CivArchive
    KOKORO(DOA) ZIT-BASE - v1.0
    NSFW
    Preview 119418805
    • Base Model / 底模: * Z-Image (ZIT) Base

    • LoRA Weight / 推荐权重: * Standard: 1.0

      • For Turbo Models: 1.2 - 1.4 (Turbo 模型建议适当调高权重以获得更好的还原度)

      • CFG Scale / 引导值: * 4

      • Sampling Steps / 采样步数: * 30 - 50


    📝 Model Description / 模型介绍

    [EN] This LoRA is meticulously trained based on the Z-Image (ZIT) Base model.

    • Weight Advice: While 1.0 works perfectly for most scenarios, please increase the weight if you are using Turbo-distilled models to maintain character consistency.

    • Prompting: Works best with natural language descriptions. Ensure CFG stays around 4 to avoid over-saturation.

    [CN] 本模型基于 Z-Image (ZIT) 底模进行精细训练。

    • 权重建议: 默认权重 1.0 在大多数场景下表现完美。如果你使用的是 Turbo 系列的高速模型,建议将权重提升至 1.2 - 1.4 以确保角色的一致性。

    • 提示词建议: 推荐使用自然语言(句子)进行描述。请保持 CFG 在 4 左右,过高可能会导致画面崩坏或色彩过饱和。

    Description

    FAQ

    LORA
    ZImageBase

    Details

    Downloads
    108
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/31/2026
    Updated
    4/27/2026
    Deleted
    -

    Files

    KOKORO Z.safetensors

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)