>=

"Greater than or equal" is the comparison you reach for when the boundary condition matters - "did we generate at least N images?", "is the upscale factor high enough that we can skip the small pass?" It's >= with a node wrapper, from the Basic data handling pack's comparison family, and it's about as simple as nodes get.

What it does

Returns True when the first value is greater than or equal to the second, False otherwise. Under the hood it's plain Python value1 >= value2. The difference from its > sibling matters exactly at the boundary: 5 >= 5 is True here, where 5 > 5 is False. If you're building "at least / minimum / threshold" logic, this is the one you want - the strict version silently eats your boundary case.

Both inputs accept FLOAT,INT, so you can mix an int from one branch with a float from another and skip a cast node. That single type-flexibility is the pack's quiet superpower across all its comparison nodes.

Inputs and outputs

• value1 - the first number (FLOAT or INT).
• value2 - the second number (FLOAT or INT), the threshold.
• Output result - BOOLEAN, True when value1 >= value2.

No settings, no modes. If you find yourself reaching for it constantly, you'll appreciate that the output is a genuine BOOLEAN that plugs straight into if/else, flow-select, or any boolean gate without conversion.

Install

Part of the Basic data handling pack. Via ComfyUI Manager: search "Basic data handling", install, restart. Or the manual route:

cd ComfyUI/custom_nodes
git clone https://github.com/StableLlama/ComfyUI-basic_data_handling

then restart ComfyUI. No dependencies, no model downloads - the pack is pure Python.

The one trap

Same one that catches people on all the numeric comparison nodes: if your number arrives as a string from a text field, Python compares strings alphabetically, and "9" >= "10" returns True because '9' sorts after '1'. Cast with the pack's create INT node before comparing, and your thresholds will behave like numbers again.