🔶 Any array2input -> ALL

The trimmed-down sibling of Any array2input -> ALL (Big). Same job - unpack an array back into individual wires all at once, no index picking involved - just capped at four outputs instead of nine. If you're only ever bundling two or three values, this is the smaller box to keep on your canvas instead of a nine-output node with most of its ports unused.

What it does

array (required, ARRAY type) comes from the pack's array-building node, Any input2array (Big) - build with up to nine inputs there if you like, but this node only reads back the first four. Outputs are ANY_1 through ANY_4, wildcard-typed, each carrying whatever was wired into the matching position upstream. Position 5 and beyond on the source array, if you filled them, simply aren't exposed here - use the Big unpacking node instead if you need more than four back out.

There's no selector widget on this node, same as its Big counterpart - it's a straight unpack-everything operation, not a pick-one operation. For picking a single value dynamically by index, that's Any array2input -> 1 Input's job, not this one.

Why you'd reach for it

Purely a footprint choice. If your array never holds more than four meaningful values, this node does the same unpacking job as the Big version with four fewer unused ports cluttering the node on your canvas - useful once a workflow has enough of these small utility nodes stacked up that screen space actually starts to matter. There's no functional advantage beyond that; pick whichever size matches how many values you're actually bundling.

Installing it

Via ComfyUI Manager: search "Chaosaiart-Nodes," or "Install via Git URL" with https://github.com/chaosaiart/Chaosaiart-Nodes, then restart. Manually: cd ComfyUI/custom_nodes && git clone https://github.com/chaosaiart/Chaosaiart-Nodes, restart ComfyUI. Linux needs pip install opencv-python and pip install tqdm (venv active first) for the pack to load cleanly - this node doesn't use either directly, but the pack imports as one unit. Windows has a bundled Install_windows script. No model downloads.

Troubleshooting

If you built an array with five or more inputs and only see four coming back out, that's expected - this node caps at ANY_4; switch to the Big version if you need the rest. If an output isn't producing anything useful, check that the matching slot was actually filled on the array-building node upstream - an empty input position stays empty here too. And since array only accepts the pack's own ARRAY type, this has to be fed from Any input2array (Big) or the Small equivalent, not from a generic list output elsewhere in your graph.