CivArchive
    Preview 17249646
    Preview 17249642
    Preview 17249643
    Preview 6162157
    Preview 6162160
    Preview 6162156
    Preview 6162159
    Preview 6162163
    Preview 6163336
    Preview 6163337

    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: 12

    Image Count: 10

    Network Rank: 32

    Network Alpha: 16

    Batch size: 2

    Clip skip: 1

    Training steps: 1200

    Resolution: 768x768

    Train Resolution: 1024x1024

    Model: ponyDiffusionV6XL_v6

    WD14 Captioning

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

    LoRA Weight: [0.8-1]

    FAQ