Open GiveMeFox opened 11 months ago
Encounter this issue on Mac (with intel core), too. It seems the setting '--no-half' is not passed to Python modules correctly. A WAR is configure it in Python modules manually.
I am now getting this issue on AMD. I added the same arguments as OP, and it does not seem to fix the issue for me. Notably, it was working fine last night.
ᐉ stable-diffusion-web-ui-server --skip-torch-cuda-test --precision full --no-half
PC SPECS
GPU: AMD 7900 XTX
OS: Arch Linux; Install AUR Repository
aur/stable-diffusion-web-ui-git v1.6.0.r2.4afaaf8a-1 (+2 1.67) (Installed: v1.6.1.r0.4afaaf8a-1)
Stable Diffusion Web UI (AUTOMATIC1111)
CPU based Linux, below, it works.
This does the trick for me, as the args are passed on to the launch.py etc. files:
bash webui.sh --skip-torch-cuda-test --no-half
FYI, I have had to manually install
pip install xformers
though.
Ref.
Central Processing Unit: Intel i5-8265U (8) @ 3.9GHz
Operating System: Ubuntu 22.04.3 LTS x86_64 Kernel: 6.2.0-39-generic Shell: /bin/bash 5.1.16 Python: 3.10.12
Is there an existing issue for this?
What happened?
i found 8773 that talks about the same issue and from what i can see someone solved it by setting COMMANDLINE_ARGS="--skip-torch-cuda-test --precision full --no-half" but a weird thing happens when i try that
I doesn't even start and suggest adding --skip-torch-cuda-test to COMMANDLINE_ARGS but its already there am I doing something wrong?
Steps to reproduce the problem
What should have happened?
I think I should be able to click generate and there shouldn't be any errors in the console
Sysinfo
sysinfo-2023-10-06-01-37.txt
What browsers do you use to access the UI ?
Other
Console logs
Additional information
No response