Lora strengths should probably be in the names or somewhere

[cchance27]

I really think that the model strengths should be tagged in the files, its gonna definitly make for some confusion especially with more complicated workflows that have multiple loras and different lora values, if your worried about name length or something for the models maybe need to move away from storing the gen-params in the name and maybe go the way of having a .yaml named after the model next to it that stores the conversion details?

[aszc-dev]

Core ML's metadata seems to be perfect for this use case and I'm planning on using that to store this info, but there are a few details I want to think through first, so that this format doesn't change too often, because it can cause compatibility issues with existing models (worst case scenario, the user will have to convert the model again).
Apart from metadata, I want to implement some compatibility with models available at coreml-community and make sure the parameters can be easily read by the user. Once I come up with a neat directory structure that achieves that, I'll make the required adjustments.

[cchance27]

ah thats a great idea, i sometimes forget metadata on files is an option for stuff like this XD. Especially since comfy's already using metadata for other things.