Trigger words: hitozato
optional words: wall, temple, landscape, ...
V1: Trained on 113 images.
V3: Trained on 162 images. V3 makes cleaner images but is harder to get stores and other buildings outside of temples and houses.
I tried to make it similar to hitozato [human village] (人里) from touhou. Most of the data was shots of the village and roads.
I take my time decensoring, cropping, cleaning up my dataset to make my Loras.
I have a discord server (https://discord.gg/AmdETXDfHs) where you can have AI and off-topic discussions, ask for help, and having fun (gaming, playing with AI, etc).
I'll appreciate it if you support me on Patreon. I plan on sharing early access to my models and releasing more based on my milestones on Patreon. You can also support me on Kofi.
Best place to DM me is via Twitter: twitter.com/CatNatsuhi928