Replies: 2 comments
-
i added --precision full --no-half and now it generates, but its running on my CPU. how do i tell it to run on my GPU instead? |
Beta Was this translation helpful? Give feedback.
0 replies
-
i'm stupid, i had to grab the amd specific version. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi! I have a working install of 1.6.1, i can't remember how i set it up but a friend helped me and it works perfectly fine. Today i tried to update to 1.10.1 and its not working.
First i got: "RuntimeError: Input type (float) and bias type (struct c10::Half) should be the same"
then i added --upcast-sampling and now i get "RuntimeError: mixed dtype (CPU): expect parameter to have scalar type of Float".
I'm using a 6650XT. What do i do?
Beta Was this translation helpful? Give feedback.
All reactions