Stable Diffusion, NovelAI, Machine Learning Art - AI art generation discussion and image dump

So we're agreed that automation is a universal good, regardless of whose job it comes for?
Yes. Or rather if its good when it comes for one set of people, its good for when it comes for literally any other set of people.

Seeing as we have had decades of automation at this point, why are you expecting many allies now? Artfags aren't the first to be displaced, they absolutely won't be the last
 
I'm using the Automatic1111 frontend. How do I know that I successfully installed the NovelAI module?
 
Anyone try using your forum name to see what comes out? (no, I'm not posting what I got)
This is you:
1666214183662.png
This is also you:
1666214350854.png
 
Can't wait for waifu diffusions to replace all the ugly-ass picrew avatars! Although I am a little sad thinking about how we'll likely see a decline in entertainingly bad art. I'm guessing it's a lot easier for autists to fiddle with AI settings than to lovingly hand craft some deviantart abomination?
 
Tech frens, I require your assistance.
When running Webui-user.batch i get "errno 13" which basically states that there are insufficient premissions.

I've reinstalled the webui
I've put it in a new folder
I made sure it wasn't on read only.

Im pretty sure im missing something here besides sanity.

I will pay you handsomely for giving me a good solution by giving you a funny tf2 hat (i am poor). Thank you.
 
I miss when this thread was like 6 pages long and didn't get completely spammed with people bitching about the consequences of the tech instead of, you know, having fun with it.

That being said, can anyone give me some tips on how to get good results with both SDv1.4 model and the NovelAI model? What prompts to use, what setting to use, etc?
 
I think I got it to work. Didn't find yet where the models can be altered in the GUI, but what were yours for this? It made an anime and traditional japanese man at once!
The second one was the icon as image, but description was "ugly asian man in a wig".
Using the same description and your avvy I get:
1666215728695.png
But if I try "sassy anime nazi" it's:
1666215853115.png

Can't wait for waifu diffusions to replace all the ugly-ass picrew avatars! Although I am a little sad thinking about how we'll likely see a decline in entertainingly bad art. I'm guessing it's a lot easier for autists to fiddle with AI settings than to lovingly hand craft some deviantart abomination?
Why not combine the two?
Input:
1666215980782.png
Result:
1666216083099.png1666216140924.png

I wonder what "lolcow yoghurt" would yield...
1666216230483.png

Is it okay to post requests for some autists with gpus that can run this thing well and have too much free time? If so I would like a "Stupid looking Labrador retriever dripping drool from mouth."
These are horrible.
1666216618565.png1666216656697.png

I miss when this thread was like 6 pages long and didn't get completely spammed with people bitching about the consequences of the tech instead of, you know, having fun with it.

That being said, can anyone give me some tips on how to get good results with both SDv1.4 model and the NovelAI model? What prompts to use, what setting to use, etc?
https://docs.novelai.net/
 
I miss when this thread was like 6 pages long and didn't get completely spammed with people bitching about the consequences of the tech instead of, you know, having fun with it.

That being said, can anyone give me some tips on how to get good results with both SDv1.4 model and the NovelAI model? What prompts to use, what setting to use, etc?
Don't worry bro, I have a tweet brewing that will shut them all up. "Smh, so tired of ableist artists gatekeeping art for those that are creatively challenged and or/are incapable of drawing "normally" due to a disability."
 
Seeing as we have had decades of automation at this point, why are you expecting many allies now? Artfags aren't the first to be displaced, they absolutely won't be the last
I've always spoken about how awful it is that people are getting kicked out of their work and hoped the technology for driverless cars would never reach completion. You're acting as if I've crowed about people losing their jobs in the past, I'm not and never was a smug "learn👏 how👏 to👏 code👏" twitter faggot. I didn't like it when jobs were exported to foreign nations and I didn't like it when American companies culled their employees to compete by getting robotic arms to do the same work with one person at the helm.
 
The second one was the icon as image, but description was "ugly asian man in a wig".
Using the same description and your avvy I get:
View attachment 3750666
But if I try "sassy anime nazi" it's:
View attachment 3750668


Why not combine the two?
Input:
View attachment 3750674
Result:
View attachment 3750680View attachment 3750681


View attachment 3750687


These are horrible.
View attachment 3750708View attachment 3750709


https://docs.novelai.net/

That's super cute! What settings do you use? When I input it, it did nothing to it except make the hair a bit more detailed. Here are some dog requests:
nulldog.pngkiwidog.png
 
Anyone try using your forum name to see what comes out? (no, I'm not posting what I got)
Pics related, got some decent results with Stable DIffusion. My spooky avatar is also from Stable Diffusion by feeding it my normal avatar and telling it to turn me into a skeleton. Img2Img and AI upscaling is amazing for quick edits, Wojack editors on suicide watch.
jean-lafitte-null.png jean-lafitte-japanese-ink-painting-null.png
 
Back