CivArchive
    SilvermoonMix-Anima-Evolved [2.9B/2B] - v2.0
    NSFW
    Preview 134791353
    Preview 134791795
    Preview 134793312
    Preview 134793432
    Preview 134793340
    Preview 134793345
    Preview 134791824
    Preview 134791858
    Preview 134791950
    Preview 134792206
    Preview 134794074
    Preview 134793467
    Preview 134794856
    Preview 134795506
    Preview 134795771
    Preview 134795975
    Preview 134796544
    Preview 134986010
    Preview 134986013

    Anima 2.9B compatibility: Before using the 2.9B versions (including Turbo), update your ComfyUI or Forge Neo installation to the latest version and restart it. Older versions may not load or run the model correctly.

    BF16 / INT8 versions: SilvermoonMix-Anima-Evolved v2.3_2.9B now has an additional INT8 + ConvRot version, quantized from this model's BF16 weights. Choose BF16 or INT8 from the download menu. BF16 retains the original precision, while INT8 reduces file size and VRAM use and may run faster on supported hardware. Image details may differ.

    ComfyUI LoRA compatibility: Legacy Anima 2B LoRAs may need block remapping when used with the 2.9B versions. Community options include:

    Please refer to each project's documentation and choose the solution that suits your workflow.

    Anima 2.9B 兼容性提示：使用 2.9B 版本（含 Turbo）前，请先将所用的 ComfyUI 或 Forge Neo 更新至最新版本，并在更新后重启。旧版本可能无法正确加载或运行模型。

    BF16 / INT8 双版本：SilvermoonMix-Anima-Evolved v2.3_2.9B 现新增 INT8 + ConvRot 量化版，由本模型的 BF16 权重转换而来，可在下载菜单中选择 BF16 或 INT8。BF16 保留原始精度；INT8 体积更小、显存占用更低，在支持的硬件上可能更快，出图细节可能有所差异。

    ComfyUI LoRA 兼容性：在 2.9B 版本上使用旧 Anima 2B LoRA 时，可能需要层号重映射。可参考以下社区方案：

    请自行查阅各项目说明，选择适合自己工作流的方案。

    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

    本模型基于 Anima，采用我的“Evolved”训练策略进行微调。该策略擅长：

    • 稳定的手部表现

    • 中性画风，便于配合画师标签使用

    • 多角色场景

    Anima 的使用说明请参考：https://civarchive.com/models/2458426/anima

    Recommended settings:

    • Sampling method: Euler a / ER SDE (Turbo)

    • CFG: 4 (2B) / 3 (2.9B) / 1 (Turbo)

    • Step: 20-28 / 8-12 (Turbo)

    • 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 / ER SDE (Turbo)

    • CFG: 4 (2B) / 3 (2.9B) / 1 (Turbo)

    • 步数：20-28 / 8-12 (Turbo)

    • 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
    2,454
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/25/2026
    Updated
    9/28/2026
    Deleted
    -

    Files

    silvermoonmixAnimaEvolved_v20_txt.safetensors

    Size:
    1.11 GB
    SHA256:
    cd2a512003e2f9f3cd3c32a9c3573f820bb28c940f73c57b1ddaa983d9223eba

    Mirrors

    HuggingFace (131 mirrors)
    CivitAI (229 mirrors)
    ModelScope (1 mirrors)
    ModelScope CN (2 mirrors)

    silvermoonmixAnimaEvolved_v20.safetensors

    Size:
    3.89 GB
    SHA256:
    4b692bb49ae95fb2d0139d2907cd2252457f42b278f752533a58513cb1a8c9c9

    Mirrors

    HuggingFace (2 mirrors)
    CivitAI (1 mirrors)

    qwen_image_vae.safetensors

    Size:
    242.05 MB
    SHA256:
    a70580f0213e67967ee9c95f05bb400e8fb08307e017a924bf3441223e023d1f

    Mirrors

    HuggingFace (304 mirrors)
    CivitAI (249 mirrors)
    TensorFiles (1 mirrors)
    ModelScope (3 mirrors)
    ModelScope CN (5 mirrors)