CivArchive
    NAILove - NoobAI Real SDXL Merge - v0.1 PhotoReal
    NSFW
    Preview 57765943
    Preview 57765896
    Preview 57765920
    Preview 57766020
    Preview 57766110
    Preview 57766125
    Preview 57766178
    Preview 57766297
    Preview 57766331
    Preview 57766348
    Preview 57766866
    Preview 57766893
    Preview 57766983
    Preview 57767034
    Preview 57767062
    Preview 57767070
    Preview 57767141
    Preview 57767150
    Preview 57767160
    Preview 57768214

    ~ Please upload your creations and give the model a Thumbs Up if you liked it. It means a lot! ~

    All versions have different recipes and flavor. Newer does not mean better!

    A NSFW NoobAI XL Epsilon-pred 1.1 based model that produces photoreal images with much greater flexibility and scene composition prompt adherence than any other photo/real models I tested so far, including realistic pony models.

    v0.3 Contrastes

    Produces "realistic" images.

    Added CyberIllustrious, IllustriousSat-IOR, 1girl printer 2.0, to the mix. Still NoobAI EPS 1.1 based.

    v0.2 SummerBreeze

    Produces "realistic" images.

    Reworked the merging concept and reduced realism by ~20% to improve prompt adherence and image stability.

    v0.1 PhotoReal

    Produces photoreal images.

    It is by no means perfect. As a child of a photoreal SDXL model, it will generate extra hands and bad eyes sometimes. Rarely, it may require ADetailer to fix faces for people in the distance.

    And it is very naughty. :D

    Same with my real Illustrious merge - ILove, I wanted to create a model that understands booru tags, knows (some) concepts provided by the amazing Noob-AI XL and produces photoreal images. In other words, I wanted a NSFW SDXL model that would provide greater adherence to complex prompts from scene composition perspective.

    The complex multistep (~5 steps) MBW Dare & Ties merge included the following models:

    Enormous respect to the models creators.

    Parameters

    For realism: DPM++ (2M, SDE, etc.), Karras, Exponential

    For smoother images: Euler A,

    CFG: 4 - 7

    Prompts

    Keep it simple if possible. Excessive quality tags ruin composition adherence. Only put necessary tags in the Negative prompt.

    I use:

    Positive:

    masterpiece, best quality

    Negative:

    worst quality, bad quality, text, watermark, bad hands, bad eyes, ugly,

    Description

    FAQ

    Comments (7)

    megaderpFeb 14, 2025· 4 reactions
    CivitAI

    Just wow... this beats Yogi_Babes_illu and cyber_illustrious by far. Amazingly realistic!

    wind11
    Author
    Feb 15, 2025

    Thank you!

    kunde2Feb 14, 2025· 4 reactions
    CivitAI

    damn, best realistic noob so far! i am blown away

    wind11
    Author
    Feb 15, 2025

    Thank you!

    dawn66666666Feb 20, 2025· 1 reaction
    CivitAI

    It’s very realistic, but the character concept is basically lost.

    wind11
    Author
    Feb 20, 2025

    Yeah, that's the side effect of going full real. I see what I can do in the next version if I tune down the realism, Would be great if you could share a prompt with a character you'd like to see (better a few prompts and full parameters of how to generate, and/or an actual images), so I could use this for testing my merges. Send me a direct message if you don't want to share here.

    wind11
    Author
    Mar 8, 2025· 2 reactions

    @dawn66666666 , I think the new version made a comeback to the characters knowledge!

    Checkpoint
    Illustrious

    Details

    Downloads
    1,535
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/14/2025
    Updated
    5/7/2026
    Deleted
    -