CivArchive
    VisualNote Splash Art DoRA - 2026-03-02 02:14:36
    Preview 1
    Preview 2
    Preview 3
    Preview 4
    Preview 5
    Preview 6
    Preview 7
    Preview 8
    Preview 9
    Preview 10
    Preview 11
    Preview 12
    Preview 13
    Preview 14
    Preview 15
    Preview 16
    Preview 17
    Preview 18
    Preview 19
    Preview 20
    Preview 21
    Preview 22
    Preview 23
    Preview 24

    Description

    prompt example 1: This digital painting features a fierce, scantily-clad female warrior with long blonde hair and green eyes, wielding dual swords. She stands on jagged rocks illuminated by a full moon, casting a dramatic shadow. Her outfit includes a revealing green top and brown pants, accentuating her athletic physique. The background showcases a dark, rocky landscape with a distant figure suspended in the moonlight. The image is detailed with a fantasy theme, showcasing dynamic movement and intense emotion. prompt example 2: A digital fantasy artwork features a cat-eared woman in a medieval setting. She is on all fours, wearing a revealing fur-trimmed outfit, with a chain collar and a knife between her teeth. Her red hair contrasts with the dark, shadowy background filled with glowing eyes of unseen cats. The atmosphere is eerie and intense. prompt example 3: A dynamic, digital fantasy artwork depicts a fierce, bunny-eared warrior in tight, black leather, wielding a glowing, golden sword. She is surrounded by a chaotic, dark, cavernous background, with eerie, shadowy figures and a misty, mystical ambiance. Her white hair flows dramatically, and she strikes a confident pose, exuding power and determination. Training method changes: - Background of images are removed Parameter Settings Network Module DoRA Use Base Model WAI-illustrious - v16 Trigger words - Image Processing Parameters Repeat 12 Epoch 1 Save Every N Epochs 1 Training Parameters Seed - Clip Skip 2 Text Encoder learning rate 1 Unet/DiT learning rate 1 LR Scheduler cosine Optimizer Prodigy Network Dim 64 Network Alpha 32 Gradient Accumulation Steps - Label Parameters Shuffle caption - Keep n tokens - Advanced Parameters Noise offset 0.03 Multires noise discount 0.3 Multires noise iterations 10 conv_dim 64 conv_alpha 32 Batch Size 1 Steps: 3756 Loss: 0.112
    DORA
    Illustrious

    Details

    Downloads
    443
    Platform
    TensorArt
    Platform Status
    Available
    Created
    3/2/2026
    Updated
    3/2/2026
    Deleted
    -

    Files

    b61c4372-7929-489c-a198-bc57eaaf8326.TA_trained.safetensors

    Mirrors

    Other Platforms (TensorArt, SeaArt, etc.) (1 mirrors)