(Updated 2/2/2024) (Previews made at 512x768 upscaled w/ ImgtoImg)
Now that I've got even bettererer at making loras, so heres better res one,
Still based on her Zishy Era,
Trained on SD1.5, so pretty good compatibility with most realistic models
Setting the Lora to 0.7 should do the trick in most cases, a good range to stick in is the 1-0.6 range, with the lowest being 0.6
(If all else refer to Weight Sheet for Guidance)
Trigger Word SabLynn should be all you need, but words like red hair, freckles, can also help if some details get lost
Have Fun! :))))
Description
Much stronger training, uses base 1.5 for better general compat.
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.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.