This LoRA model is similar to my HyperAss model but focuses more on thick thighs and hips. Great for that pear shaped look. You can always tone down the strength to more reasonable levels.
LoRA is now supported in A1111 as of Jan/2023
I used `<lora:FantasyRacePack_V1_e8:0.15>` for the goblin images
Abyss Orange is the base model for images, Av3 for training
Training Details:
270 images
LR 8e-5
batch 2
GA 8
dim 4
base model Av3
Av3 VAE
flip aug
clip skip 2
Only Unet training
bucketing at 768
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.