But they conveniently leave out that it costs money to do anything with AI. It’s more like “open to anyone with a credit card.” The vast majority of people don’t have computers powerful enough to run generative AI models locally, and even then, server farms with a billion GPUs will always produce better results
This means that people have to rely on corporate platforms where you buy tokens that you use to get pulls at the various AI slop slot machines, hoping you get something decent. The mechanics more closely resemble a gacha game than any kind of artistic process
By contrast, learning how to draw, animate or make 3D models costs nothing. There’s free tutorials and tools everywhere, and you can also just pirate commercial ones if you want
Art was already open to anyone just pick up a fucking pencil
Edit: drawing all the talentless hacks out of the woodwork lol
im not going to take a pencil and personally draw a courtroom sketch of Macdonald’s The Grimace giving live birth in front of a judge
That sounds like a you problem
it sounds like a problem for whatever entity has to draw something like that
Stop kinkshaming
i really hate this reasoning. when people say “i can’t draw” they mean “i can’t draw what I set out to draw” not that they can’t make marks on a paper. People want to make what they have in their head, likely to a level of competence that would be appreciated by an audience beyond their mom, not some other thing that they physically can that will look bad to them and anyone else.
I also dispute OP’s assumption that we can all learn to draw competently, i’ve tried on and off for years with various tutorials and programmes and my brain and hands just do not work that way.
Ask any artist if they are satisfied with their art. They won’t be. That is the nature of the beast. Doesn’t matter how good they are at it.
I have done art on and off for years as well. I would estimate I did maybe a few thousand hours of art in my life. Other people have done literally 10 to 100 times that and they are better because of it. You hone your skills over time. Anyone like me dabbling in art has to accept that there are countless people who put in more time, who are better and who will stay being better because they will keep putting more time in then us.
Using AI, you steal those hours from those people, for a product that doesn’t show what’s in your head. It’s stilly to pretend AI can do that and you know it. If that were true, all the art prompters wouldn’t include the names of existing artists in their prompts.
So yea, put in the fucking time, or get off the field. Don’t be fucking selfish and then try to defend it in flimsy ways.
What’s being stolen when someone uses genAI to make a picture for personal use? In what way is it selfish?
It’s weird if someone acts like they’re ‘making art’, but it’s also harmless.
All of the art that was used to train generative AI was used without its creator’s permission, meaning they weren’t compensated for all of the years of work and study that went into creating it. Then all of that labour was repackaged into a product that corporations are selling at a premium, with none of the money going back to the people who made the creation of it possible. These companies have well admitted that they wouldn’t be able to make a profit if they had to actually pay all these artists for their work. Now obviously, that isn’t technically stealing, but neither is it harmless. I personally know several artists who’ve told me that work has dried up in the years since generative AI became popular, and who are upset that their own work was used to train the machines that are replacing them.
I feel like you can level these same arguments against piracy. I “steal” art without permission all the time; the sum of hours and hours of work and expertise, and I consume it all for free.
AI is going to fuck commercial artists and I’m opposed to that (though it’s a capitalism problem more than it’s an technology problem), but I’ll stand by the fact that an individual making goofy pictures for personal use that they’d never ever had paid for pre-ai is harmless and by no means “stealing”, because nothing is being stole. Same as why I don’t feel guilty downloading a movie that I probably wouldn’t have paid for and watched otherwise.
I mean, yeah, piracy is stealing. I thought most people were okay with it because it’s mostly done with games and movies made by huge corporations who’ve already paid their developers and actors, and thus you’re not actually stealing from artists. I’ve personally never understood the “I never would have bought and watched/played this anyway” argument, because here you are, watching/playing it. But also, I really don’t care if other people pirate stuff, people must have their reasons.
Maybe I’m just going hard on the whole anti generative AI thing because of my personal connection to and harm I see it causing to people I know. But on the whole, considering the environmental impact, the corporatization of the technology, the exploitation of artists, the killing of creativity/critical thought, and the absolutely gross techbro culture that’s spwaned out of it, I just thought more people on this site would be against generative AI in general.
piracy is not stealing, stealing deprives someone of something.
I just thought more people on this site would be against generative AI in general.
I’m opposed to how AI is going to interact with our economy, and hurt artists, but as I’ve said that’s an issue with capitalism far more than it’s an issue with the technology.
I understand the kneejerk reaction against it, but in my mind the tech is out the bag now and not going back in, so it feels meaningless to argue against its existence, especially along lines we as socialists otherwise don’t agree with, like on “stealing IP” or the “soul of art” or whatever.
As always we should advocate for the rights of workers. In a fairer economy, AI would just be a harmless toy if not a useful and productive tool.
“Hey man I need to see all your text and all your images you ever made.”
"“Why?”
“So I can make bad collage-copies of them and write shitty listicles.”
“I don’t want you to do that.”
“Too bad, you put your stuff somewhere I could see it so I already did it and you have no recourse now because the powerful people that made me are above copyright law.”
There is no personal use with this, because the AI was trained on everyone’s stolen information. That is the problem, not the fact that it can make a bad picture because that was done. If the AIs could actually make anything from whole cloth, then we’d be having a different debate, but that’s not what’s going on.
stolen information
Nothing is being stolen. Copying isn’t stealing. I’m a communist, I don’t believe in IP.
Steal from corporations, not form people’s pantries you sick, disgusting fuck.
For real, do you not understand that the corpos are taking everyone’s…EVERYONE’S things and making them theirs, for these garbage bots? That there is a difference between stealing from an individual as opposed to a company? You are gleefully saying that theft of personal property is okay, so long as it’s the big boys in silicon valley doing it.
Sterling fucking socialist theory there, bucko!
And since you clearly need this explained more clearly: stealing from individual artists that honed a skill to the point they can make a living from it is bad, because you are stealing the livelihood from a fellow worker. Stealing form any individual is bad, actually. It really should not be hard to understand this, yet somehow…
Again, nothing is being stolen when an individual uses genAI for personal use.
Artists aren’t losing anything. Their stuff is being copied and regurgitated but they’ve lost nothing.
As I’ve said elsewhere in this thread, I’m absolutely also concerned with how AI is going to impact workers in the commercial art, but the argument that AI is ‘stealing’ is just nonsense for the same reason piracy isn’t stealing. We’re in agreement on the conclusion I think, I just think the argument is poor.
Ask any artist if they are satisfied with their art. They won’t be. That is the nature of the beast. Doesn’t matter how good they are at it.
duh. but “good enough” or “ok this is fine i need to work on something else” are out of reach too.
Using AI, you steal those hours from those people,
lmfao
for a product that doesn’t show what’s in your head. It’s stilly to pretend AI can do that and you know it. If that were true, all the art prompters wouldn’t include the names of existing artists in their prompts.
idk lots of musicians try to copy the guitar tone or whatever else of their influences. what’s in your head might be a copy of styles you’ve seen until you develop your own style… idk what “your own style” maps to in generative “ai”, i’m not here to defend ai or say that the people using it are doing art per se, my whole thing is that I can’t get even remotely close to an acceptable level of competence and it ticks me the fuck off when someone goes “aNy OnE cAn mAkE aRt” or upholds capitalist framings of intellectual property.
I can’t get even remotely close to an acceptable level of competence and it ticks me the fuck off when someone goes “aNy OnE cAn mAkE aRt” or upholds capitalist framings of intellectual property.
In that regard, I do think there’s a distinct difference between sampling (whether a still image, moving pictures, or sound) and using the AI treat generator. There’s plenty of people who can’t play a musical instrument worth a damn, but give them some loops, one shot samples, and sequencers and they can transform the samples material into something new and fascinating. Likewise with visual media.
12tone on YouTube had this interesting argument that samples, rather than being “cheating,” are turning a particular performance in time into an instrument unto itself. Whereas AI is a smudging of all past art into an average. So while sampling celebrates the greatness of a performance, AI reduces it to a Borg-like state.
It’s always sad when I gotta actually block someone from hexbear, but since you are just a larper who doesn’t care about others as soon as you can have the slightest whiff of a treat for yourself, I am not really sad about it.
??? comrade if you see this while logged out, i don’t use gen ai to make visual “art”.
this is only about the misunderstanding that people want to make stuff and can’t because what they want to make is more specific than the head up ass maximum position that anything is art regardless of quality.
i am a professional artist (and maybe this makes me a bit out of touch,) assuming that it’s for personal use and not for profit at all, i would rather have someone take my work into photoshop/gimp/krita/whatever and trace it near directly or make edits to it to fit their vision than have that person go spend money to further refine The Slop Machine. other artists may have differing opinions on this but since generative AI has gotten popular i just simply do not care anymore as long as my work isn’t being fed to train image models. hell, if you’re tracing someone else’s work using tools on paper, that’s still building muscle memory and linework skill and while not the ideal scenario it’s doing more for you than you might think. with generative AI you are paying to generate an image based off countless images that already existed from artists that were not paid for their work to be included in the model. is that…not capitalistic or not at the very least exploitative?
Also a professional artist, and I agree with you. Someone making a collage or a trace from my art, or even just photoshopping it is still practicing creativity. Someone typing a prompt into the art slot machine has no creative process, they aren’t learning anything, experiencing anything, struggling with anything, it’s just empty output. It’s just a “pretty picture” there’s no sense of accomplishment or understanding. One of the most rewarding things in my life is when I draw something and recognise that I flat out wasn’t skilled enough to do that 6-12 months ago.
And this can apply to any hobby or skill, are people so alienated from themselves that even the most basic concepts of satisfaction at self-improvement are seen as outright insults to them?
end-users aren’t necessarily paying into anything other than their own electricity bill. We universally have a problem with the companies profiting at your expense of course, and that might be the more common case.
Those parts of “ai” discourse are tangent to someone’s aptitude or ability to have something that looks how they want it to look and i’m trying to limit myself here to being mad about the position that art is accessible already because everybody can make shitty art that isn’t what they want to make.
deleted by creator
Stable diffusion works and learns on a conceptual level. If an AI model even understands artist tags, bias was trained into the model with a LoRA.
You looked at other people’s art when you learned to draw you thief? Hand over the pencil and come out with your hands on your head
So you are seriously saying that AI has the ability to understand concepts? Waow.
Please educate yourself and don’t spout bullshit, thanks.
Not concepts as we humans operate on, but concepts in the feature extraction sense. You have a gross misunderstanding of how these models work.
Imagine it as how an image detection model learns how to detect images. It extracts features (that are vectors of data that are completely meaningless to humans). Image generation can be somewhat imagines as the inverse of a feature detector, it creates features from noise.
These models are not plagiarizing your work. You teach it the shape a dog is expected to have, and you teach it the color black. Without such thing existing in the training set, it can generate a black dog.
This is fundamental to stable diffusion otherwise it could never work at all.
I mean, yeah this true not everyone can make art up to their desired standards. But everyone can still make art, there’s tons of different genres and styles of art, all humans are gonna have the ability to engage with some of them. Maybe not to the level they’ll become famous for it but they can do it.
Edit: to provide a personal example, I suck at drawing and painting but I used to do actual paper collage art, which doesn’t require you make any images yourself but is instead about the composition of other premade images. With pretty good results.
top one is giving 1990s magic the gathering. sick.
Aw that’s so kool <3 thanks for uploading
but i don’t want to cure cancer, i want to turn people into dinosaurs.
art is in some ways a uselessly broad category, people don’t want to make things generically, they want to make something more specific than that, it does no good to tell me to go make a sandcastle because i can actually physically do that to some extent when my creative desire is for something else.
Okay, but then their frustration isn’t that “art is inaccessible” it’s that they can’t visually represent images in their head to a level they’d deem impressive.
Which is frustrating I guess when you want to make a nice looking avatar for your discord DND game, but you aren’t being denied access to anything. Also there’s millions of fantasy concept art pics for free out there you can probs find something nice looking for you kitsune rogue.
i disagree, based on what people have called “inaccessible” for the last decade+, this is a perfectly fine usage of inaccessible.
Both of those images are great
I also dispute OP’s assumption that we can all learn to draw competently, i’ve tried on and off for years with various tutorials and programmes and my brain and hands just do not work that way.
I’m curious if you’ve tried https://drawabox.com/
It’s set up to be very rote and effort in = results out. If you like studying and practicing that way, it works a lot differently than the typical advice.
drawabox is one of the worst programs for learning something from scratch i have ever tried. That shit is horrible. I am capable of imagining its good for people who already draw a bit and want to get better, but from scratch its horrible.
i’ve heard of that and it looks reasonable but i’m busy with blender things and the feedback loop is more compatible with where my head is at.
So you want an audience to adore you but for work you didn’t put in?
Also what’s competent? Have you ever seen avant garde paintings? Impressionist? Surrealism? Heck you could make your own style based on how your hands do work? There are people that paint with their mouth or feet because they want to put the effort in.
Wanting the reward first is backwards.
what? no, i’m not really looking for an audience for the thing i’m not doing at all. if any of my attempts at developing a skill had resulted in developing that skill maybe i’d be art posting instead of simply not making 2D visual art because i can’t make what i want to.
Also what’s competent?
output matching intent. I can imagine a much higher fidelity image than i have the ability (or neurological patience, probably. drugs pls) to produce which, quoting myself:
when people say “i can’t draw” they mean “i can’t draw what I set out to draw”
and that goes for whatever else. I’m not actually good enough at blender to make what i aspire to make either, but i’ve found something i can make to a level i’m satisfied with and is worth my time, unlike the literal garbage i’d get trying to do it on paper or canvas.
Have you ever seen avant garde paintings? Impressionist? Surrealism? Heck you could make your own style based on how your hands do work?
but spider-man i do not want to cure cancer, i want to turn people into dinosaurs. I made marble paintings as a kid, i’ve seen art that doesn’t look anything like what it’s meant to depict. these things are profoundly uninteresting to me and not what i’d be interested in making. so it’s incredibly fucking rude to tell me to go make garbage i don’t want to make and be happy about it.
Wanting the reward first is backwards.
what “reward” lmao. i just want to look at a thing, and since I can’t make something i want to look at I want people to not claim art is accessible to everyone because that claim is a fundamental misunderstanding of people who can’t make the kind of art they would like to make, and it is literally not accessible to me and a few other people in here who have mentioned repeated attempts at trying to develop the skill and being neurologically unable to.
You said for more than your mother would appreciate which means you are sharing it and/or care what other people think about it. If it’s for yourself than you are only as critical as you need be.
And I can imagine a remote space base on an asteroid but I’m not gonna be upset with myself that I can’t build it. It’s normal to have stuff you can’t do. And then you work towards it little by little aware that you might not get it in your lifetime and you leave it for the next people to do.
So instead of it being about being for recognition from others this is some sort of instant gratification need? Cause I am still not getting what the issue is other than a stubborn need to get exactly what you want and in as little effort as possible. And you calling it rude to try at something else instead of get what you want is entitled and not something I support.
If it’s for yourself than you are only as critical as you need be.
if i cant make a thing look like i want it to look then I can’t make the thing i want to make. no shit.
an asteroid base is something that would take multiple people many years to accomplish. a cool drawing is something one person could reasonably expect to do on their own… the fact that some of us can’t is exactly my point that art isn’t fucking accessible just because anyone can make garbage because some dorks have a uselessly broad definition of art that is useless to normal people who just want to transfer the image in their head to paper.
it’s not about instant gratification or no effort either, the inaccessibility is in that we have tried to learn and were unable to. I take this condition and dispute the notion that art is accessible.. i’d be happy to put in time and get a result, but i put in time and effort years ago and never got anywhere because brain differences.
You are mistaking art with being a skilled craftsman. And your expectations are too high on yourself.
Art is accessible in that you can express yourself and find a medium to do that but it doesnt mean you are just gonna be great at painting or line drawing. Thise are skillsand most people are lucky enough to have a couple things they are truly skilled at in life. It doesnt mean we can do everything. We work together as humans. A person born without lega can provide skills to the world but cant just build their own wheelchair and all the medications for themselves.
You can not draw exactly what is in your head, boohoo. Im sorry but im not gonna have sympathy for you being human and not getting to do everything you ever want to do but you can work together with others to help make that possible. I have an incredible tattoo that looks exactly how i imagined it in my head but couldnt possibly draw it myself or tattoo it on my own body. But i went to an artist and showed them my shitty drawings and they turned it unto something amazing and someone else put that ink to skin.
Its my art. I am expressing myself through it but i dodnt expect to do it all myself.Stop expecting yourself to be able to do everything and stop making it so that you dont feel you can work with others and accept limitations. Thats how life is. Full of limitations and disappointment but there is less when you work together instead of thiniing you are gonna be superman doing it all on your own.
Art is accessible in that you can express yourself
no, I can’t. i’ve tried. If i say “me sad” that’s technically words but it’s not adequately communicating my interiority.
And your expectations are too high on yourself.
jesus christ for the tenth time i’m not expecting to be michelangelo. I’m worse than every highschool baseball player in the world but i can throw baseball-sized objects well enough for when that cop car across the street needs a broken window.
apparently you can read about as well as i can draw because you have constantly ignored my expressed desire for competence in this matter.
I’m not categorically against generative AI tools and believe they can be fun and useful. I just don’t think you can call their output art. I would compare them to character creators and similar creative tools in video games
You wouldn’t call yourself a character designer after making a cool custom fighter in SoulCalibur or an interior designer after making a house in the Sims, but that doesn’t take away the fact that both are valid creative outlets
tbh create a soul have enough going on that you could do character design in it, if we just mean visuals. i remember when mario maker was new a bunch of actual game devs were like “holy shit i wish our tools were as good as this level editor”
yeah i think there’s some ADHD thing that short circuits the connection between my mind image and my fingies
and i doodled and drew for years up until my late teens. also took tons of classes, including drawing classes in college.
luckily I read a lot and apparently could write well (back then at least) and did that instead. but I was always envious of people that can just do the whole “my hand is a printer connected to my brain”.
Edit: drawing all the talentless hacks out of the woodwork lol
rank ableism
Isn’t it wonderful that this pseudo-AI has freed humans from having to write and draw and think and dream? We have so much more time to mow lawns and wash dishes and do the laundry.
And work at Amazon fulfillment centers!
at least for me, the joy of art is in the process. if you want to replace personal development with a slot machine, feel free i guess. every artistic or musical piece that I make leaves an imprint in my mind and manifests a physical object or vibration in the real world. you could say that AI can take your desire and manifest it, but without the internal struggle between your imagination and the medium the art won’t change anything about how you see or understand the world. you might even miss getting a deeper look into what your actual desires / dreams are / mean.
People defending gen AI in these comments proves this place isn’t much different than the rest of lemmy at all lol
People are like “art is hard, you hone your skills over time” but that’s why i do abstract paintings, there’s no difficulty, no skill, just color gettin all fling flanged around. i refuse to get better at it.
My 3070/5900 rig runs stable diffusion well enough. The barrier to entry is much more gaming pc than it is server farm but I still agree with the sentiment and don’t agree with the idea that AI makes are accessible. It makes image generation more accessible but there’s a billion tools for tracing that already made shit pretty accessible.
Yes, but there’s a reason why we gatekeep art. Your average person has no taste and is just horny.
I felt MUCH more creative just tracing other’s art (for personal practice, they don’t survive long enough to be saved). I felt more creative finding a cruddy lego comic I made when I was 8. I felt more creative seeing a pallet my neighbor threw away and taking it to use for scrap wood for maybe making a cat tree. All more creative then trying to wrestle an “ai” to make a blurry ugly mess. The BEST piece I got still had odd eyes and muddy lighting.
I can barely draw a straight line. I can barely TRACE a hand. Yet I’ve gotten better. If I had the time/energy/drive, I could become decent, even without spending 10 million hours. I’ve just accepted certain personal limits. Like a slight natural shakey hand. It was frustrating wanting to paint minitures, but I got over it and had a hell of a time painting a simple landscape ala Bob Ross.
I’ve had a better time THINKING about evangelion and how I might make a game based on all the admin and engineering aspects the anime glances over. Not even the “art” stuff about it… but also thinking about the times it talks about the environment, its relation to late 90s tech, purity, the supposed “accidental” use of abrahamic icons, its seemingly forward projected critic of certain anime tropes, the disatisfaction with there being no clean end of anything human… And I still have to watch more then just the first series.
Besides everything else, I love leftist theory/thought because of the actual freedom it provides. (“Leftist”, “Theory” here being a bit loose.) Accepting what is and improving what can and needs to be is such a detoxifying mindset. Perfect would be nice, but sometimes you just can’t be, and you have to learn to forget your notions of perfection. I’ll probably never get over ~specific, fairly minor, chronic disorder that I shouldn’t add to my dox~, but I can tune out the distress 99% of the time, and the 1% I can cope with.
If you believe you are doing art with AI, can a mirror see you when you look into it?
Running one of these genai art models really isn’t that hard and doesn’t require incredible top-end hardware.
That isn’t really a defense of it, but it does allow some people who otherwise do not have artistic skills to make pictures.
Like, I have aphantasia and can’t visually conceptualize anything. Art is very hard for me. I don’t think it hurts anyone for me to make a character portrait for my dnd character using automatic1111. Even using an unethical model, I would never pay an artist for a dnd character portrait - it is too expensive for me and while I like having a nice character portrait and it helps me have a better conceptualization of my character, it is not worth the time or money to get a real artist to make one. If not for genai, I’d just go on deviantart and use one somebody already made or like draw a really shitty one.
Plus, if we’re going to say software piracy is OK but art piracy isn’t, thats a little hypocritical. Software piracy can definitely hurt software devs (especially ones working for smaller companies and even moreso for indie devs) in roughly the same way that art piracy hurts artists.
As a rule I think software piracy is fine if it doesn’t hurt anyone (i.e. if you wouldn’t have paid for it and it’s for noncommercial use). I don’t see how art is all that much different. Its completely different if you’re using any of this stuff for commercial use to take work away from people who need it and replace it with shitty AI stuff - but I’m not talking about that.
Plus, if we’re going to say software piracy is OK but art piracy isn’t, thats a little hypocritical. Software piracy can definitely hurt software devs (especially ones working for smaller companies and even moreso for indie devs) in roughly the same way that art piracy hurts artists.
This is BS how can you even believe its the same? Piracy is about reproduction as is. You download a software, you use it as its made.
AI art is fundamentally different, you’re not using it as is, you’re taking it, distilling the authors intent and work and claiming as your own, often for a profit.
Again compared that to software piracy, please I hope you’re not suggesting the average person who downloaded Photoshop in 2015 was actualy hacking it so they could resell it for $50 called it “TotallyMyOwnPhotoEditingSoftware Pro HD Max 12”.
Embarrassing to even write this shit. Barely above “you wouldn’t download a car”.
Piracy doesn’t hurt small devs. This is a stupid myth propagated by the AAA shills. Small devs are far more likely to benefit from piracy since it gives better word of mouth. If someone isn’t going to spend $5 or $10 to buy a game to begin with then at least they’re very likely to spread the game around, through communities or social media, if your game is actualy good.
Like this is discourse from like 15 years ago I kid you not. Its been debunked for at least since the early days of Steam.
idk to me it’s more like really advanced collage.
it’s piracy if i download five games. it’s still piracy if i rip assets out of them and put them in another game, even an original one. imo that’s fine until i try to sell it, and depending on who i pirated off of it ought to be fine even if i am selling it, but of course the law doesn’t agree.
I wasn’t really thinking about artisanal indie software creators in my OP, I just meant pirating Adobe products, which I assume everyone here is totally okay with
That was more towards the comment I replied to really, they pretty much try to clutch pearls over “but what about mah
smol movie producersmol indie bandindie game devs” as if the year is 2010. We’ve been here with the movie industry and the music industry which is why it triggered me.Trying to claim piracy can hurt but its fine, therefore AI art is also fine despite hurting people. The original premise is fault, piracy doesn’t hurt anyone except large businesses, and that is being very generous “hurting” being oh no the CEO needs to earn a smaller bonus this year.
As someone who also has aphantasia, but still likes to draw sometimes, this feels so strange for me to read.
I would never pay an artist for a dnd character portrait - it is too expensive for me and while I like having a nice character portrait and it helps me have a better conceptualization of my character, it is not worth the time or money to get a real artist to make one. If not for genai, I’d just go on deviantart and use one somebody already made or like draw a really shitty one.
If you don’t consider a drawing of your character to be worth any amount of money that you’d be willing to pay an artist, why do you feel the need to have one at all? And to say you’d go to an artist’s page and use one of their character drawings as your own, something that artists famously hate, means that you don’t even want to have a better conceptualization of your character since the drawing would just be of someone else’s character. Also, I do think that any drawing you make on your own would be infinitely more charming than any generic overly polished piece of art generative AI could spit out.
Just because it has value to me, but imo that is not monetary value. And having that picture accurately represent how I want that character to be, even if it has weird eyes or an extra finger, is a benefit to me and helps me be immersed in the game. I guess like I’d pay someone money for that, but I wouldn’t be willing to pay what their time is worth, you know? Like 10 bucks or something is not appropriate for someone spending an hour making a nice illustration - more like 75 would be appropriate, and that is too much for me.
i mean, it runs on laptops, its interesting to wrangle it with control nets to try to approach what you want, not art tho, more like visual shorthand builder
If it’s that easy to run I might mess around with it myself 🤔
if you have nvidia, invoke works fineish for more involved shenanigans (open models are definitely shit for real people and stuff people do with like text controlled cloth change with big models), but they can do fine with taking a sketch, filling it out 20 different ways and then a little bit iterating (although i would say, for background foreground photorealistic type picture, ai look is kinda unavoidable, easier to fuck around in photoshop to fix it) or giving ideas.
although it’s not satisfying as sketching with pen on paper, imma be real, just entertaining as riding a bike or something, after 2 months of doing shenanigans myself when bored, i grow kinda tired of messing with it
if you have nvidia
rip. amd on linux has some support, but on windows it’s fucking shit. or if you mean only cpu - it’s so slow and energy-intensive, it’s not worth it i think? there were some moves to try to speed it up on cpus, but i haven’t looked into the results
Is an AMD GPU + Windows a complete non-starter then? That’s a shame
i think they have something called amuse, but it’s very bare program to run prompts, without interesting stuff like control nets or at least was.
and there is some shit to swap cuda for amd supported thingy, but it’s so much headache, it’s not worth it, at least i think so
No it’s not. You use direct ml, it’s slower but does work. Last I heard “shark” works? But I haven’t looked at it in ages. There are options though.
> caring about AI bros’ opinions on literally anything
couldnt be me
These AI bros include some of the most powerful people in the tech industry.
Idk I just made some invitations for a party my mom is throwing. The theme is kind of niche so I used AI to generate the background. Only took 3 tries to get something that she loved, which was within the free daily limits.
There’s a billion websites for card templating
Yeah I looked at a couple of those sites first but most of the templates were ugly and didn’t perfectly match the theme.
You can run stable diffusion on fucking android phones. Your thesis is invalid.
Really? I might look into it, then. I once tried generating random pictures with Bing (?) since Microsoft handed out some free points, and while it was fun to mess around with, I hated how much it felt like I was playing some freemium mobile game. I also just hate this sort of subscription/microtransaction-based cloud computing SAAS bullshit in general
I might actually enjoy generating stuff on my own hardware
To actually use it properly, install ComfyUI and get in deep. The whole “actually using SD to generate what you want consistently” is a form of art on it’s own, it’s kind of like learning Krita.
Because generating random bullshit ala ChatGPT is easy. Getting anatomy, object placement, logical consistency in the image and also overcoming model biases or introducing new biases is some complicated shit. For example, there are models that can generate depth layers, models that can dictate object placement, and then since SD output is smol you need to wire it into an upscaler model, etc.
SDWebUI is much simpler, but also much more limited. Same as Android apps that run SD locally, really nothing matches the level of control that ComfyUI has.
All you need is any recent Nvidia GPU with 4GB of VRAM although less VRAM was reported to work. For AMD, since AMD hates GPGPU apparently, only their top cards support ROCm. As for Apple and Intel, I do not know.
If you are stuck with AMD and can’t use ROCm, just use KoboldCPP. It will be significantly shittier in every way but atleast it runs.
never looked into it beyond “lol minions in heironymous bosch” but i see people with 10+ images of the same subject so i figure there’s some ways to get consistent-ish results out of the things that the free thing isn’t configured for
For the smarties saying you can run it on a phone, a shitfuck scratched phone costs like 20 dollars at minimum and you’re going for hundreds if you want an actually usable phone, a pencil and some sheets of paper cost way less than that
dirt and a stick are free but people want to make something that looks like their intent and a ton of us are not capable of that. i don’t think the people writing ai prompts are meaningfully making anything but they’re getting output that looks like something and if they’re lucky it has the correct number of fingers.
my point is that having a phone isn’t open to everyone, and especially running a whatever AI prompter thing, considering the third world exists, a phone costs a salary where I live, and good luck figuring out anything if you don’t speak english.
