试了很多模型 各种分辨率就是生图的时候快读完了就变成黑图 然后错误代码 参数也没有设置很大，就是基本参数
重装了系统 重装了软件都解决不了
电脑配置
↓
NVIDIA 系统信息报告创建于： 12/28/2024 22:15:21
NVIDIA 应用程序版本: 11.0.1.189
操作系统: Microsoft Windows 10 רҵ��, 版本 10.0.19045
DirectX 运行时版本: DirectX 12
驱动程序: Studio 驱动程序 - 566.36 - Tue Dec 10, 2024
CPU: 12th Gen Intel(R) Core(TM) i7-12700H
内存: 32.0 GB
存储: SSD - 953.9 GB
图形卡：GPU 处理器: NVIDIA GeForce RTX 3080 Ti Laptop GPU
错误代码
↓
NansException: A tensor with NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
用时:9.5 sec.
A: 2.31 GB, R: 2.44 GB, Sys: 3.7/16 GB (23.1%）


求大佬啊