A tensor with all NaNs was produced in Unet #10313
-
|
Error: 'A tensor with all 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. how to resolve |
Beta Was this translation helpful? Give feedback.
Replies: 5 comments 1 reply
-
|
Error: A tensor with all 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.. Check your schedules/ init values please. Also make sure you don't have a backwards slash in any of your PATHs - use / instead of . |
Beta Was this translation helpful? Give feedback.
-
|
how to resolve this kindly help new to stable diffusion |
Beta Was this translation helpful? Give feedback.
-
|
could you resolve it? |
Beta Was this translation helpful? Give feedback.
-
|
same here, nobody know how to fix it? |
Beta Was this translation helpful? Give feedback.
-
|
The cause of this problem is not unique, and more information is required to determine it, such as hardware specifications and operating environment. A common approach is to add a |
Beta Was this translation helpful? Give feedback.
-
|
|
Beta Was this translation helpful? Give feedback.
The cause of this problem is not unique, and more information is required to determine it, such as hardware specifications and operating environment.
A common approach is to add a
no-halfparameter, or to check the model for corruption.