>

Comparisons are the connective tissue of a smart workflow - "is the CFG above 7?", "did this batch produce more frames than that one?" - and this node is exactly what the display name suggests: the > operator with a node wrapper around it. From the Basic data handling pack, it's one of six basic comparisons (equal, not-equal, >, >=, <, <=), and it does precisely one job, without surprises.

What it does

Takes two numeric values and returns True if the first is greater than the second, False otherwise. Straight Python value1 > value2 under the hood, which means the usual gotcha-free behavior you'd hope for: 5 > 3 is True, 3 > 5 is False, and 5 > 5 is False (that's what >= is for).

The genuinely nice bit is the input type. Both value1 and value2 accept FLOAT,INT, so you can feed it a float from one branch and an int from another without adding a cast node. Most core ComfyUI math nodes will hand you one type or the other; this node doesn't make you normalize them first.

Inputs and outputs

• value1 - the first number (FLOAT or INT). This is the "greater" side.
• value2 - the second number (FLOAT or INT). The comparison threshold.
• Output result - a BOOLEAN, True when value1 > value2.

That's the whole schema - no options, no modes, no hidden settings. Wire a BOOLEAN consumer (an if/else, a switch, a bypass) onto result.

Install

Ships in the Basic data handling pack. ComfyUI Manager → search "Basic data handling" → install → restart, or manually:

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

then restart ComfyUI. Zero dependencies, no models, no pip install step.

Practical note

The output is a real BOOLEAN, so it feeds directly into the pack's own if/else and flow-select nodes, and into any boolean-gated node in your graph. Where people stumble: comparing ints that are actually strings (from a text field) - wire the text into the pack's create INT node first, because "10" > "9" compares alphabetically in Python and returns False, which is a confusing way to spend an afternoon.