That’ll get you started. Should see you sorted for the next month of learning. Once you’ve got the basics of using Stable Diffusion (one of many image gen software) and you have the software under control you can start looking at using custom training models for getting the styles you want and learn how to start getting the results similar to what you want, they won’t be good, most will be trash, then you’ll need to learn about ControlNet, this will get you introduced to wireframe posing, depth maps, softedge, canny, and a dozen other pre-processing tools, once you start getting things that look kinda close to what you want you’ll learn about multi-pass processing, img2img generation, full and selective inpainting, and you’ll start using tools like ADetailer to help try generate better looking hands faces and eyes, and then you’ll need to get into learning how to use Latent-Couple and ComposableLora so you can start making accurate scene placements and style divisions. Don’t worry about the plethora of other more complex tools, you won’t need those at the start.
Oh but it does. Until you understand the practical and real world usage and application of the technology, and it’s limitations, you’re talking out your ass. Opinions are like assholes, everyone’s got one and most are full of shit. I prefer objective reality over the imaginings of perpetually offended but wilfully ignorant people.
So I challenge you to recreate a traditional masterpiece with AI that is of the quality that traditional artists would respect in a style so accurate to be indiscernable for the real thing. I’ll see you in undefined years, then congratulate you on accomplishing your task and respect the amount of knowledge and skill it would take to accomplish such a feat.
What the fuck are you on about. Do you have some sort of superiority complex?
I don’t need to prove my knowledge to you just because I haven’t generated any images myself. I can be aware of all the other applications and limitations of such a tool. I’m not arguing that it isn’t useful.
I’m arguing artists should have a say in whether their work gets absorbed into the black box or not. And if they don’t get that choice, fair on them for trying to poison the system. Shouldn’t have taken without asking if you didn’t want that to happen.
And I’m saying you’re wrong. Terrorists don’t get to blow up social infrastructure because they don’t get what they want. And you seem to miss the part where I’m one of those artists.
You’re the sort to tear down babylon or burn the library of alexandria because they stored a copy of your work for the posterity and benefit of humanity.
I didn’t miss that part. You’re free to do with your art whatever you want.
But just because you are okay with your art getting repurposed for whatever doesn’t mean others have to be.
And if the library were to store a copy of my book it’d come with royalties and credit, unlike whatever is going on with image generators.
Now if libraries were to stock an illegal copy of my book, I’d get pretty pissed about that. If they did that to all of the other writers as well I wouldn’t even have to burn it down because the lawyers would do it for me.
But lone artists on the internet don’t have a massive publisher to back them up.
I absolutely know much on the topic. Please read my comments elsewhere in this thread for a strong break down of the issues and how AI actually works. Btw, the source of my authority on all of it is having a Master’s degree in art, working in a professional art field, having a BS in Applied Mathematics, and building AI’s as a hobby. I live in literally every aspect of this debate.
TL:DR - AI models are never trained directly on source material. Sources are fed into statistical analysis algorithms that utterly destroy the sources and derive info that computers can understand in a process called Vectorization. The AI is then trained on those vectors. Then, when a prompt is given, the algorithm takes it apart as an input in a process called Tokenization. From the input, in an algorithm that goes beyond the scope of this, an output is given that statistically satisfies the model. So even in the usage process, the AI never actually directly works on human inputs.
I should look into using said algorithms?
I know what they can do, but if that’s through ripping off the work of others I’m not sure I like it.
Would you pay an artist if you knew their work was traced?
Here, first you need tools, these are FOSS:
https://www.dexerto.com/tech/how-to-install-stable-diffusion-2124809/
https://www.youtube.com/watch?v=nBpD-RbglPw
https://www.youtube.com/watch?v=SYNd0vAt5jk
Then you’ll need to know the basics of using Stable Diffusion:
https://www.youtube.com/watch?v=nBpD-RbglPw
You’ll want access to community resources:
https://civitai.com
That’ll get you started. Should see you sorted for the next month of learning. Once you’ve got the basics of using Stable Diffusion (one of many image gen software) and you have the software under control you can start looking at using custom training models for getting the styles you want and learn how to start getting the results similar to what you want, they won’t be good, most will be trash, then you’ll need to learn about ControlNet, this will get you introduced to wireframe posing, depth maps, softedge, canny, and a dozen other pre-processing tools, once you start getting things that look kinda close to what you want you’ll learn about multi-pass processing, img2img generation, full and selective inpainting, and you’ll start using tools like ADetailer to help try generate better looking hands faces and eyes, and then you’ll need to get into learning how to use Latent-Couple and ComposableLora so you can start making accurate scene placements and style divisions. Don’t worry about the plethora of other more complex tools, you won’t need those at the start.
I know how to get my hands on things. Just because I haven’t used it doesn’t mean I can’t form an opinion on the ethics behind it.
Oh but it does. Until you understand the practical and real world usage and application of the technology, and it’s limitations, you’re talking out your ass. Opinions are like assholes, everyone’s got one and most are full of shit. I prefer objective reality over the imaginings of perpetually offended but wilfully ignorant people.
So I challenge you to recreate a traditional masterpiece with AI that is of the quality that traditional artists would respect in a style so accurate to be indiscernable for the real thing. I’ll see you in undefined years, then congratulate you on accomplishing your task and respect the amount of knowledge and skill it would take to accomplish such a feat.
What the fuck are you on about. Do you have some sort of superiority complex?
I don’t need to prove my knowledge to you just because I haven’t generated any images myself. I can be aware of all the other applications and limitations of such a tool. I’m not arguing that it isn’t useful.
I’m arguing artists should have a say in whether their work gets absorbed into the black box or not. And if they don’t get that choice, fair on them for trying to poison the system. Shouldn’t have taken without asking if you didn’t want that to happen.
And I’m saying you’re wrong. Terrorists don’t get to blow up social infrastructure because they don’t get what they want. And you seem to miss the part where I’m one of those artists.
You’re the sort to tear down babylon or burn the library of alexandria because they stored a copy of your work for the posterity and benefit of humanity.
I didn’t miss that part. You’re free to do with your art whatever you want.
But just because you are okay with your art getting repurposed for whatever doesn’t mean others have to be.
And if the library were to store a copy of my book it’d come with royalties and credit, unlike whatever is going on with image generators.
Now if libraries were to stock an illegal copy of my book, I’d get pretty pissed about that. If they did that to all of the other writers as well I wouldn’t even have to burn it down because the lawyers would do it for me.
But lone artists on the internet don’t have a massive publisher to back them up.
Why do you hate libraries? Does DaVinci get royalties when I replicate his engineering work?
And no, DaVinci doesn’t. That’s why copyright expires and items go into the public domain after a set amount of years.
A “set” amount of years massive corporations have been all too happy to push back, but that’s another conversation.
Please quote me the part where I said or implied I hate libraries.
You know nothing on the subject and it shows.
I absolutely know much on the topic. Please read my comments elsewhere in this thread for a strong break down of the issues and how AI actually works. Btw, the source of my authority on all of it is having a Master’s degree in art, working in a professional art field, having a BS in Applied Mathematics, and building AI’s as a hobby. I live in literally every aspect of this debate.
TL:DR - AI models are never trained directly on source material. Sources are fed into statistical analysis algorithms that utterly destroy the sources and derive info that computers can understand in a process called Vectorization. The AI is then trained on those vectors. Then, when a prompt is given, the algorithm takes it apart as an input in a process called Tokenization. From the input, in an algorithm that goes beyond the scope of this, an output is given that statistically satisfies the model. So even in the usage process, the AI never actually directly works on human inputs.
Cool, so do I. I’ve been a software developer and digital artist for 25 years. I now use AI tools to assist my work flow for both.
Fun. Apologies for misinterpreting your comment.