Recommendations:
Lora Weight: 0.3-0.7
CLIP SKIP 0-1
DivineEleganceMix or AbyssOrangeMix3 | models
The resolution of the original dataset images leaves much to be desired, so I recommend you to use upscale ( or HighRes fix ) on your images.
Additional train info:
Trained on: AbyssOrangeMix3.
Trained on 27+ anime images.
Description
A new training approach.
Better outfit drawling.
Better face drawling.
Smaller size.
Now LoRA!
Details
Downloads
194
Platform
CivitAI
Platform Status
Available
Created
10/14/2023
Updated
9/26/2025
Deleted
-
Trigger Words:
HUMajor
HUMajor, man, military uniform
Files
V1HUMajorLoRA.safetensors
Mirrors
CivitAI (1 mirrors)