who took a fat steaming **** all over image gen?

https://lemmy.world/post/42140600

who took a fat steaming **** all over image gen? - Lemmy.World

just joking. thought i’d join in the ai img mob riots since it looked fun. really i admire @perchance’s dedication to progress and willingness to try moving forward instead of being frozen into stagnation by the screams of users. i really am basically afk at this point, constantly in a state of either too busy, or too exhausted. but was generating some vertical pics today and noticed an unusual thing maybe yall might want to decipher. [https://lemmy.world/pictrs/image/1fee7964-d8dd-4437-aad3-33c3ac021819.png] thats what my gen gens up normally in her classic ‘word soup’ promptstyle. so i tried removing the Aesthetic 11 which i have both before and after all prompts. i had heard about it via some ‘bonkers insane but probably actually too genius’ person (like minori) posted that it was like a hidden ghost in teh machine. either that or it was a normal person but lead thru a rabbithole of bonkers insane craziness to the point that couldn’t tell whether it was real or what it really was. either way, i jumped on it and put it in BP as some secret juice. Now with img update totally changing large swaths of img gen, i tried removing it. [https://lemmy.world/pictrs/image/76e1a4c8-c9fa-4381-a93c-be31a5448c9d.png] Not as expected. Look at those worse hands and feet after removing it. i have more pics that magically arent uploading, but interesting eh? maybe its starting the prompt with the word aesthetic. maybe its the full aesthetic 11 crazy magician stuff. either way, youd especially see if these other imgs would upload that all the imgs without it have noticeably worse hands, feet, and sketchier fail lines.

Hmm, I don’t know, lots of weird stuff. I don’t trust out-of-nowhere crazy walls of text person, so I’ve removed their presence from my mental register.

But I worked out how to do photography, which is what most people seem to be complaining about, so here’s a short guide, hope it helps:

  • Use the default T2I.
  • Delete the negative prompt.
  • Set “style” to “NO STYLE”.

Then just play around with this template:

a low resolution photographic still frame from a cult 1980s b-movie, cinematic close-up portrait shot featuring a lonely wanderer, Jim. Background: Foggy streets of an antique gothic city. Midnight. Lit in ominous hues of purplish blue. Aesthetic: Dark fantasy. Photography Style: Modern avant garde cinema. Second millenium expressionist photography, professionally shot and composed. Natural Lighting: Exquisite strong blue lighting with dramatic deep red accents. Camera: 70mm IMAX MSM 9802. Jim walking through the streets.

Chose some pseudo LaserDisc mambo as baseline but you can change that around, obviously. And then you can keep going. Like say:

Jim walking through the streets. Face: describe Jim's face. Hair: describe Jim's hair. Eyes: same thing for the eyes... Body: idem Clothing: and so on and so on.

That template with a guidance scale of 11 has been working wonders for me, and it’s a simple enough pattern that you can easily modify it. I’m a weird case, because I have characters and style elements saved as JSON files, I just generate these things from an overcomplicated script (6000+ SLOC of spaghetti, should do a clean rewrite in Javascript and make it into a generator at this point…)

Anyway, I’m actually getting better results now than I was getting before the update, across the board. So, I’m sorry to folks having a bad time, but all the despair going around? Calling results useless and horrible and shit and all that? Man, that sounds like a skill issue. This entire situation only took me a wee bit of tinkering to solve, it was next to trivial. I mean, c’mon, people! You can do better! Or you can ask for help, maybe, now that would at least make this a more pleasant environment to be in.

OK OK I’ll stop now. Cheers! :)

AI Image Generator (free, no sign-up, unlimited)

A *fast*, unlimited, no login (ever!!!), AI image generator. Generate large *batches* of images all in just a few seconds. Generate AI art from text, completely free, online, no login or sign-up, no daily credit limits/restrictions/gimmicks, and it's fast. Other AI art generators often have annoying daily credit limits and require sign-up, or are slow - this one doesn't. Use this AI to generate high quality art, photos, cartoons, drawings, anime, thumbnails, pfps, and more. Create OCs, anime characters, AI villains, fanfic artwork, and pretty much anything else. It's an AI-based image generator - i.e. a text-to-image model. No watermark, no account needed, unlimited images. Type words, make pics.

cool, i’ll try that! thanks :)

also nice idea with your characters!

in case it gives you ideas when you make your JS, this is how i did mine. ᯽

my keyboard has a mode which allows touching a btn to summon that characters sequence of modules on a div below. Conversion is for Adjectives that describe anything, Feren for adjectives of people, Mer haircolor, Summin for race or culture, Betwyn setting etc. if i touch one once, lets say Eren’s haircolor, it makes it always in prompt. touch again and never. touch again and normal.

Number above each is amount of normal selections in a prompt. since its keyboard, button on right sends directly to focused textedit. this is the one of Dal for generating good nonspecific energy. pushing it.

comfortable comfortable growing deep profound wonderful symbiotic symbiotic cute futuristic utopian lounge and resort dreamlike room in an otherworldly dreamtemple vast otherworldly monument infinite endless vast imposing intimidating grand boundless endless infinite eternal futuristic absolutely beautiful creative divine beyond divine heavenly perfect heavenly divine beyond divine prolific passionate desirous enthusiastic

pretty promptOverloady, lol. i have a ton of characters and individual charactermaking is pretty behind, but, when ready, maybe even right after this lol, i could pick a character to give a Characters sequence of modules to, and do like Adjective, Adjective, Pose, Specific Character, Hair, Setting, etcetc, set it to only make that character, and fine tune all the other settings over time to eventually generate the variation, but of one character, i want. my example is wordsoupy, but nothing stopping it from being precise like your photography and then just tune the variation until perfect for that character.

thats my interface, would love to see yours when you make it!

also i made it so the sequence of modules was easy to try different sequences and thats been helpful. so hopefully thats a useful advice when u make your awesome one. cheers too!

I made a cute crybaby face.

object to string to object

datatransfer of oddly shaped objects worklessly