Changes from Ver.1
The training image size is changed to 512x512 to reduce the darkening of the edges of the image.
There are more types of backgrounds.
Her face has become more expressive.
Animal ears are easier to come out.
A weight setting of around 0.6 seems to be good.
---------------------------------------------------------------------------------------------------
Ver.1
I made the girl I met in "SpookyForest" into LoRA.
Her true identity may be a forest creature.
("GhostlyImage" LoRA used in the image is temporary)
A weight of around 0.5 is recommended.
Description
Changes from Ver.1
The training image size is changed to 512x512 to reduce the darkening of the edges of the image.
There are more types of backgrounds.
Her face has become more expressive.
Animal ears are easier to come out.
A weight setting of around 0.6 seems to be good.
FAQ
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.