CivArchive
    Preview 17248766
    Preview 17248757
    Preview 17248759
    Preview 5471490
    Preview 5471493
    Preview 5471491
    Preview 5471492
    Preview 5471494
    Preview 5471495
    Preview 5471496

    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: 20

    Image Count: 8

    Network Rank: 32

    Network Alpha: 16

    Batch size: 2

    Clip skip: 1

    Training steps: 1600

    Resolution: 1024x1024

    Model: ponyDiffusionV6XL_v6

    WD14 Captioning

    SmilingWolf/wd-v1-4-convnextv2-tagger-v2

    LoRA Weight: [0.5-0.7]

    FAQ

    Comments (6)

    TroublesomeAJan 14, 2024· 1 reaction
    CivitAI

    Is it possible to make a photorealistic style lora for this model?

    obuyb404
    Author
    Jan 14, 2024· 3 reactions

    I'll give it a try

    obuyb404
    Author
    Jan 16, 2024· 4 reactions

    Done!

    TroublesomeAJan 16, 2024· 1 reaction

    @prgfrg23 Thank you! I'll try it out!

    ppkkmoonJan 15, 2024
    CivitAI

    I want japan artsyle with HD lora for pony model

    obuyb404
    Author
    Jan 15, 2024

    I'm not sure what you mean.

    what japan artsyle is?