The action I see is happening in comfy-ui workflows. That software is progressing rapidly and adapts to whatever sota models are available.
Heavy emphasis is on making cutting edge models work with limited local compute.
Heavy emphasis is on making cutting edge models work with limited local compute.
For example, I wanted help setting up the use of a lora and batch iteration. The LLM can figure out where you've hooked things up incorrectly. The UI is funky and the terms and blocks require familiarity you won't have to start.
I think learning the basics of it this way would be useful because you'll get some positive feedback loop going before trying to make use of someone's shared, complex workflow.