CivArchive
    Preview 17249984
    Preview 17249986
    Preview 17249974
    Preview 6273443
    Preview 6273445
    Preview 6273444
    Preview 6273448

    Styles are trained on synthetic data and do not copy the styles of artists!

    Photo 2 - is trained on real data (Dataset from Unsplash)

    [M] Merged LoRAs

    Recommended LoRA Strength (Weight): 0.8-1

    Preview generated without using ADetailer & Hires. fix

    Description

    Repeats: 20

    Epoch: 10

    Image Count: 14

    Network Rank: 32

    Network Alpha: 16

    Batch size: 2

    Clip skip: 1

    Training steps: 1400

    Resolution: 1024x1024

    Train Resolution: 1024x1024

    Model: ponyDiffusionV6XL_v6

    WD14 Captioning

    SmilingWolf/wd-v1-4-moat-tagger-v2

    LoRA Weight: [0.8-1]

    FAQ

    Comments (4)

    ppkkmoonFeb 4, 2024
    CivitAI

    Because your loras work very well in my model (Js2Prony), too. Could you also add my model to your lora Suggested Resources ? Many thanks.

    Js2Prony = Japanese artist Style to Porny [Pony Diffusion V6 XL]

    https://civitai.com/models/280321/js2prony

    ppkkmoonFeb 4, 2024· 1 reaction

    Thank you so much ^^

    1423426Feb 4, 2024
    CivitAI

    any chance to get a sd 1.5 version ?

    obuyb404
    Author
    Feb 5, 2024· 5 reactions

    Yes, of course.

    Once I've trained all the styles, I'll post the models.

    LORA
    Pony

    Details

    Downloads
    11,528
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/5/2024
    Updated
    5/14/2026
    Deleted
    -
    Trigger Words:
    concept art, realistic,

    Files

    Available On (2 platforms)

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