这是第二个正式发布SDXLlora后续模型有什么问题可以向我反馈我会在后续版本中迭代
This is the second official release of the SDXLlora follow-up model, any questions can you give me feedback, I will iterate in the subsequent version
模型反馈技术交流Q****:377209248
建议出图参数（Suggest drawing parameters）：
推荐SDXL底模（Recommended SDXL base mode）：StarlightXLAnimated_v2
LORA建议权重0.6~0.8 LORA recommends a weight of 0.6 to 0.8
起手tag（Start tag）：best quality,masterpiece,realistic,full body,1girl,pink hair,k/da \(league of legends\),3D graphics,there is a star below the left eye,
采样方法（Sampler）:
DPM++ 3M SDE Exponential45步及以上（推荐这个recommend）
DPM++ 2M SDE Karras45步及以上
切记低配置的电脑要开启1:1倍率高清修复Remember to turn on 1:1 HD repair for low-profile computers
提示词引导系数(CFG Scale): 3~7
等倍高请修复人像人物分辨率（When times higher please fix portrait figure resolution）： 768x1280 ，1024x1024
高清修复（Hires.fix）: 4x-UltraSharp ,高分迭代步数10~15重绘幅度0.3~ 0.5
Clip Skip: 2
负面提示词(Negative)：text,username,logo,(low quality, worst quality:1.4),(bad anatomy),(inaccurate limb:1.2),bad composition,inaccurate eyes,extra digit,fewer digits,(extra arms:1.2),watermark,multiple moles,mole onbody,
本模型中不包含任何真人素材图像源和训练代码来自互联网，模型仅用于科研兴趣交流
This model does not include any real-life material, image sources, and training codes from the internet. The model is only used for scientific research interest exchange