CivArchive
    AnimaPulse | Anima - v1.1
    NSFW
    Preview 135653678
    Preview 135654135
    Preview 135658942
    Preview 135655302
    Preview 135656028
    Preview 135656537
    Preview 135658154
    Preview 135660207

    [All AnimaPulse v1.x samples are generated using Diffucore UI. Try it today.]

    AnimaPulse a fine-tune of Anima.

    Fine-tuned with:

    • ~7.5k dataset for v0.1 and v0.2

    • 9.7k images or 19.4k NLP and booru tag dataset for v0.3

    • ~2.5k images or ~5k NLP and booru tag dataset for v0.9

    • ~7k dataset for v1.0

    • ~12.5k images or ~25k NLP and booru tag dataset for v1.1

    Newly Trained Knowledge Information:

    • v1.1: Arknights: Endfield from October 1st 2025 - June 20th 2026

    Recommended settings [Updated for v1.x]:

    • ER SDE or Secant Anneal [Diffucore exclusive]

    • simple or beta_mix [Diffucore exclusive]

    • 30-32 Steps

    • CFG 4.0-4.5

    This model is a fine-tuned (modified) version of the Anima model by CircleStone Labs. The Anima Model is licensed by CircleStone Labs LLC under the CircleStone Non-Commercial License. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

    You may use Outputs (generated images) for commercial purposes, as stated on the CircleStone Non-Commercial License.

    As stated on the license discussion, I am allowed to ask for donations to cover model training expenses. Please donate to my Ko-Fi if you want to support future model training.

    Description

    Added ~12.5k Arknights: Endfield images to the training, with ~25k dataset total (both caption and tags).

    FAQ

    Comments (6)

    sansmiaJul 4, 2026· 3 reactions
    CivitAI

    I like how the dataset seems to have effectively doubled through arknights endfield data. Haha. A little mucking with merging allowed me to bring a lot of this knowledge into my personal favorite models and it seems super stable. This is a solid finetune, friend.

    ThermoticklerJul 8, 2026
    CivitAI

    Will you make a turbo version aswell as more characters? please, this is so good!

    kayfahaarukku
    Author
    Jul 10, 2026

    For a dedicated turbo version, I will probably not make one (I don't like turbo results so far). But, I'll make sure that AnimaPulse checkpoints will be compatible with Anima Turbo LoRA, that can turn any Anima model into a Turbo checkpoint.

    As for more characters, I can't make too much promises, because every Anima training so far is funded by my Indonesian under minimum wage salary (base salary under $200/mo). That's also the reason why the Arknights: Endfield knowledge looked mostly undertrained, because I can't afford more epochs to train.

    Sorry for the slight vent and I hope you're understand my condition right now.

    ThermoticklerJul 11, 2026

    @kayfahaarukku I see, i understand! Great model anyway, thank you very much :)

    just out of curiosity, how much would this cost? just to get an idea

    kayfahaarukku
    Author
    Jul 12, 2026

    @Thermotickler if it's a really large one (like 100k dataset, 50k images with 2 captioning method), probably $100-$120. For comparison, the Arknights: Endfield training cost ~$25 with NLP captioning included.

    anxiousxeonJul 17, 2026
    CivitAI

    waiting for new version hehe

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

    Details

    Downloads
    1,246
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/3/2026
    Updated
    11/11/2026
    Deleted
    -

    Files

    qwen_3_06b_base.safetensors

    Size:
    1.11 GB
    SHA256:
    cd2a512003e2f9f3cd3c32a9c3573f820bb28c940f73c57b1ddaa983d9223eba

    Mirrors

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

    AnimaPulse-1.1-RC-3-newlora.safetensors

    Size:
    3.89 GB
    SHA256:
    9cbf6814fd4f21cb425ca7e1009621411772c50b9527ac7b0b981b2febd71c14

    Mirrors

    CivitAI (1 mirrors)

    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)