CivArchive
    SilvermoonMix-Anima-Evolved - v2.0
    NSFW
    Preview 134791353
    Preview 134791795
    Preview 134793312
    Preview 134793340
    Preview 134793345
    Preview 134791824
    Preview 134791950
    Preview 134792206
    Preview 134795506

    Fine-tuned on Anima with my "Evolved" training strategy. This strategy is good at:

    • Stable hands

    • Neutral art style to work with artist tags

    • Multiple characters

    For instruction of using Anima, please refer to: https://civarchive.com/models/2458426/anima

    Recommended settings:

    • Sampling method: Euler a

    • CFG: 4-5

    • Start with no negative prompt. Sample images were generated without negative prompt.

    • Prefix artist with @. E.g. "@big chungus". You must put @ in front of the artist. The effect will be very weak if you don't

    Sample images were created with Forge Neo (https://github.com/Haoming02/sd-webui-forge-classic/tree/neo), featuring native Anima support. Right-click and open any sample image in a new tab to download the original file with its generation metadata.

    推荐设置：

    • 采样方法：Euler a

    • CFG: 4-5

    • 先尝试不使用负面提示词。示例图片都没有使用负面提示词。

    • 在画师（或艺术家）名字前加上 @ 前缀。例如：“@big chungus”。你必须在画师名字前面加上 @，如果不这么做，效果会非常微弱。

    示例图片由原生支持 Anima 的 Forge Neo (https://github.com/Haoming02/sd-webui-forge-classic/tree/neo) 生成。右键并在新标签页中打开任意示例图片，即可下载带有生成参数的原图。

    Description

    v1.0 -> v2.0:

    • Improved accuracy of fine details.

    • Improved background logic and details

    • Increased overall image sharpness and clarity.

    FAQ

    Comments (9)

    HaloSkullJun 25, 2026· 8 reactions
    CivitAI

    Your preview images all seem to have no space after each comma and Anima is pretty picky in wanting correct tagging. It supposed to have a space after each comma ", " not ",". So if you were having some trouble with prompt adherence that may be why.

    silvermoong
    Author
    Jun 25, 2026· 1 reaction

    Oh, I didn't know that. I will give it a try.

    kryd0rJun 25, 2026

    Not completely sure if it's not just placebo yet, but this seems to be correct. Thanks man.

    deitychaserJun 25, 2026

    @silvermoong hope you didnt caption your dataset that way.

    silvermoong
    Author
    Jun 26, 2026· 1 reaction

    @deitychaser No, datasets are fine. It's an issue of my tag generator.

    NomadSterbenJun 26, 2026· 2 reactions
    CivitAI

    I like the results; I think they're better than the previous version, but the Adetailer in Neo Forge tends to fail more compared to other models.

    silvermoong
    Author
    Jun 26, 2026· 2 reactions

    @NomadSterben Face getting messed up after using Adetailer? Now I stick to denoise strength = 0.15.

    Hisa_eromikoJul 6, 2026· 4 reactions
    CivitAI

    银月佬，爱你的微调模型。我发现这个模型在一众微调里默认风格是最中立的，这十分利于我在捏原创角色的时候尽量减少已有IP的影响

    justaguy111Jul 8, 2026
    CivitAI

    I'm looking forward to see the future of this model. Right now I feel it's not as flexible as the Illustrious model, it sometimes looks more "shiny" and generic. But for styles it knows well, it's great at them

    Checkpoint
    Anima
    by silvermoong
    Download (Beta) View on CivitAI
    base model

    Details

    Downloads
    2,355
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/25/2026
    Updated
    8/13/2026
    Deleted
    -

    Files

    silvermoonmixAnima_v20.safetensors

    Size:
    3.89 GB
    SHA256:
    4b692bb49ae95fb2d0139d2907cd2252457f42b278f752533a58513cb1a8c9c9

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    qwen_image_vae.safetensors

    Size:
    242.05 MB
    SHA256:
    a70580f0213e67967ee9c95f05bb400e8fb08307e017a924bf3441223e023d1f

    Mirrors

    HuggingFace (220 mirrors)
    CivitAI (166 mirrors)
    TensorFiles (1 mirrors)
    ModelScope (3 mirrors)
    ModelScope CN (5 mirrors)

    silvermoonmixAnima_v20_txt.safetensors

    Size:
    1.11 GB
    SHA256:
    cd2a512003e2f9f3cd3c32a9c3573f820bb28c940f73c57b1ddaa983d9223eba

    Mirrors

    HuggingFace (103 mirrors)
    CivitAI (151 mirrors)
    ModelScope (1 mirrors)
    ModelScope CN (2 mirrors)