Type | |
Stats | 1,842 13,478 1.7k |
Reviews | (269) |
Published | Mar 22, 2024 |
Base Model | |
Training | Steps: 2,720 Epochs: 16 |
Hash | AutoV2 667C084F74 |
This LoRA aims to replicate the style of artist Sincos. Please support the artist.
Please share you creations! I'm curious to see what you can achieve with my models!
Recommended parameters:
Base model: Pony Diffusion XL v6, AutismMix...
CFG Scale: 6-7
Sampler: Euler a
Steps: 25 - 35
LoRA Strength: 0.8 - 1.0
Inpainting is your friend to fix faces and details, but I advise you to use with 15-20 steps.
Positive prompt:
score_9,score_8_up,score_7_up,score_6_up,source anime, uncensored, ...
Negative prompt:
score_6,score_5,score_4, censored, bar_censor, text, japanese_text, ...
Some of the images in the dataset still have censoring, that's why I recommend putting those tags in positive / negative prompt.
This model comes with no warranty. Do not use this model for inappropriate purposes.