search

space-nuko / ComfyBox

Customizable Stable Diffusion frontend for ComfyUI
GNU General Public License v3.0
614 stars 48 forks source link

Push/pop workflow settings #80

Open space-nuko opened 1 year ago

space-nuko commented 1 year ago

Might overlap with #9. But anyway I'll often be prompting a lot and I'll suddenly ask myself "is the LoRA/model I'm using even contributing anything to the final output?" and want to test my theory. But I want to test this on a specific prompt/seed/config that I like so I can see how changing the settings affects only that output.

If I have a bunch of stuff queued already and want to go back to those settings after my tests then it's too hard right now. Instead would be neat to have a settings stack per-workflow that you can push on/pop off or save for later. Kind of like git stash I guess.

Also the saved data could be converted to standard prompts for reuse in other workflows, too.

space-nuko commented 1 year ago

I think this should be... well... a graph, instead of a stack. You could return to your first set of settings and want to branch off into a different direction while still keeping the other settings to experiment with

space-nuko commented 1 year ago

Also could these be autocreated with diffs instead of manually pushed? That way you could group together a set of prompts as having been originated in one node of the graph. You could turn off autocreation if you just want to tinker first.

What happens if there's some prompts that don't belong to the graph in this case, if they were never pushed but you want to branch off them? I guess you could insert them as a separate graph starting with a root node

I think by default you wouldn't have the autopushing unless you turn it on since it can create a gigantic graph