAWN BY A REAL HUMAN )
-
-
HERE ARE THE ALTERNATIVE PICTURE THE AI GENERATED ( SO DRAWN BY THE AI )
-
-
-
-
HERE IS THE ORIGINAL IMAGE MADE BY ME FOR MY GAME ( SO DRAWN BY A REAL HUMAN )
-
-
HERE ARE THE ALTERNATIVE PICTURE THE AI GENERATED ( SO DRAWN BY THE AI )
-
-
-
-
HERE IS THE ORIGINAL IMAGE MADE BY ME FOR MY GAME ( SO DRAWN BY A REAL HUMAN )
-
HERE IS THE ORIGINAL IMAGE MADE BY ME FOR MY GAME ( SO DRAWN BY A REAL HUMAN )
-
-
-
-
And of course this is just only the visible part of the iceberg, for this test, I just asked the AI to replicate my drawing, but it is also possible to ask to be inspired by the image and to add things to the sentence
So what do you think of it ? I think in my opinion this is a great technological evolution, which evokes both the immense evolutuon of AI, maybe make me feel a little bit of scariness, I feel like this can go wrong in many ways
I think this hatred is absolutely not unnecessary, people spend months or even years trying to learn to draw. And then it's frustrating that a few AI users come out just types two commands and talk about art in an offensive and disrespectful way without knowing anything. you can see many examples just a few comments up
God, I wish it was as easy as you make it out to be.
In any case when it comes to indie devs, ai opens up possibilities for new games that would otherwise never be made.
Ai also makes it possible for me to draw my own pictures, throw them into ai and have them come out looking better.
As well as make the wait for updates shorter.
Even if I just typed a prompt like you said, forgetting a lot more goes into it than that, I still spend several hours sometimes two days photoshopping and editing almost every image I use.
There are "artists " who use real world photos that they found via Google /etc and photoshop them into different images. How can you justify that being ok when I'm essentially doing the same thing just with ai images as the base instead of stealing images off Google?
you misunderstood me, using ai in any project is not wrong. but whenever people using ai try to sell them without explicitly saying it's not ai, or start disrespecting real illustrators then that's a problem. To give an example, a youtuber named samdoesart has developed an artificial intelligence to draw in his style even though he has repeatedly said that he does not want to, and they sent him emails that make fun of him, do you think this is ethical? The hatred towards artificial intelligence drawing generally comes from such situations.
Also, a human using a reference and an artificial intelligence using a reference are two very different things. For example, there are artificial intelligences that make music, and they only use copyright-free music, but ai artists do not do that. or if a real illustrator wants to use a drawing style, they have to work hard for it and in the end they add their own style. sometimes using the style of something else is the job itself, for example, an animator should draw according to the style of the animation he draws while drawing. so using references for self-improvement and using copyrighted stuff for commercial purposes are two different things.
Fair enough. I fully admit I use AI to do my "art". And regardless of the fact that I spend hours photoshopping my images (and sometimes re-drawing portions), I still don't call it art.
At best, I'd call myself a digital editor.
Who's they? I'm not sure I followed what you said, sorry. But I did see a model labeled "samdoesart" up on civitai supposedly created by the creator. Then it was removed later. Dunno what the story behind that is, but I have 0 intentions to download models that specifically follow an artists art.
One of my favorite artists is Luis Royo, but I don't intend to steal his art style.
Mix his art style with other styles maybe, but I wouldn't want to blatantly take it for myself. It's more of a preference than a morality thing, though.
No, I'm referring to art where people merge real photos and photoshop them / edit them/ filter them so they look like they were part of the original photo.
Here's an example:
You must be registered to see the links
This is an image that AI generated for me,
Now here's (the sfw version) of what it looked like when I completed photoshopping it:
You must be registered to see the links
The half-pipe is a real photo of a half-pipe that I edited in.
The hands are also real photos of (my wifes) hands that I edited in. I did use AI to do the nails, though tbh I probably should have just stuck with what I had originally.
The skateboard is a real skateboard but I did it very wonky when editing it in so it looks goofy (I'm better now). The leg redrew, lowered the brightness to add a stocking, the guard rail is TECHNICALLY drawn, but I did use the stamp tool and stole it from a different (real) image. The hair was just me playing around with Hue's in photoshop. Redrew the mouth.
Then because the hands, half-pipe and guard-rail were all 3d and didn't match the anime, I blended them a bit in photoshop. I'm better now and could make this look a lot better, but it was an easy example because I changed quite a bit.
Before AI this was a common practice and still considered art. But now if AI is in any way related, people get angry.
Anyways, not intending to argue with you, just bringing it up as a point.
Edit:
Here's a better example. This guy is obviously way better than me, but he used real pictures of rocks / animals / etc to create this doom inspired picture.
A lot of people will use copywritten art that other people made, but because they're modifying it to an extreme it is technically legal and I haven't seen anyone get too upset about it.
You must be registered to see the links
Is it really that much different from Daz3D games that mostly just load premade assets and move around models?
Compare to devs who sculpts their own 3D models and environments which takes x100 more skill and time.
Why nobody showing hatred to that?
With AI art you pretty much do the same.
