Modified Anima Yume for LoRA training.
It reduces unintended style changes.
This is not designed for the original model(anima-preview.safetensors). Plaese use Any Anima Preview instead.
Note: This model is NOT suitable for image generation. The model tends to generate ugly images.
LoRA学習用のAnima Yumeです。
意図しない画風の変化を軽減し、精度も改善します。
Dataset information:
Dataset size: 5120
Gelbooruから収集した5120枚の画像で学習しました。
なお、以下のタグがあるか条件を満たす画像は除外しました。
filetype:gif, score:<0, mpixels:<1048576, tagcount:<16, \*_artifacts, adversarial_noise, greyscale, monochrome, digimon, photophop_(meidum), ai-generated, duplicate, bad_\*, off-topic, cropped, resized, reversed, rotated, third-party_edit, screenshot, tagme, real_life, watermark, 3d, koikatsu_(medium), mikumikudance, twitter_username
Description
FAQ
Comments (2)
nice, ill try it
There aren't enough pictures to know if this is good or not, and there's another one with the same name.