CivArchive
    Cyberfalafel - falafel cyber fix - Cyberfalafel anima v1.0
    NSFW
    Preview 136421646
    Preview 136421650
    Preview 136422284
    Preview 136421648
    Preview 136421647
    Preview 136421644
    Preview 136421649

    ANIMA branch of Cyberfalafel

    The model is new to me.

    Recommended settings:

    Sampler: Euler A CFG++ (STRONG RECOMMENDATION), ER SDE, Euler, DPM++ 2m.

    Schedule: beta, simple, normal, sometimes bong tanget.

    CFG: 0.4-0.7 for CFG++ sampler and 4-5 for all other.

    Steps: 30-50, i prefer 40.

    Generic positive: masterpiece, best quality, score_7, newest,

    Generic negative: (worst quality, low quality, score_1, score_2, score_3:2.0), artist name, blurry, jpeg artifacts, blurry, blurry background, blurry foreground, blurry edges, blurry vision, bokeh, depth of field, green theme, (red theme:2.0), yellow theme, blue theme, worst aesthetic, bad quality, low quality, (bad hands:2), censored, bar censor, mosaic censoring, artistic error, bad proportions, (bad perspective:2.0), wrong hand, bad reflections, too many fingers, too many hands, too many legs, wrong feet, bad feet, extra digits, bad anatomy, ai-generated, lossy-lossless, jpeg artifacts, scan artifacts, @umanosuke, @roncostar, @ke-ta, @smewed, @melkor mancin, ai-assisted, @dikko, skinny, ribs, fog, outline, white outline, hip bones, missing finger, monochrome, greyscale, (simple background, white background:1.3), ring light reflection, (shiny skin:2), (photo background:2.0), @jasony, @ebifurya, (high contrast:2.0), (long torso:2.0),

    V-pred branch of Cyberfalafel

    Completely new model type for me, but it's work and work good.

    Model have medium cfg sensitivity. CFG 4 or 5 is recommended. Recommended vae xlVAEC_f22 or f231. MaHiRo is also recommended if cfg scale on 4-4.5.

    Recommend sampler:

    DPM++ 2m. And you can use DPM ++2M SDE by the way.
    Euler A.
    Euler.
    DDIM.

    Schedule type:

    Beta.
    SGM uniform/normal/simple/uniform.
    Polyexponential.
    Exponential.

    For upscale process i recommend DPM++2 m SDE + SGM uniform. For inpainting DPM++ 2m + SGM uniform with 0.25-0.3 denoise and 20-30 steps (if you use forge neo/reforge/forge classic - use formula: steps*denoise = 20-30. 90 steps work fine).


    Model can handle large tensor resolution (1536x1536), and i can recommend this on general use if you making composition like portrait, full body standing or something wide shot. Thanks to the new predictor, the model handle with this many times better than the EPS one.

    Generic positive: very as2, masterpiece, absurdres, best quality, very awa, very aesthetic, year 2024, newest, ultra-detailed, amazing quality.

    Generic negative: (patreon username, patreon logo, artist logo, twitter username, signature, username, logo, watermark, copyright name, copyright symbol, web address, twitter logo, gumroad username, text, artist name, gumroad logo, artist logo, logo, blurry, blurry background, blurry foreground, blurry edges, blurry vision, bokeh, depth of field:1.2), green theme, red theme, yellow theme, blue theme, worst quality, worst aesthetic, bad quality, low quality, (bad hands:1.2), censored, bar censor, mosaic censoring, artistic error, bad proportions, bad perspective, wrong hand, bad reflections, too many fingers, too many hands, too many legs, wrong feet, bad feet, extra digits, missing fingers,bad anatomy,anime screenshot, anime coloring, abstract, ai-generated, lossy-lossless, jpeg artifacts, scan artifacts,

    ===========================================================

    I made cyberfix for falafel mix by ds27sd

    This checkpoint has the same reason and goals as the original cyberfix, as well as the creation method. Many thanks to the original author.

    Recommended settings: CFG 5, sampler euler A AYS, 28-35 steps.

    Original description

    Original model: https://civarchive.com/models/913998/noobaicyberfix?modelVersionId=1022962

    NoobaiCyberFix

    Purpose of this merge

    The purpose of this model is to fix the anatomy problems of model NoobAI, while keeping 100% of its knowledge and style. NoobAI-Epsilon075 is a great model, it knows almost all characters and styles from Danbooru, but it has some anatomy issues and this merge completely solves this problem. If you use NoobAI-Epsilon075 for SFW purposes, you will hardly notice any difference between this merge and the original model, because the goal was to keep all the knowledge of NoobAI-Epsilon075, and visually this model is almost indistinguishable from NoobAI-Epsilon075. But if you are a man of culture and like Pony models, you will definitely like this one, because this merge gives the model a very good knowledge of anatomy, almost at Pony level

    Recommended negative prompt

    lowres, (worst quality, low quality, bad anatomy, bad hands:1.3), abstract, signature

    Recipe of the merge

    1 Create temporary model

    TempModel = NoobAI-Epsilon075 + cyberrealisticXL_v4 - stable-diffusion-xl-base-1.0

    2 Remove CLIP from TempModel and replace it by CLIP from NoobAI-Epsilon075

    I did this step in ComfyUI.

    Here is the workflow
    https://civarchive.com/models/991574?modelVersionId=1110897

    Logic behind this merge

    cyberrealisticXL_v31 is a general purpose model without any specific style, just like stable-diffusion-xl-base-1.0, and so if you replace the stable-diffusion-xl-base-1.0 weights with cyberrealisticXL_v31 weights in any model, it shouldn't change the model's style and its knowledge much. But at the same time, cyberrealisticXL_v31 has much better anatomy knowledge than sd-xl-1.0, and because of this, it should greatly improve the anatomy knowledge of any model, and in the case of NoobaiCyberFix, it worked exactly as I expected. In theory, you can use this recipe to improve the anatomy knowledge of any model that needs it

    Big thanks to the creators of these models!

    NoobAI

    Illustrious-XL

    cyberrealisticXL_v4

    stable-diffusion-xl-base-1.0

    Description

    A completely different mixing method, a completely new model architecture. It works stably and even coolly. Recommended vae

    My personal settings:
    Euler A CFG ++
    Beta schedule.

    CFG 0.5

    40 steps.

    Pos: masterpiece, best quality, score_7, newest,

    Neg: (worst quality, low quality, score_1, score_2, score_3:2.0), artist name, blurry, jpeg artifacts, blurry, blurry background, blurry foreground, blurry edges, blurry vision, bokeh, depth of field, green theme, (red theme:2.0), yellow theme, blue theme, worst aesthetic, bad quality, low quality, (bad hands:2), censored, bar censor, mosaic censoring, artistic error, bad proportions, (bad perspective:2.0), wrong hand, bad reflections, too many fingers, too many hands, too many legs, wrong feet, bad feet, extra digits, bad anatomy, ai-generated, lossy-lossless, jpeg artifacts, scan artifacts, @umanosuke, @roncostar, @ke-ta, @smewed, @melkor mancin, ai-assisted, @dikko, skinny, ribs, fog, outline, white outline, hip bones, missing finger, monochrome, greyscale, (simple background, white background:1.3), ring light reflection, (shiny skin:2), (photo background:2.0), @jasony, @ebifurya, (high contrast:2.0), (long torso:2.0),

    FAQ

    Comments (3)

    alexvolaJul 12, 2026· 1 reaction
    CivitAI

    I think you cooked again with the Anima version! Love that it doesn't have an aggressive style that supersedes artists tags.

    hfaifyJul 13, 2026· 10 reactions
    CivitAI

    upd: разобрались, претензий не имею, всё ок. качайте, пользуйтесь, но не забывайте про базу

    Knightus_Ai
    Author
    Jul 13, 2026

    Спор решён и всё нормализовано. Пользуйтесь чем хотите.

    Checkpoint
    Anima
    by Knightus_Ai
    Download (Beta) View on CivitAI
    noob
    v-prediction
    model
    anime
    sdxl anime
    checkpoint xl
    eps
    base model

    Details

    Downloads
    301
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/11/2026
    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)

    cyberfalafel anima 1.0.safetensors

    Size:
    3.90 GB
    SHA256:
    0fc7507b222e52ac8cc5e2826786bc4caed05223df32d17aeb05a76cb4de9941

    Mirrors

    CivitAI (1 mirrors)