CivArchive
    Hassaku (Anima) - v0.1
    NSFW
    Preview 131434118
    Preview 131431468
    Preview 131436900
    Preview 131436491
    Preview 131427835
    Preview 131431154
    Preview 131432097
    Preview 131432096
    Preview 131433642
    Preview 131431744
    Preview 131434957
    Preview 131427604
    Preview 131429806
    Preview 131432310
    Preview 131426654
    Preview 131435822

    Hassaku Anima

    Join my Discord for everything related to anime models and AI art.
    If you’d like to support my work, you can do so on SubscribeStar
    Every bit helps me continue making AI models and even an AI VTuber, which is currently in the works.

    How to Use

    You need to use ComfyUI or Forge Neo.
    20-50 steps, CFG 3-6, (i like to use 25 stepts with cfg of 3.5 and er-sde as sampler).
    - Put @ in front of artist tags
    - Use lowercase for tags and spaces instead of underscores.
    - Recommended positive: "masterpiece, best quality, score_7", but since masterpiece is altered, in some cases masterpiece is enough
    - Recommended negative: worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts"
    - When using a tag that is different between Danbooru and Gelbooru, prefer the Gelbooru version.

    Supporters

    Special thanks to my supporters:
    Estryark, SETI, Kodokuna and dataset captioners mariotheknight and tamashiicolle

    Here are some resolution suggestions for Anima:

    • 1536 × 640

    • 1344 × 768

    • 1216 × 832

    • 1152 × 896

    • 1024 × 1024

    • 896 × 1152

    • 832 × 1216 — most recommended

    • 768 × 1344

    • 640 × 1536

    Larger resolutions are possible.
    Note: It is a Diffusion Transformer (DiT) model, it is less restrictive on sizes in compare to a Unet like Illustrious, you can use bigger resolutions.

    Version and License Info

    V0.1:
    A small-scale style training test, intended to see how adaptive Anima is.

    V1:
    Test for character training with nte characters and femme soule (pukey goddess shot trick). Better use of the style training set.

    V1 Style:
    Focus on a consistend style. Revert training of nte characters and femme soule (pukey goddess shot trick), because of forgetting issues of anima itself.

    License: Anima

    Description

    A small scale style finetune of anima, it was initially not meant to be released and was only a internal test. The training worked better than expected. I like the result so that I decided to release it. The model received style-set training focused on the tag "masterpiece".

    Only about 1/4 of the dataset included NL, using a mix of tags and natural language. Thanks to @mariotheknight and @tamashiicolle for helping me in captioning the datasets! Those sets was originally intended for KLEIN fine-tuning, but that experiment ended up failing over the course of 3months.

    The fine-tune target is Anima Base v1.0.
    Since this is not a style LoRA merge, but a model natively trained with a style, tags like traditional media, watercolor or @artist styles should still work normally without change.

    Test Notes for V0.1
    The learning rate was too high, so around 1 in 10 images may show more noticeable limb issues or color bleeding. However, the overall base style in use with masterpiece looks better and closer to models like Illustrious, which was the intended direction.

    Disclaimer: Since this is not a forced LoRA-style merge, the style will vary, especially when generating characters.

    FAQ

    Comments (17)

    AihsjsjsiahsvsjsMay 22, 2026
    CivitAI

    Why can't these people use any lora for the images this style is sucks

    Ikena
    Author
    May 22, 2026

    You can still use artist tags or loras

    AihsjsjsiahsvsjsMay 22, 2026

    @Ikena I'm not asking for that

    hushichoMay 22, 2026

    Because it's misleading if you use a LoRA to try and convey what the base style of a model is. This style isn't "sucks", in your poor use of english. Though judging by your username, you're either a troll or a bot just griefing people.

    hushichoMay 22, 2026· 6 reactions
    CivitAI

    We have been blessed! One of the most solid Anima checkpoints available, of course.

    Tozi_WhiteMay 22, 2026· 4 reactions
    CivitAI

    Based at Anima 1.0 or...?

    Ikena
    Author
    May 22, 2026· 1 reaction

    Based of anima V1, you can look at "About this version" for more info

    TOF_enjoyerMay 22, 2026
    CivitAI

    is that a modified qwen_3_06b text encoder or the same one just you changed the file name?

    Ikena
    Author
    May 22, 2026· 1 reaction

    It is the same txt encoder from https://civitai.red/models/2458426/anima?modelVersionId=2945208, it gets renamed, if you download it from there. I don't train the TE (llm_adapter_lr 0)

    TOF_enjoyerMay 22, 2026· 1 reaction

    @Ikena I see, thanks for the fast reply.

    shidaioaMay 23, 2026· 7 reactions
    CivitAI

    Damn, you are quick to build on this! Anima is really great, it's just that it knows too few poses. Already imagining what its future ecosystem will look like.

    mdalfthedudeMay 24, 2026· 1 reaction
    CivitAI

    Cool Checkpoint, man. This works well for me.

    mdalfthedudeMay 24, 2026· 2 reactions
    CivitAI

    Which scheduler do you recommend with this btw?

    Ikena
    Author
    May 24, 2026

    I recommended the sampler er-sde, but simply use the one you like the most. There is no rule to stick on exacly one

    mdalfthedudeMay 24, 2026· 1 reaction

    @Ikena Yeah, I tried all of the ones on forge neo, got stuck between beta and sgm uniform.

    EquoJun 13, 2026

    Beta is generally the most reliable scheduler.

    revealerMay 27, 2026· 2 reactions
    CivitAI

    sibal my favorite model

    Checkpoint
    Anima
    by Ikena
    Download (Beta) View on CivitAI
    illustration
    art
    base model
    anime

    Details

    Downloads
    3,962
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/22/2026
    Updated
    11/11/2026
    Deleted
    -

    Files

    qwen_image_vae.safetensors

    Size:
    242.05 MB
    SHA256:
    a70580f0213e67967ee9c95f05bb400e8fb08307e017a924bf3441223e023d1f

    Mirrors

    HuggingFace (363 mirrors)
    CivitAI (310 mirrors)
    TensorFiles (1 mirrors)
    ModelScope (3 mirrors)
    ModelScope CN (7 mirrors)

    animaTrain.safetensors

    Size:
    3.89 GB
    SHA256:
    4d2f4978c7823493be13cd10af0d18ebc1535540ae3117fa2c818154b927f20e

    Mirrors

    HuggingFace (2 mirrors)
    CivitAI (1 mirrors)

    anima_baseV10_txt.safetensors

    Size:
    1.11 GB
    SHA256:
    cd2a512003e2f9f3cd3c32a9c3573f820bb28c940f73c57b1ddaa983d9223eba

    Mirrors

    HuggingFace (145 mirrors)
    CivitAI (275 mirrors)
    ModelScope (1 mirrors)
    ModelScope CN (2 mirrors)