Mastodawn

Daniel Bachran Mar 7, 2024

This comment sounded promising, but to no avail: Still getting the same error. The only thing I didn't do, yet, was to switch the execution provider: Searched for "execution provider" in the #automatic111 settings and switched from "CPUExecutionProvider" to "DmlExecutionProvider".

Still getting the same error, though. 🤔

Show thread

Daniel Bachran Mar 7, 2024

#stable_diffusion #automatic111 UI is opening fine, but without ONNX and Olive tabs... 🤔

Checked the settings and enabled Olive and ONNX there, but no change. 😕
(And yes, I have applied the settings, reloaded the UI, and even tried restarting the whole batch. No ONNX and Olive tabs in the UI.)

Daniel Bachran Mar 6, 2024

Tried setting up #stable_diffusion on my new AMD-based PC using https://github.com/nod-ai/SHARK

#shark needs to download a lot of additional stuff when switching models or even changing parameters... This slows down playing around a lot. Cannot remember that from #automatic111 in the past.

Replicating example prompts often fails, since #shark does not seem to support long prompts?

I often get: "Token indices sequence length is longer than the specified maximum sequence length for this model"