You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
What are the current command line args and options that Sygil-Streamlit can use in the docker-compose.override.yml file? I have been trying to use the local install (official) version of A1111, but it is currently broken on main for me, and as I am unable to work out why, I'm trying a different codebase.
I currently have a mobile 1050 (non ti) 4GB VRAM card, with 24GB RAM, and a further 24GB of pagefile (Windows 11). I don't mind that the generations take a while, as I can set it up overnight and come back to any results the next day.
Bit of back story:
When I first used A1111 (the weekend before the big break), I was getting pretty decent images for what I wanted, with some changes needed, which I didn't know how to do, due to starting to use AI in that precise moment. If I can get something that is stable, or at least works with the least amount of errors/crashes, I would be appreciated. I've looked into the Colab system, but as I had already downloaded about 110GB of models I wanted to try for various things, I am reluctant to setup and upload all that data, only to clog up my Google Drive. Also, sunk cost fallacy.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi all,
What are the current command line args and options that Sygil-Streamlit can use in the docker-compose.override.yml file? I have been trying to use the local install (official) version of A1111, but it is currently broken on main for me, and as I am unable to work out why, I'm trying a different codebase.
I currently have a mobile 1050 (non ti) 4GB VRAM card, with 24GB RAM, and a further 24GB of pagefile (Windows 11). I don't mind that the generations take a while, as I can set it up overnight and come back to any results the next day.
Bit of back story:
When I first used A1111 (the weekend before the big break), I was getting pretty decent images for what I wanted, with some changes needed, which I didn't know how to do, due to starting to use AI in that precise moment. If I can get something that is stable, or at least works with the least amount of errors/crashes, I would be appreciated. I've looked into the Colab system, but as I had already downloaded about 110GB of models I wanted to try for various things, I am reluctant to setup and upload all that data, only to clog up my Google Drive. Also, sunk cost fallacy.
Please help.
Beta Was this translation helpful? Give feedback.
All reactions