AI [AI Art] - Show Us Your AI Skill *NO TEENS*

4.80 star(s) 6 Votes

devilkkw

Member
Mar 17, 2021
337
1,143
I have no clue at all. There's no actual documentation on it, and the code is fucking soup.
I tried variations of it, but it never actually seems to make any factual difference apart from lowering or raising both model and clip weight togheter (setting them both to 0.8 or 0.2 acts exactly how A1111 does Lora weights, but making them different values does something I can never predict nor understand so far, it becomes wildly random results).

And that's a problem with ComfyUI, either small details like this one are never explained anywhere at all, or terms like "weight", "clip", "noise", "steps", etc, have different meanings and logic behind them than how A1111 does it, for example.

IMO, it's a standards issue. All of the clients, webuis, etc, all of them follow no actual standard. So people have to spend days tweaking and testing things around on any of them to catch glimpses of what something does and how it does it, and only then produce something actually worth the time invested. That's both good and bad in equal measures.
What if you try make image withe same seed and modify only clip value of lora? i'm curios about tath.
I think comfy actually have good power, but in my case switching to it is not a good because i have to restart from 0 and have no time for doing experiment with it. maybe in a future i'll try it better.
Thank's again for reply.
 

SDAI-futa

Newbie
Dec 16, 2023
29
31
I enjoy creating futanari art and was looking for a place to post some of it. Here's something I created recently.
I use Standard Diffusion with different extension, and often finish off the work with Photoshop.

I hope to be able to post more here soon, I'm trying to learn the ropes around here :)

00167-1585416355.png
 
4.80 star(s) 6 Votes