CivArchive
    林襄 Lin Xiang - v1.0
    Preview undefinedPreview undefinedPreview undefinedPreview undefinedPreview undefinedPreview undefinedPreview undefinedPreview undefinedPreview undefinedPreview undefined

    Don't know why the page becomes 404, so repost

    -

    Using the Chilloutmix-Ni 7G model, the training LORA model has 46 photos and 30 steps

    -

    Model: Chilloutmix-Ni,

    Steps: 30,

    Sampler: DPM++ 2M Karras,

    CFG scale: 12,

    Face restoration: CodeFormer,

    Size: 512x768,

    -

    Denoising strength: 0.6,

    Hires upscale: 2,

    Hires steps: 30,

    Hires upscaler: Latent (nearest-exact)

    -

    It is recommended to enable Highres.fix

    Description

    LORA
    SD 1.5

    Details

    Downloads
    844
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    3/27/2023
    Updated
    8/9/2025
    Deleted
    8/7/2025
    Trigger Words:
    林襄
    1girl

    Files

    林襄.safetensors

    Mirrors

    CivitAI (1 mirrors)

    Available On (1 platform)