CivArchive
    AnyAnimagine-XL(for LoRA Training) - 4.0
    Preview 54362970
    Preview 54363586

    Modified Animagine-XL for LoRA training.

    It reduces unintended style changes and improves quality.

    If you make a LoRA with this checkpoint, do not use "--noise_offset"!

    This is not suitable for image generation!

    LoRA学習用のAnimagine-XLです。

    意図しない画風の変化を軽減し品質を改善ます。

    これでLoRAを作る場合、「--noise_offset」は使用しないように!

    画像生成は適していません。

    Training information:

    Finetuned Animagine-XL by repeating the training and merging a DoRA 2 times with sd-scripts.

    sd-scriptsで二回DoRAの学習とマージを繰り返すことでファインチューンされました。

    Style training has not been tested, but some users reported that it can be learned successfully.

    画風学習は未確認ですが、問題なく学習できるという報告があります。

    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, mikumikudance, twitter_username

    Training script(source code)

    sd-scripts( https://github.com/kohya-ss/sd-scripts )

    Description

    Base model is Animagine-XL-4.0

    Original filename is AnyAnimagine-XL-4.0.safetensors

    FAQ

    Checkpoint
    SDXL 1.0

    Details

    Downloads
    290
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/28/2025
    Updated
    4/30/2026
    Deleted
    -

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.