There's some really random times where the filter won't catch it, I guess they also use AI as a way to filter out explicit but posing naked is fine, I guess?Damn shame, it was a decent site for a time for people with a potato PC.
Sometime (and feel free to correct me if this has already happened), someone is going to use AI like this to create a game that will utterly blow us away. And will produce it blindingly quickly. Someone will create dynamic scenes with new characters that don't feel like they're cookie-cutter copies of old ones (like every amazon SSR7 draws). Don't get me wrong, I respect the difficulties SSR7 faces in having to draw all of these characters in all of these permutations.
I wish so much that SSR7 would do whatever you did here for the entire game.
Yeah, that's (one of) the dirty little secret of AI 'art'. Cherry-picking.Sometime (and feel free to correct me if this has already happened), someone is going to use AI like this to create a game that will utterly blow us away. And will produce it blindingly quickly. Someone will create dynamic scenes with new characters that don't feel like they're cookie-cutter copies of old ones (like every amazon SSR7 draws). Don't get me wrong, I respect the difficulties SSR7 faces in having to draw all of these characters in all of these permutations.
But seeing this, I find myself wishing you could combine whatever AI you're using with SSR7 to revamp the whole of Something Unlimited. I don't know how long it would take, but with AI replacing all of the scenes based on the art that's already there...I suspect it would be shockingly short. Unless there's like 100 bad images for every good one you show us here.
I'm working on a game that's focused on DC girls that's not SSR7 style. The main issue right now is ensuring that none of the loras I use are based on real people or real people's art styles. I'm trying to find a blend that works.Sometime (and feel free to correct me if this has already happened), someone is going to use AI like this to create a game that will utterly blow us away. And will produce it blindingly quickly. Someone will create dynamic scenes with new characters that don't feel like they're cookie-cutter copies of old ones (like every amazon SSR7 draws). Don't get me wrong, I respect the difficulties SSR7 faces in having to draw all of these characters in all of these permutations.
But seeing this, I find myself wishing you could combine whatever AI you're using with SSR7 to revamp the whole of Something Unlimited. I don't know how long it would take, but with AI replacing all of the scenes based on the art that's already there...I suspect it would be shockingly short. Unless there's like 100 bad images for every good one you show us here.
I think it might be even higher if you want the outfit to be absolutely consistent. Most of them have some miscellaneous bullshit that gets changed from render to render. Especially with the more complex outfits and masks. The average joe might not notice it, but someone would probably bitch in the thread for a game. Currently trying to figure out whether to put a disclaimer that tiny changes may happen, or just redo constantly.Character standing around in correct outfit? ~1:6
Character kneeling in correct outfit, giving BJ to a naked guy? ~1:8
Character dressed like someone else, giving BJ to a guy in a tuxedo? ~1:15
Trying to get multiple characters in one txt2img prompt is indeed hell. Trying to change one of the characters in inpainting is another kind of hell.Character, dressed as Sailor Moon, being anally fisted by a different character wearing a Pikachu onesie while sucking Lex's dick? 1:1000!
Can you please DM me on what tools you used for this please?I've been experimenting with more photorealistic images, so here are various girls being "Free Use" abused in the LexCorp office, but realistic.
(Hope they're not regarded as OT)
Zatanna:
View attachment 3773473
Black Canary:
View attachment 3773477
View attachment 3773475
Mercy Graves:
View attachment 3773474
View attachment 3773492
Supergirl:
View attachment 3773478
View attachment 3773479 View attachment 3773481 View attachment 3773483 View attachment 3773480
Huntress:
View attachment 3773482
View attachment 3773485 View attachment 3773484
Punchline:
View attachment 3773489
View attachment 3773486
Starfire:
View attachment 3773490
View attachment 3773488 View attachment 3773491
What kind of lora and model are you using? Details please.View attachment 4125298 View attachment 4125299 View attachment 4125302 View attachment 4125305 View attachment 4125301
The probability that I get a perfect picture is about 1/3-1/5
I use forge with autismmix confetti checkpoints. I think Jimwalrus has written a good guide somewhere on the forums for noobies with step by step instructions.Noob questions: What AI are you guys using? And how are you guys using it? I want to do the same.
I'll find it this evening and either DM it to you (Kane_Freeman) or post a link here.I use forge with autismmix confetti checkpoints. I think Jimwalrus has written a good guide somewhere on the forums for noobies with step by step instructions.