imagesSplitImage

This is the node for when you have a batch and you want specific, named images out of it - the first one, the third one, whichever - rather than the whole batch as one blob or an arbitrary fan-out. easy imagesSplitImage takes an image batch and unpacks it into five separate, individually addressable outputs: image1 through image5.

The pack's own changelog is blunt about what this is for: "Batch images split into single images." That's the entire feature, and it's a genuinely common need - you generated four variations in one batch and now you want to preview, save, or route them completely independently instead of treating them as a unit.

Why you'd reach for it

Anytime a batch's items need to diverge downstream. A few real cases: you ran a batch of 4 and want to save each one with a different filename prefix; you generated a small set of candidates and want to pick just one (say, image2) to feed into the next stage while discarding the rest; you're building an A/B/C/D comparison layout and each slot needs to come from a specific batch position rather than the batch as a whole. Anywhere you'd otherwise need an index-based switch just to peel one image at a time off a batch, this node gets you all of them at once, each on its own labeled wire.

How it works

It reads the batch and routes position 1 to image1, position 2 to image2, and so on, up through position 5. If your batch has fewer than five images, the outputs past the batch's actual size simply have nothing to give - connect only the outputs that correspond to images you know exist in the batch.

The inputs and outputs that matter

• images - the batch to split. The only input.
• image1, image2, image3, image4, image5 (outputs) - the batch unpacked by position. Wire only the ones you need; leaving the rest unconnected is fine.

Installing it

Ships with the base pack, no separate step. ComfyUI Manager: search ComfyUI Easy Use, install, restart. Manually:

cd ComfyUI/custom_nodes
git clone https://github.com/yolain/ComfyUI-Easy-Use

then install.bat on Windows or pip install -r requirements.txt, restart. No models involved.

Common issues & troubleshooting

Batch has more than 5 images. This node caps out at five named outputs - anything beyond position 5 in the batch simply isn't exposed here. If you need to reach further into a larger batch, you're better off with an index-based node like easy imageIndexSwitch, which can select any position by number rather than being capped at five fixed slots.

Batch has fewer than 5 images. Connecting image4 or image5 when your batch only has 3 images will fail or return nothing meaningful for that slot - only wire the outputs that correspond to images you know actually exist. If your batch size varies at runtime, check it first with easy imageCount before assuming all five outputs are populated.

Confusing this with the grid-split or list-split nodes. All three of easy imagesSplitImage, easy imageSplitGrid, and easy imageSplitList have similar names and live in the same category, but they do different jobs: this one unpacks a batch into up to five named single images; easy imageSplitGrid cuts one image into a row x column batch of tiles; easy imageSplitList spreads a batch across three unlabeled outputs. If the outputs on your split node aren't behaving the way you expect, double-check you grabbed the right one of the three.