Reproduction2<a target="_blank" rel="ugc" href="https://huggingface.co/Linaqruf/animagine-xl-2.0">https://huggingface.co/Linaqruf/animagine-xl-2.0</a>animagine v2をベースにしましたLinaqrufさんに感謝<hr />SDXL 1.0に追加学習を行い、さらにほかのモデルをマージしました。Additional training was performed on SDXL 1.0 and other models were merged.推奨のネガティブTIはunaestheticXLですThe recommended negative TI is unaestheticXL<a target="_blank" rel="ugc" href="https://civarchive.com/models/119032?modelVersionId=129199">https://civarchive.com/models/119032?modelVersionId=129199</a>v1,sky3.1はアニメ、v31は少しリアル、v13はさらにリアルになると思います。v1,sky3.1 is animation, v31 is a little more realistic, v13 will be even more realistic.

Reproduction | SDXL

今回はただのマージ(blue pencilに自分の学習は入ってると思うけど)

Files with SHA256: fb80e38cc04670c9655d0b3f430b2c9531f2cdbae42150dc55667051ba01db1b