(Updated Description for V2 8/10/23)
Always seemed to bug me that the proportions were every so slightly off, so now that I'm a lil' better at this, gave it a another go around,
Trained on SD1.5, so pretty decent compatibility with most realistic models
Setting the Lora to 0.75 should do the trick in most cases, that said if its little too strict especially if your trying to mix loras, I would bring it down to as low as 0.65
if all else refer to the provided lora chart for weight reference
Trigger Word Sayafox should be all you need for this one, due the nature of this dataset I found you can mix and match haircolors and styles pretty well to what you'd want.
Have Fun!