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 ???
DIM 32 / 16 Alpha
The generated image came out better. But there is more chance of overfitting
Used in conjunction with other LoRAs to reduce the chance of overfitting to some extent.
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.