CivArchive
    LunaR - v1.0.1
    NSFW
    Preview 130117014
    Preview 130117013
    Preview 130117017
    Preview 130117019
    Preview 130117021
    Preview 130117022
    Preview 130117023
    Preview 130117024
    Preview 130117025
    Preview 130117027
    Preview 130117029
    Preview 130117030
    Preview 130117033
    Preview 130117034
    Preview 130117035
    Preview 130117037
    Preview 130117041
    Preview 130117040
    Preview 130117044
    Preview 130117047

    LunaR is a specialized LoRA designed to enhance [mention the style, e.g., feminine features / cinematic lighting / specific character details]. It focuses on delivering high-quality textures and consistent results for [mention the subject, e.g., portrait photography / stylized characters].

    Key Features:

    • Style: [e.g., Realistic, Semirealistic, Stylized]

    • Best used for: [e.g., Close-up portraits, dramatic lighting, fashion shots]

    • Trigger Word: LunaR

    Usage Tips

    • Recommended Weight: 0.6 - 0.8 (Adjust based on your checkpoint)

    • Sampling Method: [e.g., Euler a, DPM++ 2M Karras]

    • CFG Scale: 5 - 7

    • Base Model: Recommended for use with [mention your base model, e.g., Pony Diffusion V6 / SDXL 1.0].

    Notes

    • What it’s good at: [e.g., Capturing intricate skin details and soft lighting.]

    • What to avoid: [e.g., Not intended for complex landscapes or heavy architectural work.]

    If you enjoy using this model, please consider leaving a review and sharing your generations! Your feedback helps me improve future iterations.

    Description

    Version changes or notes

    Initial release of the LunaR LoRA. This model is fine-tuned to generate high-quality, photorealistic portraits with a signature vibrant pink and yellow ombre hair style. It handles both soft, natural indoor lighting and dramatic, cinematic night scenes with excellent skin texture and facial consistency.

    Trigger Words

    LunaR (Note: If you trained it with specific tags for the hair or glasses, you can add multicolored hair, round glasses as well, but LunaR is your main one.)

    Recommended Settings

    • Clip Skip: 2

    • Min Strength: 0.5

    • Max Strength: 1.0

    • Strength (Default): 0.8

    Training Parameters

    If you remember your training data, you can fill these in, but they are optional:

    • Epochs (Korszakok): 10 (standard guess)

    • Steps (Lépések): 2000 (standard guess)

    Quick Tip: Once you fill these out and click Next (Következő), you will be able to upload your .safetensors file and then the showcase images we wrote the prompts for earlier!

    LORA
    ZImageTurbo
    by 7p3kai
    Download (Beta) View on CivitAI
    character
    beauty
    women
    gen
    noob
    pic

    Details

    Downloads
    49
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/9/2026
    Updated
    5/13/2026
    Deleted
    -
    Trigger Words:
    LunaR

    Files

    image_z_image_turbo (1) (1) (1).json

    Size:
    6.06 KB
    SHA256:
    e6b2c3b43d24adfa80077366422b34e4277d93dbc8199ee358cf39a110c9556a

    Mirrors

    CivitAI (12 mirrors)

    clip_l (1) (3).safetensors

    Size:
    234.74 MB
    SHA256:
    660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd

    Mirrors

    HuggingFace (1770 mirrors)
    CivitAI (23 mirrors)
    TensorFiles (1 mirrors)
    CivitasBay (1 mirrors)
    ModelScope (3 mirrors)
    ModelScope CN (5 mirrors)

    decoder (1).pt

    Size:
    2.32 GB
    SHA256:
    c9cebd3132dd9c42936d803e33424145a748843c8f716c0814838bdc8a2fe7cb

    Mirrors

    HuggingFace (2 mirrors)
    CivitAI (18 mirrors)

    TCTR18QW73ACEKD4Z97SXSE490.safetensors

    Size:
    217.88 MB
    SHA256:
    0792d6e140392c63d1db12ddfa137ae08ada8d810a719bfa163a8c10c06be821

    Mirrors

    CivitAI (8 mirrors)

    TCTR18QW73ACEKD4Z97SXSE490.safetensors

    Size:
    217.88 MB
    SHA256:
    0792d6e140392c63d1db12ddfa137ae08ada8d810a719bfa163a8c10c06be821

    Mirrors

    CivitAI (8 mirrors)