If you like my work then drop a 5 review and hit the heart icon
Character commission is open on Patreon
Join my New Discord Server
This model has no VAE baked in so you don't need to use any vae with the baked version.
Suggested settings:
I had CLIP skip 2 on every image
I had ENSD: 31337 all of them
All of them had highres.fix or img2img at higher resolution.
I don't use restore faces
NOTE: if you find any prompt of the preview images look familiar it's because I've taken them from other model review images, Credits to the original authors. Thanks for the benchmark.
Description
FAQ
Comments (10)
Hello. I'm new to stable diffusion and I like this style. I'm still learning. can you elaborate on what is clip skip and ENSD? thank you.
Clip Skip is an option in Automatic1111. I am still learning the specifics of what it does myself, but I know that many models like to have it set to 2, while the default value is 1.
as far as i know, SD images are mode with different layers and with clip skip we skip the selected amounts of layers. most of the anime models are trained with clip skip 2 so we use clip skip to generate the image. just experiment.
If you want know about clip skip and how used him, check this, bro:
https://www.youtube.com/watch?v=wVVv81bqCg4&list=LL&index=1&t=34s&pp=gAQBiAQB
Can you at least vaguely describe what this model is? I mean the purpose. Maybe pros/cons, or something.
its an anime model that can do colorful HD anime stuff with great details when used with highres fix. what else is there to say. as seen in the preview and review.
What's the mix recipe?
good job, man, this checkpoint amazing, thank you for your work