CivArchive
    Preview 21813805
    Preview 21813779
    Preview 21813771
    Preview 21813795
    Preview 21813750
    Preview 21813754
    Preview 21813753
    Preview 21813810
    Preview 21813813
    Preview 21813757
    Preview 21813769
    Preview 21813748
    Preview 21813747
    Preview 21813749
    Preview 21813751
    Preview 21813758
    Preview 21813761
    Preview 21813770
    Preview 21813776

    You can also use this model at;

    https://tensor.art/models/1036496771968201923

    https://www.seaart.ai/models/detail/da69mvle878c73efco70

    NON CANON SAMPLE ARE HERE;

    https://civarchive.com/posts/30596668

    Historical log of the model:

    V-Final - Anima ver. Its to commemorate EOS. Trained under 1536 for Anima BASE 1.0

    V4 - IllustriousXL V2 model - Literally had the knowledge of everything previously had, reminiscence of AnimagineXL v1.5 in consistency, while being all the versatility and everything else that previous version had due to further in-training designated for ILXL v2.

    V3.5EX-RevB - IllustriousXL 1.1 final model - Literally had the knowledge of everything previously had, with far superior consistency.

    V3.5EX - IllustriousXL 1.1 experimental model. - Had the knowledge of Black Rose clone outfit.

    V3 - Illustrious XL and AnimagineXL 4 - Huge versatility, very consistent artstyle. (increased consistency, trained on higher resolution images to follow-up with ILXL 1.0)

    V2 FLUX - Upgraded flux version. Removed v1 due to its lower tier nature.

    V1.5 - Illustrious XL - Huge versatility, very consistent artstyle. (slightly stabilizing the colors.)

    V1 - Illustrious XL - Huge versatility, very consistent artstyle.

    V2.3 - Animagine XL 3.1 - Huge versatility (Up to animagineXL3.1 limit), very consistent artstyle.
    V1 FLUX - Testing ground. FLUX is a non-NSFW model.
    V2.2 - Animagine XL 3.1 - Good versatility, consistent artstyle.
    V1 Pony - Huge versatility, inconsistent art.
    V2 ALT - Animagine XL 3.1 - BAD versatility, consistent artstyle.
    v1.5 ALT - Removed, too much weakness.
    V1.5 Animagine XL 3 - Inconsistent artstyle, good versatility.
    V1 Animagine XL 3 - Removed due to so much weakness.

    Recommended setting is 30 step, 5 CFG, euler a. For either Anima or ILXL or AnimagineXL/Pony. All of them share same exact configuration with some additional data slightly after v3.

    Use strength between 0.7 to 1.

    Preview are generated using Raehoshi Anima. Upscaled using 4xRemacri.

    Description

    v1 Experimental. Example of tagging is on sample picture. Uses same exact tagging for animagine XL version, it has slightly more images trained compared to the old version. Maybe its overcooked, but some poses do have limitation. I never did pony, but yea, this is a good experience, I guess.

    Someone from pixiv requested this.

    FAQ

    LORA
    Pony

    Details

    Downloads
    389
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/29/2024
    Updated
    8/25/2026
    Deleted
    -
    Trigger Words:
    shin jia
    oridress
    normalform
    annivdress
    cowgirlbikini
    racequeen
    long hair, brown hair, blue eyes
    purple eyes
    large breasts