CivArchive
    Preview 17250059Preview 17250063Preview 17250062Preview 17250064Preview 6380494Preview 6380492Preview 6380496Preview 6380493

    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: 12

    Network Rank: 32

    Network Alpha: 16

    Batch size: 2

    Clip skip: 1

    Training steps: 2400

    Resolution: 576x832

    Train Resolution: 1024x1024

    Model: ponyDiffusionV6XL_v6

    WD14 Captioning

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

    LoRA Weight: [0.7-0.8]