CivArchive
    Preview 149279709
    Preview 149280361
    Preview 149278878
    Preview 149327727
    Preview 149355333
    Preview 149334260
    Preview 149277801
    Preview 149277882
    Preview 149277945
    Preview 149277162
    Preview 149277879
    Preview 149277904
    Preview 149280913
    Preview 149336125
    Preview 149278701
    Preview 149277153
    Preview 149275785
    Preview 149277955
    Preview 149278481

    krea anime V2

    A well-balanced model that combines flexibility, precision, and a high level of detail; in terms of quality, it’s hot on the heels of Krea 2 Anime UWU v1 + Qwen Image 2.1.

    It is recommended to use the text encoder proposed in 1.7.

    8-12 step

    euler\simple (I haven't tested it on others)

    image resolution 1–1.3–1.5–2-3 MP


    A mix of precisions: although the model file is about 800 MB larger, it actually contains only 1.7 million more parameters than the standard Krea2 Turbo.


    Krea2 anime UWU V2 .safetensors

    Total parameters: 12,821,780,812

    --- Breakdown by format ---

    torch.uint8 format: 16,128 parameters

    Torch.int8 format: 12,155,092,992 parameters

    Format torch.float32: 323,263,052 parameters

    Format torch.bfloat16: 343,408,640 parameters


    Meanwhile, the base Krea 2 Turbo model in BF16 format has the following configuration:

    krea2Turbo_v10_bf16.safetensors

    Total parameters: 12,820,073,036

    --- Breakdown by format ---

    BF16 format: 12,498,501,632 parameters

    F32 format: 321,571,404 parameters

    have fun)

    krea anime 1.7

    The following TE is used for inference

    Qwen3 VL Instruct 4b Heretic 7refusal +convrot (alternate Krea 2 text encoder for ComfyUI) - v1.0 | Krea 2 Text Encoder | Civitai

    It’s also attached to the card, even though the author said it wasn’t necessary to credit them. The encoder is genuinely good.

    As for mine... um... well, it looks like this...

    Yeah, it’s still taken apart, but at least it works.

    krea 2 anime


    The model was trained on a high-quality dataset of over 3,000 images; approximately 350 of these consist of my own drawings and AI-generated images that I edited using drawing software.


    Qween VL annotation + manual corrections


    I consider this model one of the strongest and most powerful I have ever released.

    The download fee is nominal. The hardware required to train the Krea 2 model on a large dataset is expensive; even though I can afford to train it locally—my PC costs around $5,000–$6,000 (and I’m currently upgrading it)—it still places a massive strain on the system. I need the funds to enable generation using this model on Civitai and possibly to purchase some cosmetics on the platform. I have previously released a large number of models completely for free, and I hope you understand my decision in this instance.


    I was really impressed by this model's performance—specifically its speed and flexibility. I had originally planned a large-scale fine-tuning project for Z-Image, but I changed my mind and decided to focus on Krea 2 instead. At the moment, I have a "raw" dataset of 350,000 images (about 20,000 have been processed so far; manual filtering weeds out roughly 60–70% of the material, leaving a final set of around 100,000 images), as well as a high-standard, carefully curated regularization set. Additionally, I plan to compile a supplementary set of about 20,000 images featuring game characters (primarily from HoYoverse titles) if I determine they are underrepresented in the main dataset, given that the base Krea 2 model doesn't recognize them very well—and is unfamiliar with many of them entirely.


    int 8 model

    euller\simple 8 step

    Image resolution 1.0–1.3–1.5 MP

    Description

    compact V2 model from low vram. Good quality at a low weight was achieved thanks to a mix of weights.

    W4A4 (INT4 weight packed int8 containers) 12.82B params · 8.06 GB · ~5.03 bits/param

    From now on, I’ll be packaging Krea2 this way, because the quality is better than standard 4-bit Convrot it’s roughly comparable to Q5–Q6 GGUF, but with a smaller file size.

    I’m being serious here: some creators using Krea2 specifically when working with its INT8 checkpoints end up with lower detail and overall quality than what’s shown here.

    FAQ

    Checkpoint
    Krea 2 Turbo

    Details

    Downloads
    49
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/17/2026
    Updated
    11/18/2026
    Deleted
    -

    Files

    Krea2_anime_cgi_semi-real v2.safetensors