I'm excited to share my first LoRA featuring Molang, the adorable rabbit. This model captures Molang in various poses and styles, perfect for creating heartwarming and cute images.
Recommended Model: For the best results, I suggest using this LoRA with the SD 1.5 CHECKPOINT model:
Cuteyukimixadorable Style
Keyword List for optimal results:
no humans
rabbit
simple background
animal
animal focus
:3
blush
solo
looking at viewer
blush stickers
bird
chick
smile
standing
closed eyes
holding
full body
solid circle eyes
open mouth
pink background
white background
blue background
food
star (symbol)
sky
._.
fruit
:<
cloud
monochrome
heart
checkered background
closed mouth
yellow background
rainbow
food focus
artist name
signature
strawberry
grass
green background
creature
one eye closed
bear
sparkle
moon
purple background
crescent moon
Test Configuration:
Sampling Method: Euler A, DPM++ 2S a
Scheduler Type: Automatic, Karras
Sampling Steps: 30 to 60 depending on the sampling method, with 40 being an optimal choice for most cases.
High Resolution Fix (HIRES FIX):
Upscaling Model: R-ESRGAN 4x+ Anime6B
Hires Steps: 10-20 (I recommend experimenting for best results)
Denoising Strength: Between 0.5 and 0.7
Upscale by: x2 (adjust based on desired resolution and texture optimization)
Additional Recommended Settings:
Clip Skip: 1
CFG Scale: 7
LoRA Strength: Between 0.5 and 0.8 (using 1 can lead to too many Molangs popping up... haha!)
Face Generation: The model generally generates Molang’s face well, but occasionally creates extra parts or details that weren't intended.
Extra Animals: Sometimes, additional animals or elements appear in the image. This behavior seems to vary depending on the base model used.
1. Dieses Modell dient nur Lernzwecken. Urheber- und Auslegungsrechte liegen beim Originalautor.
2. Bist du der Originalautor eines Modells, kontaktiere uns bitte zur Authentifizierung über unsere offiziellen Kanäle. Wir schützen die Rechte aller Schöpfer. Hier klicken, um es zu verifizieren.
