SDVN11-Ghibli-flux

SDVN11-Ghibli-flux | dev fp8 hyper version

_____

📖 Checkpoint Info

Info : This model was trained by me from 7200 photos, compiled from 17 different movies from Ghibli animation company. I train with 72000 steps to achieve maximum efficiency. You will see that the model will show off the Ghibli style even withou* ***ng the activation keyword. In addition, when using the keyword Ghibli, the model will give very good results. People can use the activation keyword Ghibli or the name of any Ghibli movie

____

This is the full standard version, I have optimized it to speed up shaping with 8steps and create the best stability in style and anatomy.

____

Info + Workflow:  https://huggingface.co/StableDiffusionVN/SDVN11-Ghibli-Flux

You can refer to some of the indicators below to achieve the best image quality :

CFG: 1

Steps: 8 (Hyper version)

Sampling: Euler

Scheduler: Simple

Key : (You can use a main keyword, Ghibli, or more specifically, you can use the name of any Ghibli movie)

ghibli

ghibli style

arrietty

castle in the sky

from up on poppy hill

grave of the fireflies

howl moving castle

kikis delivery service

mononoke

my neighbor totoro

on your mark

only yesterday

pom poko

ponyo

porco rosso

princess mononoke

rosso

spirited away

tales from earthsea

the ocean waves

the wind rises

_____

👨🏻‍💻 Creator : stablediffusion.vn

📢 Discord : Discord SDVN

📢 Facebook : Group SDVN