Discuss matters related to our favourite AI Art generation technology
The update process should be simple but may be buggy while things are ironed out. Installing a second copy of Automatic1111 would allow you to test SDXL without causing issues with your current setup, in case it takes a while.
New loras/embeddings/etc will have to be created for SDXL. Any pre-existing loras will only work with older models, so the community will have to spend time training new ones for SDXL
This makes sense. Damn it's going to take a while to get all new models trained up again, there's such a wealth of them right now
No reason to wait, you are getting experience by playing around with current state!
The real value of SDXL isn't the higher native resolution, its the improvements in rendering fingers and text and so on. But honestly I have not yet been super impressed by SDXL, in the same way that I want to stay playing the old game with all its DLC and mods. SDXL is good, but until we have the same depth of resources available I am staying with 1.5.
You probably just need to download the SDXL model and update Automatic.
is updating automatic just git pull?
The release candidate appears to have support for it. Just wait for full release and pull the changes and download the model. Should be as easy as that.
Yeah, should suffice.