The training data consisted of VN CGs with a focus on the romance/high school genre. I tried to pick CGs with similar aesthetic types or coloring styles.
Recommendations:
Works well with anime checkpoints that produce clear outlines
Background tags that can be used:
indoors, outdoors, day, night, evening, backlighting
v0.1 and v0.2 have drastically different styles
In my opinion v0.1 captures the VN style better.
While v0.2 is a bit more generic in style, it can produce better eyes and more vibrant colors
I've found that v0.2 still has a few tagging errors related to background tags.
Description
Double the amount of training data
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.