1
« Last post by redhome on Today at 06:18:20 am »
I know its a little off topic talking about AI, my feeling are sticking about it specially to just for ppl that think they are arts when there really not. Im a high beliver that anyone can draw and be arts, we improve over time, I havent spend 20+ year drawing just to see other ppl using AI to call them selfs arts. Many ppl specially arts are againts it. AI is super easy to know when its use and I do hope it dosent come a "tool" like u just stated.
Using AI for this type of things I dont fine much of a problem, I cant control u or aint ur mother. I know ur just using AI to "provide" nw stuff and imo restore art I have no problme with how ur using it in this way. Viper already ran its peak and dont think it would come back... and thats a maybe, I really have no idea.
Im a old school arts, paper and pencil and I really dont sell my hand work even tho I do digital I rather not at the moment, I rather improve my own skills even more as well my art style but thats me talk.
As long as ur doing it for the love of the what u like (Sogna) and doing it for good motives and I do think I can hope to see more AI stuff, ppl still do fan art of Sogna characters even tho fue ppl know about the games in general, but ppl still draw some of the popular characters after all.
just do what U wanna do with AI and hope to see some good stuff and well dont benefit and call it ur own art, do hope I make a little sences.
I think I know what you're getting at - and understand your point. The question is: do you think digital art is art? Or is "pen and paper" art - everything else is "easy", because of low effort. You see, digital art in itself (see Photoshop, Krita, Affinity etc.) are also tools that support the artist - or allow others to create art (not sure, if there is just one definition of art - or if art is the process of creating something that wasn't there in the first place?). In any case the world turns. Which means there are people who love art that was created (and mastered) in real life. Others do the same with art that was solely created with digital tools (see above). AI art is also art - and believe me when I say that you can spend countless hours to perfect "AI art", because the AI output is not always what you want, but something that was created by your "prompt" - but doesn't match your imagination. That gets me back to the "tool" - AI (in the sense of AI image generators) are tools you can use to perfect your own art. But it's not limited to that and that's the beauty of that technology. People who just enter "Big titty goth woman sitting on a chair, style of Leonardo Davinci" and then print that on mugs and sell it, is very low effort. But AI can do so much more. And that's why I think (personal opinion) that it will become much, much more in the future. I suggest looking a bit at the Krita Diffusion plugin I mentioned in my first post. It's really magical - and if anything AI can help with shifting the perspective and then do it by hand. This doesn't invalidate any real artists effort to do it "by hand" or get better at her/his craft. But the world is not black and white, I think that is what I am trying to say. 
2
« Last post by Saika on Today at 05:46:17 am »
Wanted to take up 3D sculpting,
its gonna be a while until a get good, though. I need more practice.
A WIP Cala sculpt, and a WIP Maranello sculpt.
Practices makes perfect, only way to get better is doing it over and over again. HOPPING SUCCESS and wish u all the power of good luck and wating for it.
3
« Last post by Saika on Today at 05:44:40 am »
As I said, it's a controversial topic. I am with you on the "selling part". This thing for me is very problematic, too. The part where it's about a tool that supports the artist - and let's be real, in a few years AI will be standard in most tools we're using on a day to day basis - I am fully pro AI. It should be a technology that helps, but everything that helps can also be used for "other purposes". Hence the selling part (of artwork from other people).
For me the VIPER series is something that I used to know (a lot better) a few years ago and just got back too, because of nostalgia. I also collect old stuff from the Nintendo (NES, SNES - Famicom) era. There too is something called "new retro". Which is basically stuff from the old days, but new. This includes certain art styles (in games or cover artwork, which wouldn't be created nowdays anymore, because there is no big market for it - see "Limited Run" (and others)).
To me this is more of an experiment and maybe for showing what's possible. Without looking too much on the positive or negative side.
I know its a little off topic talking about AI, my feeling are sticking about it specially to just for ppl that think they are arts when there really not. Im a high beliver that anyone can draw and be arts, we improve over time, I havent spend 20+ year drawing just to see other ppl using AI to call them selfs arts. Many ppl specially arts are againts it. AI is super easy to know when its use and I do hope it dosent come a "tool" like u just stated. Using AI for this type of things I dont fine much of a problem, I cant control u or aint ur mother. I know ur just using AI to "provide" nw stuff and imo restore art I have no problme with how ur using it in this way. Viper already ran its peak and dont think it would come back... and thats a maybe, I really have no idea. Im a old school arts, paper and pencil and I really dont sell my hand work even tho I do digital I rather not at the moment, I rather improve my own skills even more as well my art style but thats me talk. As long as ur doing it for the love of the what u like (Sogna) and doing it for good motives and I do think I can hope to see more AI stuff, ppl still do fan art of Sogna characters even tho fue ppl know about the games in general, but ppl still draw some of the popular characters after all. just do what U wanna do with AI and hope to see some good stuff and well dont benefit and call it ur own art, do hope I make a little sences.
4
« Last post by redhome on Today at 05:19:42 am »
As I said, it's a controversial topic. I am with you on the "selling part". This thing for me is very problematic, too. The part where it's about a tool that supports the artist - and let's be real, in a few years AI will be standard in most tools we're using on a day to day basis - I am fully pro AI. It should be a technology that helps, but everything that helps can also be used for "other purposes". Hence the selling part (of artwork from other people).
For me the VIPER series is something that I used to know (a lot better) a few years ago and just got back too, because of nostalgia. I also collect old stuff from the Nintendo (NES, SNES - Famicom) era. There too is something called "new retro". Which is basically stuff from the old days, but new. This includes certain art styles (in games or cover artwork, which wouldn't be created nowdays anymore, because there is no big market for it - see "Limited Run" (and others)).
To me this is more of an experiment and maybe for showing what's possible. Without looking too much on the positive or negative side.
5
« Last post by Saika on Yesterday at 04:36:57 pm »
As long as ppl are not selling AI...
Same, This is why I'm so annoyed by people selling Viper AI art on the Yahoo Auctions
That stuff should be mocked and reported imo, like I hate Konami (example) cus greed but, I dont go out and buy bootleg playmats. Reason Y I buy original playmats not only cus its original art from the arts but I can get more money out of em IF I need to sell em. Also u suport the orginal thing ur play/Fan off.
6
« Last post by 黒い灯影 on Yesterday at 02:11:07 am »
As long as ppl are not selling AI...
Same, This is why I'm so annoyed by people selling Viper AI art on the Yahoo Auctions
7
« Last post by Saika on May 04, 2024, 11:24:08 pm »
Personally Im NOT a fan of AI.... kinda...
As long as ppl are not selling AI, think AI is there OWN art and or Stealing other ppl art IM ok with it.
If ur using AI to make just art and tos arround to have art of characters and so on or just make art for shits and giggles im ok.
Restoring art also is a good idea like in censored art and so or bumping the art like, if its a half art using AI to get the full picture im down. Really just all thats stuff im not ok, ALWAYS recomand support arts who well do art, the original stuff and so on.
I like it to have just art of a character I like and lacks art, as long as ppl dont sell it we good here.
8
« Last post by redhome on May 03, 2024, 02:47:01 pm »
Okay, so one more post.  Since I am currently decensoring the input images (or at least some of them that have censoring in it), I made one example screenshot to let you compare input to output. It's not a 100% percent match, because the "LoRA" I created is not finished, but it's good enough to just alter the artwork veeeerrrryyy slightly, but not as much, that it looks weird.
9
« Last post by redhome on May 01, 2024, 01:05:38 pm »
I've started seeing some VIPER AI images on Pixiv over the last year or so. (And a few posted here as well.)
It seems to be getting closer, especially for the faces though Cala's unusual hair is rarely done right and the Rise girl's clothing is often wrong or miscolored as I think it tends to confuse the Anne Mitter's uniform with other, similar styles.
I had not heard of anyone using AI to plug in uncensored parts to otherwise original art though. What I'd seen of this before was presumably handmade or used assets from other series copied onto the original. It would be great to see some of this, too to know if it looks any better than the handmade or copy-paste uncensoring.
That's AI for you. AI model training seems easy, but is very hard to master when it comes to getting the right output. Usually, the wrong input (images & tagging) when training models is all that matters (garbage in, garbage out). The things you describe could be "hallucination" by the AI model - or the image creator chose to let the AI have more "creativity", if you will. Although, that term is not really true, since it's all about statistics and noise (in the AI latent space). In the post above I tried to explain the "burn in" effect. It's good to have this, to get the character (e.g. Cala) right, but it's bad, if the burn in is too strong. If it's too strong, you will always get the same outputs no matter what you "prompt for". (e.g. "Cala in a bikini, on a mountain, sunrise in the background" - but what you get is Cala in a cave with a monster...). So you need to get something in the middle, which allows for things not found in the source material (to create completely new stuff), but this also means the output may differ (hair, clothing, colors). The training parameters itself may also have a very big impact on the outcome. But this is way too complex to go into detail here. And let's not talk about hands. The Achilles' heel of AI image models.  My guess is, that image models will get better over the next years, but as usual it takes time. Maybe I am not so critical about the output, if the style is the right one - and the characters are (very) recognizable. With or without clothes. I try to get into the uncensoring part with a few screenshots, if I have time!
10
« Last post by redhome on May 01, 2024, 12:53:52 pm »
I knew it was only a matter of time until AI generated Viper images would be done. The days of crude looking and poorly pieced together results from combining existing images and gifs into new gifs and images are practically over lol.
They look great btw! The V16 Rise girls especially; that Karin though  , though I'd say the Cala images from the AI could use a little work. I'm sure I wouldn't be the only person one here who can identify many of the images that have been used/referenced or which characters have been combined. Makes me feel like an expert 
There are at least two possibilities to train an AI image model to let it "know" what to learn and what to ignore (in both cases the source material must be high resolution, which is a real problem when trying to do something like that with VIPER): - Characters/Clothing/Concepts: I need to tag everything in the image - except - the things that should "burn in". Lets say I want to train a character named Karin, we know she usually has twin braids, blonde and long hair, glasses etc. - those things are not described by me, so the AI associates those specific traits always with the character/concept. Things not described by me, burn in.
- Style: The contrary to 1. is true here. I tag everything seen in an image. I don't want anything (except the style) to "burn in", but I like the AI to learn the general art-style, not the characters or anything else in the picture. This way the AI model is later able to generate images that look like VIPER artwork, but can be a lot of different things. I could create Lara Croft using the VIPER V-16 style, for example.
Coming back to your input about Cala: I didn't tag the images properly (see 2.), plus I didn't uncensor the source material. This way I can prompt for "a young woman on mars, moons in the sky" and I will get Cala being "taken" by some monster (because it burned in). It's an early model. But I need some time to refine it. Another thing is making things complicated: I cannot use similar images twice. That means, all images presented to an AI should/must be different, so that the AI model learns the concept (character et al) by seeing it/her/him/... in different positions etc. The Cala base images are different, but the things happening to her are usually the same. That's why you recognize those poses/scenes easily.
|
Recent Posts