CivArchive
    Box series - Food Girl<盒子系列——吃货女孩> - v1.0
    Preview 5759104
    Preview 5759085
    Preview 5759094
    Preview 5759097
    Preview 5759102
    Preview 5759101
    Preview 5759088
    Preview 5759089
    Preview 5759092
    Preview 5759107
    Preview 5759095
    Preview 5759103
    Preview 5759091
    Preview 5759099
    Preview 5759105
    Preview 5759090
    Preview 5759098

    Box series - Food Girl

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

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

    Sampler recommended: DPM++ 2M Karras,

    Recommended number of iteration steps: 30

    It is recommended to open the HD repair: the magnification algorithm is R-ESRGAN 4x+ Anime6B, magnify 2 times, and the redraw amplitude is 0.5

    ADetailer is enabled. Recommended AD model: face_yolov8s.pt

    lora weight is recommended to be 0.6-0.7

    CFG: 5.5 to 7

    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

    盒子系列——吃货女孩

    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++ 2M Karras,

    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0.5

    ADetailer开启,AD模型推荐:face_yolov8s.pt

    lora权重推荐0.6-0.7

    CFG为:5.5~7

    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
    198
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/22/2024
    Updated
    1/12/2026
    Deleted
    -
    Trigger Words:
    hezi

    Files

    盒子系列——吃货女孩.safetensors

    Mirrors

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