CivArchive
    Box series - European and American character design drawing<盒子系列——欧美角色设计立绘> - v2.0
    NSFW
    Preview 10623191
    Preview 10623186
    Preview 10623181
    Preview 10623193
    Preview 10623188
    Preview 10623190
    Preview 10623189
    Preview 10623185
    Preview 10623192

    Box series - European and American character design drawing

    Bottom mold recommendation: The whole net first | SHMILY classical colorful _v1.0,model address: https://huggingface.co/swl-models/shmily-GuDianXuanCai-v1.0/tree/main

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

    Sampler recommendation: DPM++ 2 m 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 0.3

    ADetailer is enabled. Recommended AD model: face_yolov8n.pt

    The recommended weight of lora is 0.5-0.85

    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

    盒子系列——欧美角色设计立绘

    底模推荐:全网首发|SHMILY古典炫彩_v1.0,模型地址:https://huggingface.co/swl-models/shmily-GuDianXuanCai-v1.0/tree/main

    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0.3

    ADetailer开启,AD模型推荐:face_yolov8n.pt

    lora权重推荐0.5-0.85

    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

    V2.0 version has more materials, and the understanding of prompt words is better than V1.0 version, the quality of the model is much better than v1.0, and V2.0 is recommended.

    The material comes from the character design type of Valanrote, with a strong European and American cartoon character design characteristics of the model

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

    Sampler recommendation: DPM++ 3M SDE Exponential

    Recommended number of iteration steps: 30

    It is recommended to open HD repair: the amplification algorithm is 4x-UltraSharp,

    Open the ADetailer, recommended AD model: face_yolov8n.pt, recommended to open an ad model for repairing eyes: mediapipe_face_mesh_eyes_only

    The recommended weight of lora is 0.7

    CFG: 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

    This model is only used for communication and learning, and is not commercially available. It is open to download on various platforms. If it is integrated, please mark the original model to avoid unnecessary trouble

    V2.0版本素材更多,而且对提示词的理解是优于V1.0版本,模型出图质量比v1.0好很多,推荐使用V2.0.

    素材来源于瓦兰洛特人物设计类型,具有强烈的欧美卡通角色设计特色的模型

    底模推荐:全网首发|SHMILY古典炫彩_v1.0,

    采样器推荐:DPM++ 3M SDE Exponential

    迭代步数推荐:30

    推荐开启高清修复:放大算法为4x-UltraSharp,

    ADetailer开启,AD模型推荐:face_yolov8n.pt,推荐多开一个修复眼睛的ad模型:mediapipe_face_mesh_eyes_only

    lora权重推荐0.7

    CFG为: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

    此模型仅用作交流和学习,不可商用,在各个平台开放下载,如果融合请标注原模型以免不必要的麻烦

    FAQ

    LORA
    SD 1.5

    Details

    Downloads
    319
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/24/2024
    Updated
    5/16/2026
    Deleted
    -
    Trigger Words:
    HEZI

    Files

    欧美卡通人物设计V2版本-000012.safetensors

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.