DickContest

joined 2 years ago
MODERATOR OF
[–] [email protected] 4 points 1 year ago (1 children)

Fucked up hands and the face is too smooth compared to the body. Should look into autodetailer and reduce the amount of facial correction.

[–] [email protected] 1 points 2 years ago

Low quality pictures? Could be a fetish I guess.

[–] [email protected] -1 points 2 years ago

Do you have measurements to go with that?

You can zoom in all you want, but next to your hand it looks like an average dick at best.

[–] [email protected] 1 points 2 years ago (1 children)

That's a firm 10/10.

[–] [email protected] 2 points 2 years ago (1 children)

It looked like a giant swollen pussy. Huge mound splitting apart. I'll post a photo tomorrow when I'm on my pc.

[–] [email protected] 1 points 2 years ago

It is a local installation. No worries on the questions, how we learn. I don't currently do any custom training on my models - this is Deliberate V2 straight from civitai.com. If you are using the standard model that might be part of your problem.

Try adding "imperfect skin" to the positive prompt, make sure you are using DDIM instead of euler_a and use 40+ steps.

[–] [email protected] 4 points 2 years ago (2 children)

Stable Diffusion on a 4090. I find DDIM sampling is far superior to the default euler_a but it takes fractionally longer. I typically do a 768x512 base image. If it is good then I img2img it to 1.5x size using between 0.4 and 0.6 diffusion. If the results are still good then I upscale using SD Upscale to 2x the size (splits it into pieces) using between 0.2 and 0.3 diffusion.

At any point if the images sucks I can go back a step and adjust.

Prompts tend to matter. It was surprising that switching "woman" to "lesbian" for this prompt immediately made the characters objectively less attractive - like visibly older. Adding "ugly" to the negative prompt then corrected that problem while still maintaining subtle things like the haircut.

[–] [email protected] 2 points 2 years ago

Thanks. Just went through and fixed all my posts.

[–] [email protected] 5 points 2 years ago (2 children)

What is an enby? (Normally I would just google it, but want to encourage conversation on here).

[–] [email protected] 3 points 2 years ago (1 children)

I always think of the scene in silicon valley where Denesh has to look at millions of pics of dicks to train AI...guess it's hard to find a lot of bored nerds to do that for free.

There are some impressive LORAs but I haven't figured out the trick to get in painting to do just that area well. I can make two chicks with dicks...but not my thing. If anyone has a good method for realistic mixed genders in the same scene please share.

[–] [email protected] 1 points 2 years ago

I'm not usually interested in gonemild...thanks for changing my mind :). Hope you stick around!

[–] [email protected] 5 points 2 years ago (1 children)

I tend to find the models amplifying age. 18 doesn't always look obviously 18 and 45+ can often come out looking 65. I wasn't originally planning on posting my prompt and the outcome looks more like the fantasy I was aiming for.

view more: next ›