CivArchive
    Preview 94444505
    Preview 94444525
    Preview 94444577
    Preview 94444608
    Preview 94444632
    Preview 94444640

    based on NoobAI Epsiron Pred v1.1,

    (semi) realistic model.

    Esotericism of NoobAI

    illustrious' LoRA also works.

    recommend setting.


    prompt:

    *** MUST CHANGE THIS LINE *** character name, costume, situation, pose, and so on..., BREAK

    (realistic:1.5), masterpiece, best quality, reference photo, photorealistic, cosplay photo, highres, very awa, photo background, detailed face, detailed background,

    negative prompt:

    lowres, (worst quality:1.3), bad quality, normal quality, bad anatomy, illustration, anime, (3d:1.5), game, cg, oekaki, figure, BREAK

    watermark, signature, logo, artist name, text, username, stamp, date, footer, header, title, subtitle, body writing, censored,

    sampler: Euler A

    steps: 40 or higher(may be 28)


    I created LoRA using images from FLUX. and merge their to original NoobAI model.

    And I merge some models, but I lost memo... because my machine is often crashed.

    The merge with LoRA was done using a modified version of a1111

    -> https://github.com/frsk9999/sdwebui_savetensors_aftercreateimg

    I think you can probably do the same thing using comfyui.

    additional of prompt:

    • (realistic:1.5) for realistic image.

    • realistic for semireal or 3d. to create character.

    LICENSE is following Original NoobAI.


    ここからは日本語です。

    このモデルは個人が趣味で作ってるものなので商用不可でお願いします。

    もう(今の環境下では)モデルなんて作らないと決めていたのに何の因果か作りました。

    プロンプトの設定などは英語部分を参照してください。

    キャラクタの画像作成時に(realisitc:1.5)部分をrealisticにするとセミリアルというか3Dっぽく出ます。

    マージするためにNoobAI用のLoRAを作成したのですが、1つにつき1~2週間、3つで1か月半程度かかるのです(GTX1070だから)。今は時期が悪いので新調もできないし…。

    VRAM8GBだとUnetのみでDim32(Lycoris)が限界でした…もっとVRAM欲しい(時期が悪い)。

    SDXLのマージを通して得た知見としてはこの辺り

    IN08には塗りが入っていて、OUT01は絵側に戻す補正がかかる(ので、やり過ぎた場合に出るノイズを軽減してくれる)、OUT02はリアル寄りにするらしい。

    意外とTE部分を入れ替えるだけで出力ががっつり変わったりする。

    あとはふいんき(なぜか変換できない)でやりました。

    Description

    • The probability of generating the correct costume has increased slightly.

    • Challenging for more realistic expression

    • The environment is the same as v1.03.

    FAQ

    Comments (3)

    SinonkaZlp1Aug 25, 2025
    CivitAI

    Cute Tailred.
    Does this model support Tailred, or is a LoRA needed? Or is it your own custom Tailred LoRA?
    If it’s your own LoRA, please consider uploading it – I’m very interested.

    This model really caught my attention because of Tailred.
    Every week I search for mentions of Tailred, and your model won this “lottery” ^^
    Now I truly appreciate your model.

    fcski
    Author
    Aug 25, 2025
    Thank you for using my model. LoRA is not required. As for characters, if they can be produced with Noobai, they should be able to be produced to a certain extent. Specifically, you can produce them by using the tag "tailred, ore twintail ni narimasu, 1girl, red eyes, purple eyes, hair between eyes, red hair, gradient hair, very long hair, antenna hair, blonde hair, long hair, twintails, flat chest, covered navel, leotard, leotard, elbow gloves, bare shoulders, magical girl, magical girl, headgear". Alternatively, if you're using a WebUI such as A1111, try downloading the image and loading it from the "PNG Info" tab. For characters whose details cannot be output using only the model, please consider using LoRA. Illustrious or Noobai's LoRA should generally work.

    SinonkaZlp1Aug 27, 2025

    @fcski thx info im have all models tailred and owned and this by now deleted in civitai

    Checkpoint
    NoobAI

    Details

    Downloads
    101
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/15/2025
    Updated
    6/11/2026
    Deleted
    -
    Trigger Words:
    realistic

    Files

    eon_v104.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.