CivArchive
    CinEro XL - PANDORA | LoCon / LoHa - v1.0 S. Hawking (LoCon)
    NSFW
    Preview 2661778
    Preview 2663881
    Preview 2663840
    Preview 2664657
    Preview 2664664
    Preview 2664665

    v.1.1 <== Stable version with "Prodigy" optimizer. You can use any weight without risk to get any kitties died ;)

    This version is just 2nd epoch, but already shows significant effect on picture. Feel free to try and comment.

    PS: "RiP Keith Flint"

    PPS: You can show your appreciation ==> https://www.buymeacoffee.com/zemskov

    v.1.0 <== !!!AcHTUNG!!! Very UNsTabLE experimental Lora. Read Description CaReFuLlY! I am serious!

    Weight <0.195: PANDORA 8==> CAN'T EXPLAIN WHAT IT DOES EXACTLY ¯\_(ツ)_/¯
    Complex improvement of cinematic look, subject separation (depth of field, swirly bokeh, etc), scenery mood (fog, flame/smoke epicness and realism, etc), anatomy (better poses, shyness, face / body expression, etc).

    Weight 0.195...0.21: Wipes out subject, but renders cool scenery with narrow depth of field and lovely creamy bokeh :P

    Weight > 0.21: Explodes planets, stars, galaxies and initiates the spontaneous vacuum collapse at quantum level (GO THAT FAR IN ANOTHER UNIVERSE PLEASE :)

    Description

    Trained with JuggernautXL

    About 60 hrs of training with 932 carefully selected images (cinematic moody nsfw art photos) + few 1000s of regular softcore nsfw photos.

    Tooling: Kohya SS

    Mode: LoCon

    LR: 0.00001

    Precision/Save: bf16

    Resolution: 1024,1024

    Network Rank: 64

    Prior loss weight: 0.4 (importance of regularization imgs)

    Epochs: 6

    (subsequent epochs felled out to NaNs)

    FAQ

    LoCon
    SDXL 1.0

    Details

    Downloads
    203
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/25/2023
    Updated
    5/13/2026
    Deleted
    -

    Files

    cinero-locon-xl.safetensors-000006.safetensors