Yea and I keep making more since its "hit a button things happen"..lol
Once I found a good model, got the prompt right how I like, and using dynamic prompts wildcard extension its hit generate and let it go.
So I edited the gui ini for auto1111 so the batch slider goes to 1000, slide it all the way up and go to bed or eat and watch TV or something. Repeat every day or so.
-We don't control what happens to us in life, but we control how we respond to what happens in life.
-Hard times create strong men, strong men create good times, good times create weak men, and weak men create hard times. -G. Michael Hopf
Disclaimer: Post made by me are of my own creation. A delusional mind relayed in text form.
So are there any quick and easy radeon compatible solutions available nowadays? Haven't tinkered with local installations for 2-3 months already. I guess that is an eternity in generative art, so I hope for some advancement
Not sure about quick and easy, but there are solutions.
My friend has my old 6700xt and was wanting to do it, but we had a lot of things to try to work out that was pretty technical about running it in a linux VM, and needing python, git cloning, and such that combined was above both our heads without a hand holding guide.
But that was 6 months ago. Not sure if there a a turnkey solution now. Would be nice if there was. Like Auto1111 web gui is dumb simple on Nivdia to get the very basics bare bones basics up and running of 'input words, pics come out' if you have a Nvidia. Literally: clone/download github, run bat file, wait. Localhost browser pops up and start.
Auto1111 can run on it too. But that was the whole "Ok we tried all day, and neither of us knows linux well enough to do this...just use my google colab account"
-We don't control what happens to us in life, but we control how we respond to what happens in life.
-Hard times create strong men, strong men create good times, good times create weak men, and weak men create hard times. -G. Michael Hopf
Disclaimer: Post made by me are of my own creation. A delusional mind relayed in text form.
This considered art? Not really art I guess. Artistic...maybe?
But made this with AI for my tabletop game too. Going to make a new one each week that recaps the week before:
http://sndup.net/rycd
-We don't control what happens to us in life, but we control how we respond to what happens in life.
-Hard times create strong men, strong men create good times, good times create weak men, and weak men create hard times. -G. Michael Hopf
Disclaimer: Post made by me are of my own creation. A delusional mind relayed in text form.
This considered art? Not really art I guess. Artistic...maybe?
But made this with AI for my tabletop game too. Going to make a new one each week that recaps the week before:
http://sndup.net/rycd
I liked that one, what did you use? I need something similar
edit: Would love to send similar to my players before next session
shitloads of new stuff in my pc. Cant keep track of it all.
I used elevenlabs.io, seems way better than anything I can run locally for quality.
-We don't control what happens to us in life, but we control how we respond to what happens in life.
-Hard times create strong men, strong men create good times, good times create weak men, and weak men create hard times. -G. Michael Hopf
Disclaimer: Post made by me are of my own creation. A delusional mind relayed in text form.
Made this one, not using it for a session..but the group laughed how sarcastically on the nose it is. https://sndup.net/dt7q/
-We don't control what happens to us in life, but we control how we respond to what happens in life.
-Hard times create strong men, strong men create good times, good times create weak men, and weak men create hard times. -G. Michael Hopf
Disclaimer: Post made by me are of my own creation. A delusional mind relayed in text form.
Maybe it has somewhat lost its magic to me, but those aren't that impressive at all.
They are quite literally just different pictures merged together without even trying to blend them in. I guess the only impressive part is the matching light/shadow direction.
There must have been a door there in the wall, when I came in.
Truly gone fishing.
They are quite literally just different pictures merged together without even trying to blend them in.
that's not how it works, every pixel is actually created from scratch, it's completely new images which has never existed, its made from scratch via the machine learning. however it doesn't mean there's never imperfections or oddities.
for a 5'ish second render its pretty impressive, warts and all.
via plugins you can get close to perfect images these days, but that requires actual effort to set up each render.. its more than just writing a sentence (which most of the content out there is).
Last edited by vurt on Wed, 12th Jul 2023 09:17; edited 1 time in total
how it works is not a theory at all, we know how it works. I do machine learning myself with my own images so i know quite exactly how it works, i know for a fact that it never copies anything.
which "original image" are you refferring to? part of a rope comes from its learning, the sentence described "climbing" and in images of that there will be people holding rope. A very expected outcome is someone holding a part of a rope in such a render. via plugins we can remove such artifacts easily and we can pose people too so it looks more natural.
I stand corrected! Dunno what I was thinking, as I followed a machine learning course too. I guess some artifacts are pretty jarring, and things like the missing shadow under the kid's foot (2nd picture) stand out and make it look like someone is learning photoshop.
But the hands are still proof it's indeed generated
There must have been a door there in the wall, when I came in.
Truly gone fishing.
Signature/Avatar nuking: none (can be changed in your profile)
You cannot post new topics in this forum You cannot reply to topics in this forum You cannot edit your posts in this forum You cannot delete your posts in this forum You cannot vote in polls in this forum
