This is a LoRA for inducing a cartoon/comic feel.
It aims to stylize the character with small influence over the used checkpoint style.
It works best with anime/cartoon models, but it also works with realistic ones.
No keyword/trigger. Meant to be used within 0.8-1.2 weight range.
Goes crazy above 1.5, gives a photo/drawing vibe below 0.
ADetailer/HiRes.fix recommended!
Strengths:
girls (and feminine/anime boys)
portraits and closeups
stylized hair and eyes
tight clothes
sfw and light nsfw
Weaknesses:
closely following pose prompts (ControlNet helps greatly)
some hairstyles are improbable due to stylization
loose clothes
nudity and hardcore nsfw
Description
Second version
This version is less likely to produce random polygons in the background and it should be more consistent across different checkpoints, but is not compatible with as many models as v1.
It is not a direct improvement over v1, rather v2 aims for a softer, rounder, more comic-like style compared to it. It also moves its attention to the whole picture, instead of just focusing on mainly the face and hair.
As such, v2 inherits most of the strengths and weaknesses of v1.
It does, however, hate covered shoulders even more than v1.
FAQ
Comments (1)
What base model did you use for the photo of the girl with the green hair? I love that style the most