Pony:
A model of Natasha Aughey, trained over 151 images at 1024 using Pony Diffusion V6 XL as a training model
Trigger word: natasha aughey
Weight: 1 to 0.5 (0.6 is recommended)
Appearance tags: long hair, black hair, brown eyes, muscular female
Additional information:
Webui I use
VAE I use
R-ESRGAN 4x+ Anime6B upscaler for anime
4x NMKD Superscale upscaler for realistic
Imagine dimensions vary depending on what I'm trying to do
Sampling steps I go 20-30
hires steps I go 10-15 (I don't always use hires fix)
Denoising strength I go 0.4
I use 3 CFG Scale and CFG Scale Fix set at 7
uddetailer for faces
SD 1.5:
There isn't a trigger word just set the weight and you're good to go
For weight you can go 0.6 to 1
All images you see have been Upscaled with 4x-UltraSharp from 512x512 to 1024x1024
If you wanna support me ko-fi
Description
FAQ
Comments (7)
Didn't know her, googled her, built like a superhero
She is indeed
Great work thank you! getting pretty good results. Did you trained it on the site or locally?
Thank you for the kind words, I did train it here yes
@infamous__fish You're welcome, very nice work, i guess it is about the training settings and the quality of the pics.
@chrisss1 I would say 90% is the pictures and 10% is the settings
@infamous__fish True, that makes sense