Eugene Brodsky

This is ready to be reviewed again, because the runtime dir / init file location refactoring will be dealt with separately, likely in https://github.com/invoke-ai/InvokeAI/pull/1615

@lstein I'd be keen to tackle all of these if the team desires

I will work on this today, yes. I agree with @mickr777's suggestions, was thinking along the same exact lines. :) And :100: to the autoscan idea, I can certainly do...

@mauwii @damian0815 thank you both for the review and testing! Let me see if I can cover all comments: - I would not expect it to work on Mac in...

I only mean they are inefficient for this specific application (maintaining an external, shared model cache that needs to exist beyond the lifecycle of a pod), because if you have...

so, (again, offtopic :wink: but i can't help being baited by k8s talk): consider a case where multiple application pods are running on a multi-GPU node, and each such pod...

a sidecar is, by definition, a container that runs inside the same pod next to the "primary" container :) (but there's nothing that inherently makes a container a "sidecar" or...

> Share same pod? how can one pod have more entrypoints? In brief: a **pod** is comprised of one or more **containers**. Each container has its own entrypoint, args, environment,...

@damian0815 I also updated the PR description, but: https://runpod.io/gsc?template=vm19ukkycf&ref=mk65wpsa - give this template a try (see README). I ran it through some paces, and it's basically a 2-click process now...

Right, I see the problem - I had the `INVOKEAI_ROOT` set when testing, so it never hit the code path where `get_root()` returns `None`. Sorry about that. I'd like to...