Recommended Settings are :
Steps: 30-64
CFG scale: 7
Sampler: DPM++ 2M
ADetailer face can fix face, eyes and some other problem
recommended ADetailer :
How to install :
go to the "Extension" tab then "Available" and check if you have already "https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui-extensions/master/index.json" then press "Load from:" and search for "ADetailer", install it and put your file previously installed in webui/models/adetailer and reload your stable diffusion ui. finally use it in the txt2img tab.
"anime source" for anime style (Other are for a more realistic style)
Positive Prompt :
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up
anime sourceNegative prompt is not perfect, it can influence the result's quality. (Use your own negative prompt for better results or use negative embedding).
Negative Prompt :
score_4, score_3, score_2, score_1 bad hands, missing fingers, (censor), monochrome, blurry 3d, source_cartoon text, signature, watermark, username, artist name (Merge of WAI-ANI-NSFW-PONYXL and Omega Pony XL anime style ,In files at V8 to V9 you have models with or without VAE.)
V2 changes :
Better Face
Better Hand
Better anatomy
Less young face strength
V3 changes :
Better Eyes
Better perspective anatomy
Less duplicated arms/legs
More women face/body strength
V4 changes :
Better Shadows
Better face expression
Less duplicated arms/legs
More duplicated fingers
V4.1 changes :
Just Newer Model form Omega Pony XL anime style V1 to V2
V5 changes :
Better age slider impact
More young face strength
Less perspective duplicated arms/legs
More duplicated fingers
V6 changes :
Better Background
better eyes
fix vae
V7 changes :
Fixed images appeared entirely covered with snowflakes
Added better backgrounds, mature women, and clothing
Fixed blurry eyes in medium and long shots.
Fixed some minor issues.
Description
(Newer merge)