(Brand New To This) Need Just A 🤏 Bit Of Help Plz ❤️ #13720
Unanswered
iammehaha2
asked this question in
Q&A
Replies: 1 comment
-
hi https://github.com/lshqqytiger/stable-diffusion-webui-directml there is a topic there in discussion named sharing the experience... u should check that out otherwise u can go fully CPU mode [search how to use cpu for stable diffusion webui on google for the commands and tips] |
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
-
I was able to get everything working for 1 entire picture then it all crashed down again haha. I do some web design so while I don't know any of this type of coding, I do understand some of the general code functionality and how to troubleshoot code-like problems, so I would love some expert advice to get this working again!
To help diagnose what I need to do, I got the following issues during my time trying to figure this out:
fatal: not a git repository (or any of the parent directories): .git
Similar errors do show up and I think some issues are because I have a Radeon RX 580 instead of a newer model. I have heard these can be used successfully.
RuntimeError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check
I had to add the line in order to get the program to launch
Then I got some kind of error involving --half which fixed it? I can't recreate that atm and can't find it in my browsing history.
After fixing that I was able to make one low quality image in about 15 minutes
Now everything seems to be broken and I'm seeing people saying to adjust my launch.py to ajdust COMMANDLINE_ARGS but my file looks nothing like their example and it doesn't have that option.
So sadly after trying I'm in a bit of a hole as all my fixes don't seem to be working and I can't get the program to start now with error:
launch.py: error: unrecognized arguments: set COMMANDLINE_ARGS=
I would in future also want to try to get better images like I've seen people making, but ofc one step at a time. My image looked like the very first AI created haha.
Thanks to anyone willing to help! I promise to try to be proactive if you'll point me in the right direction!
Beta Was this translation helpful? Give feedback.
All reactions