a photo portrait of a beautiful girl with curls and lots of freckles, (dirty blonde hair), (face portrait:1.5), dramatic light, Rembrandt lighting scheme, (hyperrealism:1.2), (8K UHD:1.2), (photorealistic:1.2), shot with Canon EOS 5D Mark IV, detailed face, detailed hair
modules.devices.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.
重新启动界面再看在的是不是ok的,重新启动程序之后验证信息的发现,还是不行的.
我们换一种方法,首先知道的改程序下的所有参数在
可以看到有参数
parser.add_argument("--disable-nan-check", action='store_true', help="do not check if produced images/latent spaces have nans; useful for running without a checkpoint in CI")
parser.add_argument("--no-half", action='store_true', help="do not switch the model to 16-bit floats")