CivArchive
    HEZI Fifth personality Illustration 2.0<HEZI_第五人格插画2.0> - v1.0
    Preview 23414451Preview 23414421Preview 23414423Preview 23414422Preview 23414425Preview 23414424Preview 23414440Preview 23414441Preview 23414443Preview 23414442Preview 23414446Preview 23414450Preview 23414452

    Bottom mold recommendation: The whole net first | SHMILY classical colorful _v1.0,

    VAE is recommended: vae- FT-MSE-84000-EMA-Pruned.safetensors

    Recommended sampler: DPM++ 3M SDE,DPM++ 2M Karras, Euler a,

    Recommended number of iteration steps: 30

    It is recommended to open the HD repair: the magnification algorithm is R-ESRGAN 4x+ Anime6B, magnification is 2 times, and the redraw amplitude is 0.3~0.6

    ADetailer is enabled. Recommended AD model: face_yolov8n.pt

    The recommended weight for lora is 0.5-0.75

    CFG: 5.5

    CLIP Recommended: 2

    The generalization is very good and can be combined with other lora, I hope you can return more pictures and praise more, thank you


    底模推荐:全网首发|SHMILY古典炫彩_v1.0,

    VAE推荐开:vae-ft-mse-840000-ema-pruned.safetensors

    采样器推荐:DPM++ 3M SDE,DPM++ 2M Karras,Euler a,

    迭代步数推荐:30

    推荐开启高清修复:放大算法为R-ESRGAN 4x+ Anime6B,放大2倍,重绘幅度为0.3~0.6

    ADetailer开启,AD模型推荐:face_yolov8n.pt

    lora权重推荐0.5-0.75

    CFG为:5.5

    CLIP推荐:2

    泛化性很好可结合其他lora,希望大家多返图多点赞,谢谢

    Description

    LORA
    SD 1.5

    Details

    Downloads
    65
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/9/2024
    Updated
    10/1/2025
    Deleted
    -
    Trigger Words:
    HEZI

    Files

    第五人格2.0-000015.safetensors

    Mirrors

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