Quote:
Originally Posted by Renegade334
Thank you for your kind words, but, alas, that sentiment isn't universally shared. As a concrete example, Imgur loves to downvote to oblivion Community posts with the tags "aiart" and/or "stablediffusion"; they're a lot more vocal in their rejection of AI artistry. Real, flesh-and-blood artists could also feel discouraged by this new form of competition; as an occasional Photoshopper, I, for one, know that I can never match this kind of graphical prowess (not to mention, I've grown somewhat rusty in that field - it's been a while since I made user signatures for forums). However, I've found that SD still requires a lot of Photoshop post-processing, especially to fix some of the finer stuff like hands and faces - and sometimes the eyes.
For the prompts, I stopped appending them because I've started making increasingly more complex pictures, leveraging regional prompts (I've switched from the time-honored Regional Prompter to Multidiffusion Upscaler for Automatic 1111, which also has a regional prompt option but with a far better boundary box-adjustment system), Hires fix upscaling, ControlNet reference models and daisy-chained After Detailer tasks with fine-grain instructions. These combinations make for very long text outputs, which quickly degrade the readability of the forum's post editor.
|
Prompts themselves are becoming a skill with which to create the desired result. It is not an easy thing to do. Not too mention that most AI Art engines will generate a larger number of images that are "mistakes" as they do "good" images that are useful. I'm not as advanced in it as you are, but I'm learning and it is the learning that is likely what is causing many traditional artists to oppose AI Art.
I've done hand drawn artwork myself (here is an example of an original Code Geass piece):
I've since moved on to 3D digital artwork for my own science fiction.
However, I'm not afraid to use AI for that science fiction because I don't do character images well at all and employing an artist to design and create book covers or interior artwork is cost-prohibitive. I'm working on a TTRPG series of books right now for my Nexus Arcana series of traditional novels and the estimated cost to hire artists to do the interior artwork was upwards of $50,000 US. That's not possible for me to afford or justify. AI however (with commercial license) makes it possible at a greatly reduced cost and that's why we're seeing every major publisher of books going over to it. Video game companies are also going to it for backgrounds, and other art that doesn't require the skill of a flesh-and-blood artist. Traditional artists will still be needed for the concept art, detailed art, etc. because as you know, getting AI to actually craft something like a whole anime series is not possible, yet.
My own AI art is akin to this (nothing spectacular, but functional for its purpose).
Book 1 is purely AI art:
Book 2 is a combination of AI art with a photo background completed in photoshop:
Book 3 is a combination of AI art with original 3D graphic models composited in photoshop into one image:
It will take some time, but once traditional artists figure out that AI can cut production time and increase workflow significantly for backgrounds, and other uses to improve their original art, methinks the resistance to the technology will subside considerably (there will always be hold outs).