CivArchive
    Luna_Flex_zimage - v1.0
    NSFW
    Preview 140923210
    Preview 140923208
    Preview 140923209
    Preview 140923213
    Preview 140923212
    Preview 140923247
    Preview 140923277
    Preview 140923311
    Preview 140923357
    Preview 140923497

    Training Settings

    Steps

    Each image seen ~2×

    2000

    Checkpoints

    10

    Advanced Settings

    Sample Media Prompts

    3/3 ready

    Training Parameters

    Click the info icon next to each setting for more information.

    Default settings are based on your chosen model. Altering these settings may cause undesirable results.

    Editing advanced parameters forfeits your refund

    These defaults are tuned for your selected model. If you change them and the result is poor, the training is non-refundable. Steps and Checkpoints above are not affected.

    I understand and want to edit the advanced parameters

    Train Batch Size

    1

    Resolution

    1024

    LoRA Type

    lora

    Enable Bucket

    Shuffle Tags

    Keep Tokens

    0

    Clip Skip

    1

    Flip Augmentation

    Unet LR

    0.0001

    Text Encoder LR

    0

    LR Scheduler

    constant

    LR Scheduler Cycles

    3

    Min SNR Gamma

    0

    Network Dim

    32

    Network Alpha

    32

    Noise Offset

    0

    Optimizer

    AdamW8Bit

    Description

    LORA
    ZImageTurbo

    Details

    Downloads
    31
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/26/2026
    Updated
    9/8/2026
    Deleted
    -

    Files

    Luna_Flex_zimage.safetensors

    Mirrors

    CivitAI (1 mirrors)