×
Login Register an account
Top Submissions Explore Upgoat Search Random Subverse Random Post Colorize! Site Rules
18

Dreaming of Goats: M-mein Führer?! Edition!

submitted by GloryBeckons to AI_art 1 yearApr 29, 2023 09:53:29 ago (+18/-0)     (files.catbox.moe)

https://files.catbox.moe/k11gma.png

Continuing previous thread, featuring some upgrades. Finest German engineering.

The AI doesn't understand some names as well as others, so I've taken some liberties to spice up some prompts. But still staying true to the theme of the name.

@drhitler
Just "dr hitler" seems to merely have an... odd effect on Uncle Adi's nose. But emphasizing doctor helps it along:
https://files.catbox.moe/ies9c2.png
https://files.catbox.moe/k11gma.png
https://files.catbox.moe/hwftli.png
Mirrors:
https://pomf2.lain.la/f/n6fqnnlf.png
https://pomf2.lain.la/f/peag7eb5.png
https://pomf2.lain.la/f/iw92ctd1.png

@SecretHitler
The previous version merely showed a board game, so here's "Hitler playing Secret Hitler":
https://files.catbox.moe/fbilbv.png
https://files.catbox.moe/8utwih.png
Mirrors:
https://pomf2.lain.la/f/zjvtnvjw.png
https://pomf2.lain.la/f/jpu971cj.png

@NaturalSelectionistWorker
The previous version didn't quite understand the concept of natural selection, so I added some eugenics and darwinism:
https://files.catbox.moe/ig5wc2.png
https://files.catbox.moe/ljs4lk.png
Mirrors:
https://pomf2.lain.la/f/ctig08t3.png
https://pomf2.lain.la/f/4jinvx3x.png

@doginventer
The first one is just the name. The second is cursed. Click at your own peril.
https://files.catbox.moe/4qatvu.png
https://files.catbox.moe/n66wao.png
Mirrors:
https://pomf2.lain.la/f/efmswgcl.png
https://pomf2.lain.la/f/amzstcft.png

@FacelessOne
This one just needed a space to get it... without the space it made creepy faces instead of no faces.
https://files.catbox.moe/kprb4i.png
https://files.catbox.moe/qkfv4g.png
https://files.catbox.moe/0qi77e.png
Mirrors:
https://pomf2.lain.la/f/6lr2r39d.png
https://pomf2.lain.la/f/so7xjh8.png
https://pomf2.lain.la/f/eo1ss7oc.png

@x0x7
Really random for obvious reasons... most of them look comfy though?
https://files.catbox.moe/ai8i97.png
https://files.catbox.moe/x3shzz.png
Mirrors:
https://pomf2.lain.la/f/yov8sf06.png
https://pomf2.lain.la/f/nmrwi5yz.png

That's all for now.


15 comments block


[ - ] GloryBeckons [op] 1 point 1 yearApr 29, 2023 15:44:41 ago (+1/-0)

[ - ] dulcima 0 points 1 yearApr 29, 2023 19:42:32 ago (+0/-0)

Dangus looks as expected.

[ - ] MuricaPersonified 0 points 1 yearApr 30, 2023 15:43:07 ago (+0/-0)

LOL! Hitler's expression screams "I'd rather be playing Risk!"

[ - ] lord_nougat 1 point 1 yearApr 29, 2023 14:24:29 ago (+1/-0)

I like that one with Hitler playing against Higgins from Magnum PI.

[ - ] bobdole9 1 point 1 yearApr 29, 2023 12:49:40 ago (+1/-0)

Are you using something installed on your computer or some website somewhere?

[ - ] GloryBeckons [op] 4 points 1 yearApr 29, 2023 13:41:47 ago (+4/-0)*

I'm running this completely locally.

The base technology is called Stable Diffusion. The model I used for all of these is called Deliberate v2. I'm running it using a tool called AUTOMATIC1111 (technically, "Stable Diffusion Web UI" made by AUTOMATIC1111, but everyone calls it by the author's name). There are other tools which can do similar things, but I like this one since it's one of the more flexible ones. The tool and model are actually capable of much more... what I'm doing to generate these is very basic.

You can find the Deliberate model (and many others) here:
https://civitai.com/models/4823/deliberate

AUTOMATIC1111 lives here:
https://github.com/AUTOMATIC1111/stable-diffusion-webui

And has an in-depth wiki here:
https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki

There is a great guide to get started here (also has many useful links beyond that):
https://rentry.org/voldy

I'm actually using it via docker, which is a bit different from the above, but I wouldn't worry about that unless you already know what that means. For completeness, here's a link to the dockerized version (which also contains and has links to some alternatives to AUTOMATIC1111):
https://github.com/AbdBarho/stable-diffusion-webui-docker

[ - ] Thyhorrorcosmic103 1 point 1 yearApr 30, 2023 07:06:11 ago (+1/-0)

That is gonna take some time to figure out, thanks for directing me though.

[ - ] GloryBeckons [op] 1 point 1 yearApr 30, 2023 07:16:07 ago (+1/-0)

Follow the Voldy guide and you should be up and running in no time. From there, it's one huge rabbit hole after another to figure out all the nuances. But you can do a lot with just the basics.

[ - ] dulcima 0 points 1 yearApr 29, 2023 19:47:51 ago (+0/-0)

This has been fun, I have to say.

[ - ] drhitler 0 points 1 yearApr 29, 2023 19:05:42 ago (+0/-0)

hah thank you, got a good laugh out of this

Seems like the AI really doesn't want to draw a proper Adolf mustache

[ - ] LiberalsAreMental 0 points 1 yearApr 29, 2023 18:29:53 ago (+0/-0)

Looks like George Noory.

[ - ] NaturalSelectionistWorker 0 points 1 yearApr 29, 2023 18:00:12 ago (+0/-0)

I think it gave dangus a pussy.

[ - ] SecretHitler 0 points 1 yearApr 29, 2023 16:23:13 ago (+0/-0)

Hitler playing Secret Hitler

This is one of the best things I've ever seen I love it

I notice there's no swastikas? Do you think the ai engines are filtered to leave those out?

[ - ] GloryBeckons [op] 1 point 1 yearApr 29, 2023 17:40:33 ago (+1/-0)*

Glad you liked it!

Not intentionally, I don't think so. It knows Hitler, and Nazi uniforms, etc. Not to mention, there are far more problematic and outright illegal things which it will generate without blinking.

More likely it's a side-effect of AI struggling with details like that. Just like it struggles with hands and writing. It will try to make Swastikas, but they come out garbled. Like it's just not very good at it.

It's a bit counter-intuitive, but a symbol like that requires far more precision than most things. You might think "but it makes such intricate details, like individual strands of hair"... but the thing is, with a strand of hair it doesn't matter if it's exactly there, or two pixels to the left, or three pixels to the right. It'll still look fine as long as the general pattern is consistent. Even with faces, features can be a bit out of place and you'll still recognize the person. But a symbol like a Swastika, if you mess it up even a little, it immediately looks completely broken. I got similarly messed up results when I asked for a Star of David.

Of course, there probably weren't very many labeled Swastikas in the training data, so that doesn't help either.

It's something that can be fixed though. There are LoRAs (kind of like "plugins" for AI models) which let you generate SS Nazi Anime Waifus, for example. Or so I'm told.

[ - ] doginventer 0 points 1 yearApr 29, 2023 15:55:38 ago (+0/-0)

Click at your own peril.

You did warn me!
Yeah, the first ones are quite strange enough for me :)

Cheers GB