CivArchive
    Anima 2.9B preview v1 convrot quantization - int8convrot
    NSFW
    Preview 140313897
    Preview 140314017
    Preview 140313943
    Preview 140314070
    Preview 140314096
    Preview 140314111
    Preview 140317569
    Preview 140317645
    Preview 140321194
    Preview 140415751

    Convrot quantization of Anima 2.9B preview v1. All credits to @gazingstars321 for creating that model. Anima 2.9B is a diffusion model based on Anima-base_v1 by circlestonelabs and is thereby a derivative of Anima. It's a self-funded finetune, so check out the huggingface page, if you want to support it. It has additional layers and was trained on 1.7M images additional to the dataset of anima base with knowledge cutoff July 2026. Can be used with Forge Neo or ComfyUI with latest versions. Also LoRAs trained with anima-base can be used with this model in Forge Neo, though they may not all be working correct. I made two different quantized versions. The first one is made using svd learned rounding for less rounding errors. The second one keeps more layers in bf16 precision and is therefore slightly larger. The differences between them and the original full bf16 version are usually subtle except for very short prompts. Due to the additional layers Anima 2.9B is slower in inference than Anima-base, though using the int8convrot quantization makes it run at a similar speed.

    recommended quality tags: masterpiece, best quality, highres, absurdres, newest, year 2025
    negative prompt: lowres, bad quality, worst quality, score_1, score_2, score_3, jpeg artifacts, signature, watermark
    Sampler: ER-SDE
    Scheduler: Beta
    Steps: 30-50
    CFG: 3-5

    Showcase images were made with ~1.5k resolution mostly, but I think the model generates slightly better images with 1k resolution. Look at the images directly to get a grasp of what the model is capable of, in the overview the images are scaled to 450px width and are highly compressed, that makes them look blurry.

    Attribution Notice

    “The CircleStone 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.”

    Description

    FAQ

    Comments (2)

    lanceshockerAug 22, 2026· 2 reactions
    CivitAI

    I didn't know that a 2.9 even existed until today. Even though this isn't an "official" anima, it's definitely more versatile and vibrant.

    RisingV
    Author
    Aug 22, 2026

    That's one of the reasons I published this, to give it a bit more attention. I also mentioned it in my latest news article, but maybe I'll write a separate article later. I am quite happy with the results I got there, especially the painting style images came out great, though they look horrible in the model overview.

    Checkpoint
    Anima
    by RisingV
    Download (Beta) View on CivitAI
    anima
    base model
    int8convrot
    convrot
    anima 2.9b

    Details

    Downloads
    403
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/22/2026
    Updated
    11/7/2026
    Deleted
    -

    Files

    qwen_image_vae.safetensors

    Size:
    242.05 MB
    SHA256:
    a70580f0213e67967ee9c95f05bb400e8fb08307e017a924bf3441223e023d1f

    Mirrors

    HuggingFace (353 mirrors)
    CivitAI (301 mirrors)
    TensorFiles (1 mirrors)
    ModelScope (3 mirrors)
    ModelScope CN (7 mirrors)

    Anima-2.9B-preview-v1-INT8_CONVROT-v2.safetensors

    Size:
    3.38 GB
    SHA256:
    082fd0b44deffeecfe1f18f2fc6e0f06b92743554705215152c4a78c5655c961

    Mirrors

    CivitAI (1 mirrors)

    Anima-2.9B-preview-v1-int8convrot-svdlearned.safetensors

    Size:
    2.95 GB
    SHA256:
    9bb0fb1bafa59c678c9baac8603282336b1f9081fc80da22d4d5d66c7e847f66

    Mirrors

    CivitAI (1 mirrors)

    qwen_3_06b_base.safetensors

    Size:
    1.11 GB
    SHA256:
    cd2a512003e2f9f3cd3c32a9c3573f820bb28c940f73c57b1ddaa983d9223eba

    Mirrors

    HuggingFace (145 mirrors)
    CivitAI (267 mirrors)
    ModelScope (1 mirrors)
    ModelScope CN (2 mirrors)