This LoRA model was created by Gtonero
v1.4 Increase image training
If the situation is right, the resulting image will be less distorted.
recommend use highres.fix denoising = >0.4
prompt : (milking machine:1.0-1.2), (lactation:1.0-1.2),
If used with other LoRAs, increase str = (lactation) to 1.2
Training Data v.1.4
437 image 5 repeats 4 epochs
Powershell ISE run script kohya-ss
module = Networks.LoRA
cosine_with_restarts 3
8 DIM / 4 Alpha
U-net 1e-4
Loss ???
Popularity
Info
Version v.1.2_Beta: 1 File
About this version: v.1.2_Beta
LoRA is a beta with reduced DIM.
Increased the number of images trained, but the steps during training remain the same
Update in Beta
No need to tag leaning forward and upper body
Sometimes use the upper body if the resulting image is distorted.
I'll probably add a step in v.1.2 and reduce the LR later
6 Versions
Go ahead and upload yours!
