CivArchive
    Kreanima - v2.0
    NSFW
    Preview 145936039
    Preview 145936040
    Preview 145936046
    Preview 145936044
    Preview 145936050
    Preview 145936052
    Preview 145936061
    Preview 145936059
    Preview 145936087
    Preview 145936079
    Preview 145936093
    Preview 145936095
    Preview 145936101
    Preview 145936107
    Preview 145936110
    Preview 145936112
    Preview 145936115
    Preview 145936116
    Preview 145936122
    Preview 145936123

    V2 Update

    This version has been redone from scratch using the original Turbo, μKrea2 β LoRA and the Vanilla version of Lianima 4 Krea. It is should work better even if some measure of glitch still happens! Now, back to ANIMA 💜

    V2.0 is available as:

    • INT8 Convrot (safetensors)

    • Q8_0 (GGUF)

    • FP8 Scaled (safetensors)

    Each file is ~14GB and took me ~4h to upload (and any failure can kill the upload). I will not upload the BF16 version: this would take me 9h to do if nothing happens during the upload.

    If none of the version above is working for you, it is also available as a LoRA you can use on top of the good old Krea2 Turbo or you can unquantize either of those version above to get a BF16 version that would be version close to the original.

    V1

    This is a bit of a broken merge of Krea2, based on my own LoRA, provided as-is, published here only to link my own local experiments with Krea2.

    TL; DR: Use at your own risk 😅 (mainly sanity and time are what you could lose🤣).

    It works with stable-diffusion.cpp and should work with other tools that accept GGUF files.

    Recipe

    It is leveraging a mix of DMerge (marked as allowing merge at time of integration) and the Vanilla version of Krea2 Turbo plus a 50/50 mix of the uncensored and vanilla version of Lianima 4 Krea, at 0.8.

    Due to the inclusion of uncensoring stuff and my own OC, the result is a highly unruly, very NSFW, woman focused, anime version of Krea2 in my own style 😘

    No trigger word needed, use as you would use Turbo (CFG ~1, Steps ~8)

    • LoRA merge was done painfully manually until i can find a way to do it faster/easier with sd-mecha (unlike ANIMA, i can't hold the whole BF16/FP16 version in memory).

    • Quantization was done thanks to the new "stream layers" feature of sd.cpp:

    sd-cli.exe -M convert -m kreanima_fp16.safetensors -o kreanima_Q5_0.gguf --type q5_0 --stream-layers --max-vram -1 --offload-to-cpu

    PS: It took 9 hours but i have also uploaded the FP16 version. I will not provide any other variant.

    Thanks for reading! 💜

    For reference, prompt for the picture at the top:

    [character description]
    1girl, Liadora, red hair, green eyes, black oni horns, black dress, purple elbow gloves, upper body, shy smile
    [scene description]
    Liadora is on the left side of the screen, holding a board with "Kreanima" written on it, showing to the viewer. Abstract background, geometric patterns, neon colors.

    Description

    Posted on Civitai, upload found elsewhere are FORBIDDEN and done without the author permission.

    FAQ

    Checkpoint
    Krea 2

    Details

    Downloads
    300
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/17/2026
    Updated
    10/23/2026
    Deleted
    -

    Files

    kreanima_v20_int8.safetensors

    Mirrors

    kreanima_v20.gguf

    Mirrors

    CivitAI (1 mirrors)

    kreanima_v20_fp8.safetensors

    Mirrors

    CivitAI (1 mirrors)