Lora Selector (Yogurt Nodes)

Most ComfyUI LoRA nodes are either "pick the file" or "apply the weights". YogurtLoraSelector splits the difference: it's a picker that doesn't apply anything, but hands you a whole packet of information about the selection - the file name, the stem, the strengths, the trigger word, the absolute path. If you've ever wanted a LoRA choice to drive other nodes - a prompt builder that inserts the trigger word, a path-based loader, an automation graph - this is the node.

It's part of ComfyUI-YogurtNodes, yogurt7771's 150+ node all-in-one pack. Obscure, MIT-licensed, auto-generated README, no community buzz - but this node is the rare one in its model section that's about workflow ergonomics rather than weight math.

How it works

Four inputs:

• lora - an enum of your LoRAs (defaults to "None"), with model_strength and clip_strength sliders (both default 1.0, step 0.1) and a trigger_word text field you can fill in.

And it pays all of that back out. The outputs are where it gets interesting:

• lora - the selection itself, passed through as a value.
• name - the LoRA's full name.
• stem - the filename minus extension.
• model_strength / clip_strength - the strength values, so downstream nodes can read them rather than hardcode.
• trigger_word - the trigger word you entered.
• absolute_path - the resolved path to the file on disk.

It's a metadata router, not a weight loader. Nothing gets applied to a model - you're choosing and describing a LoRA so the rest of your graph can react to that choice. That's the mental model that makes it click: think of it as a "LoRA config object" node, the same way you'd use a selector to drive a switch or a text builder.

Where you'll use it

• Multi-LoRA workflows where you swap models in one dropdown and everything downstream updates.
• Prompt building: pipe trigger_word into a text node so switching LoRA switches the prompt keyword too.
• Automation: feed absolute_path or stem into path-driven loaders and logging nodes.

Install

ComfyUI Manager, search ComfyUI-YogurtNodes, install, restart. Or:

cd ComfyUI/custom_nodes
git clone https://github.com/yogurt7771/ComfyUI-YogurtNodes
cd ComfyUI-YogurtNodes
pip install -r requirements.txt

Restart, look under "Yogurt Nodes". No model downloads - it reads your existing models/loras folder. Light dependencies throughout, since this node is pure selection logic.