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!
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
