AI Art Seething General

LMAO no it won't, the repulsive globohomo art style is pushed by major corporations and NGOs. They don't put that shit everywhere because it's cheap or easy to produce, they put it everywhere because it's the exact shade of soulless they want the entire world to be. The only difference is now the globohomo art will be made by computers.
i couldnt even get ai to generate that when i tried
 
The guy making the big tiddy victorian ai waifus has "tranny" and "trans" in the negative prompts lmfao
IMG_20221002_122721.jpg
 
The guy making the big tiddy victorian ai waifus has "tranny" and "trans" in the negative prompts lmfaoView attachment 3708783
Every time I see one of these prompts written out it feels like reading some degenerate occult spell. I picture some Aleister Crowley-like sitting in a dark basement surrounded by dakimakura pillows rubbing his semen-coated palms together and mumbling these phrases in the hopes of invoking some greater collective will to bring wAIfus to life.
 
I've read several articles now about AI art, and I feel like all of them focus on the commercial art industry. It makes sense, since that's obviously what would be most impacted. But I feel like they never address some important things.

Commercially, wide availability of machine made (or in this case, computer generated) tends to make hand-made things more "elite". How many people do you know with a bespoke or hand tailored suit, or a piece of genuine couture?

It also tends to ignore that human beings like to make things, art in particular. People will always make art, in the same way that people still garden, or knit, or build their own furniture. Maybe it won't be a viable career option, but really - it's not a viable career option for most people now.

As for whether AI art is art, articles are always focused on the consciousness of the creator. I haven't seen one yet mention that art is a two way communication- between an artist and a viewer. So, to so extent, even if an AI created something from a string of prompts, a viewer is still there to add their consciousness to the process. Their feelings, sense of aesthetics, and eyes are still there, so consciousness is still involved to an extent. We can still look at AI generated art and see where it gets things wrong, and can also look and see when it gets things right, or makes something that strikes us as beautiful.
 
Don't worry too much if you have actual talent. There are always going to be people who want art with a human touch. AI however will be a major filter for talentless, low-effort artists, and we may see the end of certain modern styles, like that awful Globohomo flat style (I don't know the real name, but "Globohomo flat style" on your favorite image search engine will turn up more than enough examples). If we have AI that can replicate the style of Vermeer, why would we pay for garbage an AI could have probably done 5 years ago?
AI might make art great again. The human artists who can't do much above flat stick figures will learn to code because an AI will be able to create art that has both the quality and human feeling of their garbage. Truly good artists should have no problem being recognized and well paid because there will probably always be things AI won't be able to reproduce. Emotion, experience, originality, and God forbid the ability to translate such things onto a canvas or image file, are totally foreign to an AI.
I tried to make robots draw "Nikocado avocado's asshole corporate alegria," but they all wanted me to sign in, as if they had dignity or something.
 
I play around with NightCafe sometimes, and I like to give it simple prompts like "autum forest" then search the same prompt on google images.
I think it's learning, because I used to laugh at it a lot more than I do lately.
It's even figured out what a cornfield is.
 
I tried to make robots draw "Nikocado avocado's asshole corporate alegria," but they all wanted me to sign in, as if they had dignity or something.
Alegria is what that shit's called, thanks.
Anyway, there's a couple you can use without a login. Here's Nikocado avocado's asshole corporate alegria" done by Craiyon:
craiyon_002159_N_span_style____tw_border_spacing_x__0____tw_border_spacing_y__0____tw_translat...png

Even just "Nikocado Avacado" just gives you images of avocados and guacamole. One of my former favorites, DeepAI, is really no different. DeepAI has been around for a few years and up until very recently (like the last month or so) it produced images that were like a nightmare version of the text you typed, a nightmare version of some alphabetically nearby word or the text you typed, or something that was a total mystery. For example, I tried to see what would happen when giving it an abstract concept (liberty) and it gave me a picture of a room that looks kind of like a library. Here's one I saved:

liberty787.jpg

They must have changed something because now DeepAI is just like all the others. I liked it better when it produced images like this.
 
I think half the hate towards ai art is artists who specialize in bottom of the barrel generic art are scared their cashflow of horny people wanting to see their oc in various situations moving to a ai that can make it for free and 10 times quicker.

Ai art amazes me because in the course of about 2 years we went from funny blobs that vaguely look like your prompts to shit that can make near perfect images with minimal errors, give it another 2 years and who knows what will happen.
 
Every time I see one of these prompts written out it feels like reading some degenerate occult spell. I picture some Aleister Crowley-like sitting in a dark basement surrounded by dakimakura pillows rubbing his semen-coated palms together and mumbling these phrases in the hopes of invoking some greater collective will to bring wAIfus to life.
I think half the hate towards ai art is artists who specialize in bottom of the barrel generic art are scared their cashflow of horny people wanting to see their oc in various situations moving to a ai that can make it for free and 10 times quicker.

Ai art amazes me because in the course of about 2 years we went from funny blobs that vaguely look like your prompts to shit that can make near perfect images with minimal errors, give it another 2 years and who knows what will happen.
It makes you wonder, too, how the users will change as well. Right now everything seems possible, but as people learn what "works" they're going to start thinking and behaving differently and that will probably narrow the scope.
The optimistic part of me hopes there are some proto-"artists" in that sphere that will keep pushing for the weird and interesting shit.
 
It makes you wonder, too, how the users will change as well. Right now everything seems possible, but as people learn what "works" they're going to start thinking and behaving differently and that will probably narrow the scope.
The optimistic part of me hopes there are some proto-"artists" in that sphere that will keep pushing for the weird and interesting shit.
I imagine that ai will branch out into a alot of different paths, you'll have models trained purely on concept art for a certain theme, models trained on porn, vehicles, etc, skys the limit but the community will splinter fast.
 
Turned my shitty little pixel scratch avatar I drew in like a minute when I joined into this with img2img.
View attachment 3713677 (for posterity)
to
View attachment 3713682
This is one of the primary uses I see - I can't draw for shit, but I can photoshop together a set of shapes and lines that approximate my vision - which tends to be enough for AI to turn it into fx a Dürer style pencil drawing that actually looks usable. It's a shortcut, but a creative process is certainly still involved if you want to get decent results.
 
I have access to the beta version of Dall-E. I wanted to use it to explore ideas and bounce of them for my drawings/paintings. But for me it completely ruined my ability to create because I would end up trying to emulate and copy parts of the generated images.
It makes a great tool for desctop background creation.
Really impressive stuff.
 
I'll take goofy images of one-armed women and tard dogs over Alegria any day.

Turned my shitty little pixel scratch avatar I drew in like a minute when I joined into this with img2img.
View attachment 3713677 (for posterity)
to
View attachment 3713682
It is rather handy for avatars. I also can't get enough of that hilarious image disguising people have been doing with pepes, wojacks, and the like. My avatar hides an older cartoon, but you would never know just glancing at it.
 
Back