CivArchive
    Hikari Anima - 0.4.1
    NSFW
    Preview 128151840
    Preview 128151941
    Preview 128152239
    Preview 128153273
    Preview 128251896

    Modified Anima to get rid of the quality tags(e.g. "masterpiece, best quality...", "worst quality, low quality...")

    The quality tags are optional, but using certain meta tags and aesthetic tags can make your illustrations more beautiful.

    The base model is Anima Base.

    All the sample images were generated without the quality tags.

    This model does not have the "AI Masterpiece" style.

    This model supports artist tags.

    日本語:

    品質タグを不要にしたAnimaです(例: "masterpiece, best quality...", "worst quality, low quality...")

    品質タグは任意ですが、一部のmetaタグやaestheticタグを使うことで、イラストをより美しくできます。

    このモデルの画風はマージモデルに多い、いわゆる「AIマスピ絵」ではありません。

    Noob版と同様に典型的なAIイラスト感を抑制しつつ美しいイラストを生成します。

    ベースモデルはAnima Baseです。

    すべてのサンプル画像は品質タグなしで生成しました。

    アーティストタグ対応。

    Text Encoderの仕様上、SDXL版のように勝手に美しいイラストを生成することはほとんどありません。足りない部分をDanbooruタグと自然言語(英文)で補うとよいでしょう。

    Steps: 14-32(fast: 14, balanced: 20, quality: 26)

    Sampler: RES Multistep, ER SDE, Gradient Estimation, SA Solver

    Scheduler: Simple, SGM Uniform, Normal, Linear Quadratic(requires >= 26steps)

    Guidance Scale: 2-6(best value is 3.5)

    Flow Shift(ModelSamplingAuraFlow): 2-4(best value is 2.5)

    Tips: The amount of image error and detail is inversely proportional to the Flow Shift value.

    VAE: Default(Qwen Image VAE) or Wan 2.1 VAE

    Incompatible schedulers: Karras, Exponential, KL Optimal

    Requirements

    ComfyUI

    VAE and Text Encoder not included. Please download it from here

    Note/注意

    • version 0.1.0 does not support sd-scripts and diffusion-pipe.

    • version 0.1.0はsd-scriptsとdiffusion-pipeは非対応です。

    Notice

    This model provided "as is", without warranty of any kind.

    This model is not designed for inpainting.

    このモデルは「現状のまま」提供され、一切の保証はありません。

    このモデルはinpainting用ではありません。

    Description

    Higher aesthetic score?

    The base model is Anima Yume 0.4

    FAQ

    Comments (3)

    eptarch796Apr 28, 2026· 15 reactions
    CivitAI

    That's the first time I comment on any model, but that's only because I just broke my personal record with this one, totalling 9 fingers per hand.

    soralzMay 4, 2026
    CivitAI

    This model does not add weird artifacts like extra “buttons, pockets, cuffs” etc… to my display model like other finetunes, and the color is more vivid, brighter and preserve my original training image details. Recommended as showcase.

    hushichoMay 18, 2026· 1 reaction
    CivitAI

    Very beautiful results. Still tends to do the "anime face" that has different coloring to the rest of the piece, so hopefully that can be fixed in future.

    Checkpoint
    Anima

    Details

    Downloads
    834
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/21/2026
    Updated
    8/11/2026
    Deleted
    -

    Files

    hikariAnima_041.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)
    TensorArt (1 mirrors)
    TensorHub (1 mirrors)