V0.2 Important Notes:
Trained with Danboru tags and Natural language, real pain in the ass to manually write/edit but, better prompt adherence.
Bumped to 4000 Steps.
Damn. Where did Misato get that 'fit...
A style LoRA for Anima (by extension its finetunes) by CircleStone Labs.
This LoRA was trained on a curated dataset of 72 screenshot from You Are (Not) Alone and You Can (Not) Advance. All images were treated to remove text, and most symbols, then batch tagged with ConvNextV2 Huge Full and manually tagged for fixing/adding tags.
This Lora is best used at 1 strength, imo. Trigger word is very optional, but hey, its R3BUILD.
Also this was trained on my chef's kiss AMD 7900XT, (under Linux with Ostris's Ai-Toolkit❤️)
Description
Main Settings: 4000Steps, AdamW8bit, 1Batches, [768], LR 4e-5, WeightDecay 1e-2, Rank32, Repeats 3(TAG) and 3(CAPTION), No X Axis Flip
[Trained with both Danbooru Tags and Natural Language. Tags weight 1.4, Caption Weight 0.6]
FAQ
Comments (1)
Roughly when is the release of V1.0 scheduled?