Register a SA Forums Account here!
JOINING THE SA FORUMS WILL REMOVE THIS BIG AD, THE ANNOYING UNDERLINED ADS, AND STUPID INTERSTITIAL ADS!!!

You can: log in, read the tech support FAQ, or request your lost password. This dumb message (and those ads) will appear on every screen until you register! Get rid of this crap by registering your own SA Forums Account and joining roughly 150,000 Goons, for the one-time price of $9.95! We charge money because it costs us money per month for bills, and since we don't believe in showing ads to our users, we try to make the money back through forum registrations.
 
  • Post
  • Reply
Mercury_Storm
Jun 12, 2003

*chomp chomp chomp*
Got some amazing fidelity on this one:

"a baby seal that eats only Doritos and drinks only Mountain Lion on an apartment carpet floor" :q:

Adbot
ADBOT LOVES YOU

Rutibex
Sep 9, 2001

by Fluffdaddy

Mercury_Storm posted:

Got some amazing fidelity on this one:

"a baby seal that eats only Doritos and drinks only Mountain Lion on an apartment carpet floor" :q:



you liar! thats just a normal picture. your no AI artist :colbert:

Mercury_Storm
Jun 12, 2003

*chomp chomp chomp*
NOOOoooo! how will my reputation as an AI artist recover from this gaffe!!

Tamba
Apr 5, 2010

Rutibex posted:

you liar! thats just a normal picture. your no AI artist :colbert:

You can tell because the text is not messed up :v:
Turns out that making text is harder than making images

Tamba fucked around with this message at 23:28 on Oct 22, 2022

Rutibex
Sep 9, 2001

by Fluffdaddy

Tamba posted:

You can tell because the text is not messed up :v:
Turns out that making text is harder than making images

also im sure "drinking mountain lion" would produce very different results :v:

an actual frog
Mar 1, 2007


HEH, HEH, HEH!

Tamba posted:

You can tell because the text is not messed up :v:
:hmmyes:


e: a cute plushie baby seal orb on a carpet floor, surrounded by doritos and mountain dew

Rutibex
Sep 9, 2001

by Fluffdaddy
"a baby seal that eats only Doritos and drinks only Mountain Lion on an apartment carpet floor"

Attack on Princess
Dec 15, 2008

To yolo rolls! The cause and solution to all problems!
plush baby seal on carpet, doritos bag, mountain lion

deep dish peat moss
Jul 27, 2006

mobby_6kl posted:

SD seems to have absolutely no idea who Beavis and Butt-head are but the results are... something





if you think that's bad you should see Midjourney's take

daguerrotype photograph of beavis and butthead in an early earth jungle





bonus
beavis and butthead cuddling on the couch, by studio ghibli and alex ross

Attack on Princess
Dec 15, 2008

To yolo rolls! The cause and solution to all problems!
I gave Lexica.art the Beavis & Butthead challenge, and it attacked me with this


Beavis and butthead :: 8k resolution concept art by magali villeneuve :: patrice murciano :: minjae lee :: beautiful lighting :: hyperdetailed :: intricately detailed splash art trending on artstation :: deep colors :: unique striking composition :: james jean :: jonas de ro :: alena aenami :: sharp focus

I appreciate that it book-ended the set with each of them.

Attack on Princess fucked around with this message at 03:20 on Oct 23, 2022

The Sausages
Sep 30, 2012

What do you want to do? Who do you want to be?
lexica.art is probably the best free SD service and the prompt search/image search tools are useful and fun. You even can adjust the image size.

The outputs aren't high quality and you can't pick the sampler but they'll do the job for just messing around, you can always take the same prompts and seeds and use a different service for fine tuning. They also upscale automatically.

I'm not sure what the usage limit is, it's come back with "try again later" a couple of times, then immediately gone back to spitting out pics.

"Rainbow Lion, Street Art"

precision
May 7, 2006

by VideoGames
it seems as though DALLE finds pokemon quite confusing

"an Oddish and an Eevee happily walking along a woodland path, anime"



:psyduck:

Rutibex
Sep 9, 2001

by Fluffdaddy
"Christmas card reindeer and Santa by Anton semenov"


"a man made out of the best bread ever, artisnal bread, bread man, crust"

Rutibex fucked around with this message at 18:29 on Oct 23, 2022

RPATDO_LAMD
Mar 22, 2013

🐘🪠🍆

they are working on the fourth iteration of the waifu-diffusion model already
this one will have 10-20 million anime jpegs in the dataset, compared to just 50k for the first version (it's still based on sd 1.4 though, not 1.5)
seems like the money to make bigger and bigger finetunes is rolling in fast

Wheany
Mar 17, 2006

Spinyahahahahahahahahahahahaha!

Doctor Rope

BrainDance posted:

One thing I noticed is that I'm getting very different results now, less these long essays and more scenarios which is cool but I wish I understood exactly why so I could fine tine things even more.

You could try tweaking the repetition_penalty, temperature and TOP_P values. The higher the repetition_penalty is, the less likely the model is to generate a token it has already seen, so the generations become more unique. Higher temperature means the model is more likely to generate less likely tokens, which is roughly how """creative""" the model becomes. TOP_P sets a threshold for the quality/likelihood of the generated tokens. Set the temperature high and TOP_P low and you get random nonsense. Set TOP_P high and it filters out most of the worst garbage. Set temperature low and the generated text takes less liberties with the prompt.

Rutibex
Sep 9, 2001

by Fluffdaddy

LifeSunDeath
Jan 4, 2007

still gay rights and smoke weed every day

this are really cool

Rutibex
Sep 9, 2001

by Fluffdaddy

LifeSunDeath posted:

this are really cool

i was reluctant to post the prompt because its kind of embarrassing "portrait of a mother giving milk to an alien". gives a lot of very bizarre and creepy results!


TheWorldsaStage
Sep 10, 2020


I love this so much

feedmyleg
Dec 25, 2004
A couple of days ago I was having trouble getting to bed, thinking about the imminent collapse of our society and trying to be ever so slightly less fatalist and cynical about the future. I thought back to how close man was to the brink of extinction in the ice age, and decided to use Dreamily to generate the wording for a story I had the shape of in my head. It was surprisingly easy to direct the AI to mostly stick with what I had in mind, and definitely improve it in areas. I got inspiration from what it wrote, and used it to spark new ideas and move the story and emotions forward in ways I wouldn't have otherwise. It got off course plenty, and I had to write a few really prescriptive things in order to point it back in the right direction (mostly in the story the young man tells), but I really like how it came out, which was more or less how I had imagined. The prompt involved two cavemen walking through a snowy mountain pass.

quote:

"Do you remember the stories?" The young hunter whispers to his partner, who seems lost in thought as he stares into the cold, icy nothingness.
The older man looks over at him with furrowed brows before replying, "No." He stops walking momentarily and faces forward again, eyes scanning the horizon, "We have no use for those stories now. They speak of green fields and flowers." His gaze drifts back down towards where they came from and he continues walking.
The younger human follows suit and falls into step beside him once more. "If we ever make it across the mountains, what do you think we'll find there?" He asks curiously.
The older man did not reply.
"Something new?" The younger man asks eagerly, looking up hopefully at his companion.
The older hunter only shrugs and continues walking, though he does seem to frown a bit as his lips form around the words, "Maybe. But I'm not sure if that's possible anymore."
He continues to trail along without further comment, and the shorter man keeps walking beside him, occasionally stealing glances at the man next to him and wondering why he is always so quiet.
They continue on, the snow crunching underfoot and making the air cold even through the thick material of their heavy winter clothes.
"How much farther tonight?" The young hunter finally speaks, breaking the silence.
His question earns another shrug from the older man, but he answers anyway, "A little farther." He glances ahead as if to emphasize that the journey is almost complete, but says no more.
"Tell me a story," the young man said, "of green fields and flowers."
The old man grimaced, lips tight.
"If you do not," the young man chuckled, "then I will be forced to make up my own. And you hate my stories."
"You want to hear a story like the ones from your father?" The old man replied, sneering, "The ones about the foxes? About a man who made a beautiful bird in his hands out of a broken eggshell? About a woman with red hair?" The last sentence dripped with contempt.
The young man was silent, watching as the old hunter marched on through the snow. In the distance, the first pale rays of dawn were appearing.
"The foxes are dead." The old man hoisted himself up a rocky outcropping at the crest of the hill. "The man is dead, the bird is dead, the woman is dead." He gestured toward the unending tundra. "Nowhere to go."
The young man followed after him silently, climbing onto the rocky summit to join the hunter.
They stood together on top of the mountain peak overlooking the valley below, staring out across the empty landscape, the only sounds the soft patter of snow hitting stone.
"All that remains is for you to grow colder and colder." He glanced at the young hunter, who had followed him, and frowned, "And for me, to be dead. We've reached the end of the world."
The young hunter looked away, feeling ashamed.
"It's getting harder and harder to see the sun. It's getting harder and harder to see anything. Soon there will be nothing left to hunt or eat." The old man continued, "Nothing except for each other."
The young man nodded silently, thinking of all the stories his father had told him, before the valley had frozen over. Stories of brave hunters returning in triumph, of bountiful harvests of crops beyond count, of strange and curious goods brought from faraway lands. All the wonders the old man had dreamed up, to entertain the little boy when he was sick or scared. Stories of love and family and life.
And now, all that was gone.
"I have a story," the young hunter said suddenly.
His companion looked at him with mild interest, "Go on then," the old man encouraged softly, "What is it about?"
The young man hesitated before continuing, "It's about a young woman, whose tribe had been following a group of caribou. One night, a storm came in, and washed all but her out to sea, drowned. Alone and with no better plan, she continued to follow the herd. For many moons she walked in their shadow, hunting rabbit and fox when she could..."
The old man listened with half an ear, eyes fixed outwards towards the lightening land. When the young hunter paused, his attention returned to his companion.
"...her hair turned grey, following the caribou. She came to know them well, to live amongst them. To eat what they ate, to sleep where they slept. Her hair became thick and hardy, a pelt much like theirs. Her hands and feet became hard and calloused until they were like hooves. As time passed, she became less like a woman and more animal; cunning and quick. And soon enough she had become one of them."
The man stopped speaking and stared off across the valley. After a moment he added, "She grew strong too, becoming as strong as the most powerful of the herd. When wolves came, she used her cunning to stave off their attacks. When rivers froze over, she led them over the ice to hot springs. When the wind howled, she held firm against it. The herd thrived. But, like all things, one day she died. And the herd still thrived. Even now, the herd yet thrives."
Silence hung heavily over the pair, only broken by the occasional distant cry of a raven. The young man looked up at the sky. The sun had begun to rise higher in the east, the rays piercing the black dome above.
"So what happens when the sun rises?" He asked, turning toward the older hunter.
The old man shrugged. "The day begins anew."
The young man nodded, turning back toward the valley to watch it change colors slowly as the sun stretched over the tundra. "It must have been quite beautiful," he murmured to no one in particular.
There was another pause, then a grunt of agreement. The old man reached for a rock and slowly sat, stiff knees creaking under the weight of his long furs, staring out across the expanse of snow and ice. The young man sat behind, watching the valley fill with light. Silence reigned throughout the hills as the old man's breathing slowed, growing more and more shallow.
Suddenly the young hunter felt a hand upon his shoulder and a soft voice whispering in his ear, "Will you tell me one more?"
The young man smiled gently and turned around in time to see his companion lay back against the rocky cliff and close his eyes. Their breath rose in wispy clouds, and the young man began to whisper stories to the sunrise.

The tense changes at one point, and there's probably a few minor goofs here and there, but I was impressed. I ran it through an automatic plagiarism filter and it picked up a decent number of sentences yanked from everything from random nonfiction YouTube videos to old half-forgotten pulp fiction. Once these tools reach full maturity and the copyright issues are cleared up, it's really going to be scary how fully they'll be embraced by authors.

I like this story enough that I decided to adapt it into a comic book as an experiment:





This also involved a ton of image generation for every panel in MidJourney, picking the handful that felt close to what I had imagined or pleasantly surprised me, then selectively erasing things and adding in new prompts in DALL-E and expanding the scenes. I also manually adjusted the colors here and there to match a bit more, but nothing is painted or added by hand.

After a certain point, what I was able to do with the tool started to make the visuals feel very repetitive, so I stopped. I couldn't get it to do specific poses or compositions which would add a ton to the visual storytelling, and it looses a lot of emotion that's present in the prose because of it. I couldn't even get them to consistently hold spears or bows, or show emotions easily.

Still, a fun experiment.

feedmyleg fucked around with this message at 04:05 on Oct 24, 2022

Elotana
Dec 12, 2003

and i'm putting it all on the goddamn expense account
Midjourney anime beta is looking sharp



KwegiboHB
Feb 2, 2004

nonconformist art brut
Negative prompt: amenable, compliant, docile, law-abiding, lawful, legal, legitimate, obedient, orderly, submissive, tractable
Steps: 32, Sampler: DPM++ 2M Karras, CFG scale: 11, Seed: 520244594, Size: 512x512, Model hash: 99fd5c4b6f, Model: seekArtMEGA_mega20
This post inspired by a couple of iconic photographs.
https://news.mit.edu/2016/scene-at-mit-margaret-hamilton-apollo-code-0817
https://www.pbs.org/newshour/science/katie-bouman-hardly-knew-what-a-black-hole-was-her-algorithm-helped-us-see-one
It is simply amazing how far we have come in so short a time. I want to acknowledge the hard work that came before that let me make the next images on a home computer with just a few words. This definitely feels like cheating lol.



Imgur Gallery, 40 images - Casually Peeking Into Black Holes

XYZAB
Jun 29, 2003

HNNNNNGG!!

BrainDance
May 8, 2007

Disco all night long!

Tried to do my first thing with dreambooth, training it on some pictures of myself

So, from this repo, https://github.com/XavierXiao/Dreambooth-Stable-Diffusion it just stopped at this point

quote:

Average Epoch time: 864.25 seconds
Average Peak memory 21626.06MiB
Epoch 0: 20%|▏| 801/3992 [14:24<57:23, 1.08s/it, loss=0.316, v_num=0, train/loss_simple_step=0.00608, train/loss_vlb_step=3.1e-5, train/loss_step=0.00608, global_step=799.0, train/loss_simple_epoch=0.161, train/loss_vlb_epoch=0.00187,
Saving latest checkpoint...

No error message, nothing, just stopped. And it gave me a model that seems to work? It's super uncanny because I just grabbed a handful of random pictures of myself but, Is that right, like is there a sensible reason it just stopped at 20% or is this wrong and somethings broken?

Rutibex
Sep 9, 2001

by Fluffdaddy

feedmyleg posted:

A couple of days ago I was having trouble getting to bed, thinking about the imminent collapse of our society and trying to be ever so slightly less fatalist and cynical about the future. I thought back to how close man was to the brink of extinction in the ice age, and decided to use Dreamily to generate the wording for a story I had the shape of in my head. It was surprisingly easy to direct the AI to mostly stick with what I had in mind, and definitely improve it in areas. I got inspiration from what it wrote, and used it to spark new ideas and move the story and emotions forward in ways I wouldn't have otherwise. It got off course plenty, and I had to write a few really prescriptive things in order to point it back in the right direction (mostly in the story the young man tells), but I really like how it came out, which was more or less how I had imagined. The prompt involved two cavemen walking through a snowy mountain pass.

The tense changes at one point, and there's probably a few minor goofs here and there, but I was impressed. I ran it through an automatic plagiarism filter and it picked up a decent number of sentences yanked from everything from random nonfiction YouTube videos to old half-forgotten pulp fiction. Once these tools reach full maturity and the copyright issues are cleared up, it's really going to be scary how fully they'll be embraced by authors.

I like this story enough that I decided to adapt it into a comic book as an experiment:





This also involved a ton of image generation for every panel in MidJourney, picking the handful that felt close to what I had imagined or pleasantly surprised me, then selectively erasing things and adding in new prompts in DALL-E and expanding the scenes. I also manually adjusted the colors here and there to match a bit more, but nothing is painted or added by hand.

After a certain point, what I was able to do with the tool started to make the visuals feel very repetitive, so I stopped. I couldn't get it to do specific poses or compositions which would add a ton to the visual storytelling, and it looses a lot of emotion that's present in the prose because of it. I couldn't even get them to consistently hold spears or bows, or show emotions easily.

Still, a fun experiment.

This is awesome thank you! I am also currently working on a project that uses the AIs for writting and art assistance. It's gonna be a D&D adventure and hopefully it will look fancy with all of my new AI art, unlike my last two which used public domain clip art.

Sedgr
Sep 16, 2007

Neat!

Is this you btw?

Rutibex posted:

the best outcome Ukraninan civilians is for Russia to purge out every last western influences from the country and end the civil war. going back to the status quo of the last 7 years is not ideal

Rutibex posted:

If you want to argue that the lines on the map as conceived by western powers are sacred than I guess russia is pure evil. but to me this is a civil war

Rutibex posted:

russia isn't doing any genocide, unless you count nazis as a culture. it could be argued that Ukraine was doing a genocide against Russian speaking Ukrainians though. do you care about them?

Rutibex posted:

russia could just nuke the entire ukranian army and send in guys with radiation suits to occupy the rubble. i hope Ukrainians understand this, they actually can't win no matter what. winning just means escalation

(USER WAS PUT ON PROBATION FOR THIS POST)

Seth Pecksniff
May 27, 2004

can't believe shrek is fucking dead. rip to a real one.
I mean this very sincerely and very seriously:

Do not import drama from other forums, especially in a thread dedicated to AI Art that's been chugging along fine so far. GBS is one of the few forums on this site where anyone is allowed to post (except getfiscal), and as such we don't forumban anyone. If someone's posting along just fine in a thread, leave them be. If you think they're breaking a rule, report them.

If you have problems with other forums, take it up with the admins or their mods. Don't do whatever it was above. And I don't want to turn this into a discussion thread on this particular post so let's move on. If you have questions about this feel free to PM me and I'll get back to you as soon as I'm able.

mobby_6kl
Aug 9, 2009

by Fluffdaddy
Yeah well they imported the drama to GBS themselves with horrible takes.



You can make your own! "professional oil painting of a man punching a nazi_ss_officer with fist, amazing art, trending on artstation"

Boba Pearl
Dec 27, 2019

by Athanatos
So a really interesting way to use AI in digital art that's not being really talked about is upscaling. Automatic-1111 has the option to use SwanIR tiles, and you can use that to take a reference image and make it huge. One of the problems I run into a lot (because I photobash 3D models and trace from reference,) is that I don't always have a high quality reference at the size I need.

NSFW pic, but basically, I was struggling to figure out how I'd draw this part of a scene:



because it's just a small part of the canvas, I know it doesn't look small but when you're tracing you need lots of space for clean lines, and part of a much larger scene (which I can't really post because anatomic models are primarily nude, if barbie doll nude)



A normal part of my process now is using this tile based upscaling to get very clean references at absurd resolutions, which also lets me get more texture in the line work, and makes the piece look more cohesive when it's down-scaled. Some webtoons are done by teams, and so have seperate people sketch, ink, and color. I was thinking how more traditional artists, until the AI gets to the necessary points, could use it to massively up scale the sketches as they pass them from the sketcher to the inker, and how that might help get smoother and cleaner lines.

WhiteHowler
Apr 3, 2001

I'M HUGE!
The prompt was "puppy races".



I'm not sure what foul sorcery brought this about.

I did get a better one:

MechanicalTomPetty
Oct 30, 2011

Runnin' down a dream
That never would come to me
Not sure if this is even the right place to ask, but what exactly is the “best” ai writing tool out there right now? I was futzing around with Novel AI yesterday and it seems to have a lot of neat features to work with.

KinkyJohn
Sep 19, 2002

It's interesting that the most critical and expensive part of making a good ai model is a properly tagged dataset of source images to train on.

Which the image stock companies posess. But, the existence of such an ai model directly threatens their own existence.

So I'm wondering what the conversations are like in the boardrooms of places like Shutterstock. Do they attempt to create their own ai or do they wait for their own inevitable demise?

deep dish peat moss
Jul 27, 2006

MechanicalTomPetty posted:

Not sure if this is even the right place to ask, but what exactly is the “best” ai writing tool out there right now? I was futzing around with Novel AI yesterday and it seems to have a lot of neat features to work with.

Unless you need it tailored for a specific purpose like copywriting, go directly to GPT3 through openAI:
https://openai.com/api/
https://beta.openai.com/playground

Their best model (Davinci) ends up costing about $0.25 per 1k words. Their cheaper models like Ada are like, 10k+ words per $0.01 - and you start off with $18 in free credit. You do have to give them your phone number though. Definitely recommend reading the manual if you want to get serious about it, but it can do an enormous variety of things you wouldn't expect out of a text AI. You could probably subcontract like 80% of your average computer toucher office job to it - it can write your emails, it can bugfix your code, it can write your pivot tables, it can translate natural language to code...

AFAIK there's no other writing AI that really competes, other than purpose-built ones for specific tasks, and those may or may not be based on gpt3 in the first place. I am less familiar with text AI than image AI though

e: FWIW I just looked at NovelAI and it is as far as I can tell based on GPT1 so it has cool features but they'd be pretty far behind GPT3 on actual power (this is not at all a 100% accurate comparison but imagine GPT1 as someone who is conversational in English but doesn't grasp its nuances, vs GPT3 as a fluent and somewhat eloquent English speaker), which is unfortunately the case with most GPT-based tools I believe.

deep dish peat moss fucked around with this message at 23:56 on Oct 24, 2022

IShallRiseAgain
Sep 12, 2008

Well ain't that precious?

deep dish peat moss posted:

Unless you need it tailored for a specific purpose like copywriting, go directly to GPT3 through openAI:
https://openai.com/api/
https://beta.openai.com/playground

Their best model (Davinci) ends up costing about $0.25 per 1k words. Their cheaper models like Ada are like, 10k+ words per $0.01 - and you start off with $18 in free credit. You do have to give them your phone number though. Definitely recommend reading the manual if you want to get serious about it, but it can do an enormous variety of things you wouldn't expect out of a text AI. You could probably subcontract like 80% of your average computer toucher office job to it - it can write your emails, it can bugfix your code, it can write your pivot tables, it can translate natural language to code...

AFAIK there's no other writing AI that really competes, other than purpose-built ones for specific tasks, and those may or may not be based on gpt3 in the first place. I am less familiar with text AI than image AI though

e: FWIW I just looked at NovelAI and it is as far as I can tell based on GPT1 so it has cool features but they'd be pretty far behind GPT3 on actual power (this is not at all a 100% accurate comparison but imagine GPT1 as someone who is conversational in English but doesn't grasp its nuances, vs GPT3 as a fluent and somewhat eloquent English speaker), which is unfortunately the case with most GPT-based tools I believe.

Based on the leak It looks like it uses GPT-Neo

Boba Pearl
Dec 27, 2019

by Athanatos
KoboldAI is free but runs on your GPU so if you have a top of the line gaming PC that could be an option for you.

lunar detritus
May 6, 2009


Boba Pearl posted:

KoboldAI is free but runs on your GPU so if you have a top of the line gaming PC that could be an option for you.

Most model options are pretty bad though, unless you have a ton of VRAM and system RAM (for example the 20B models can run on 10GB VRAM but you need 32GB of RAM and it takes minutes to generate even a bit of text)

Boba Pearl
Dec 27, 2019

by Athanatos
Yeah I have a 3090, but I run everything on runpod which is about 1$ an hour. I'm looking at Jasper but it's expensive, and I don't want to pay a sub AND per word, which means NovelAI but that's pretty trash because it's not a very good Neo tune, and whatever they use loses a lot of info even with world information.

Squatch Ambassador
Nov 12, 2008

What? Never seen a shaved Squatch before?
Messing with clips from 2001: A Space Odyssey

https://i.imgur.com/C1zwzIy.mp4

The furry_tranformation hypernetwork that came with the novelai leak can lead to some cursed faces.
https://i.imgur.com/XkstV6c.mp4

I like how it keeps his stare mostly intact even with the denoise turned up to 0.5, and how it can't decide how many mouths he should have

Commie Lasorda
May 15, 2009

IT'S CLOBBERIN' TIME!
I try to come up with cool and creative prompts but I always default to some dumb poo poo

Adbot
ADBOT LOVES YOU

LifeSunDeath
Jan 4, 2007

still gay rights and smoke weed every day

Drive-Thru Salad Bar posted:

I try to come up with cool and creative prompts but I always default to some dumb poo poo



hot drat lol

  • 1
  • 2
  • 3
  • 4
  • 5
  • Post
  • Reply