This was my first attempt at training a LoRa. It produces a more consistent handwriting style across images and prompts. It can produce individual letters and common words pretty well but is not great at longer text, uncommon symbols, etc.
Example prompts:
Woman holding piece of paper with handwritten text 'Hello'
I'd suggest starting with strength 0.5 and increasing from there. I found a range of 0.4-0.7 works well when pairing with JuggernautXL as base.
Constructive feedback is very welcome!