ToImageList

ToImageList is the image member of the bmad "make a list" family: it takes several individual IMAGE inputs and hands you one list of images on a single output. It exists because ComfyUI has two different notions of "many images" - a batched tensor (frames stacked in one IMAGE) and an actual Python list - and some nodes and workflows genuinely need the list form. This node is how you build one from loose ends.

The input that matters

inputs_len - the number of input sockets (default 2, up to 32). Set it to 3 and you get image_0, image_1, image_2. Plug in each image, and the output is an IMAGE list. Output: a single IMAGE list socket.

Why you'd reach for it

The classic use is pairing with the pack's ControlNetHadamard node, which takes a list of images and a list of conditionings and applies each ControlNet to its corresponding pair. ToImageList builds the image side of that. It's also the natural companion to list-consuming utilities elsewhere - if a node you imported wants an IMAGE list and your graph produces scattered images, this is the adapter. And the family round-trips: FromListGetImages splits a list back into individual sockets, FromListGet1Image pulls a single one.

Note the distinction from a batch: an IMAGE list is a Python list of tensors, not one stacked tensor. If a node says "IMAGE list" in its input type, that's what it wants - and what this node provides.

Installing

Ships in comfyui_bmad_nodes, bmad4ever's grab-bag of API, CV, and utility nodes. ComfyUI Manager - search "comfyui_bmad_nodes" (or "Bmad Nodes") - install, restart. Manual:

cd ComfyUI/custom_nodes
git clone https://github.com/bmad4ever/comfyui_bmad_nodes
cd comfyui_bmad_nodes
pip install -r requirements.txt

Restart after. No model downloads; pure Python, no opencv needed for this one.

It's a boring utility, and that's the point - when a workflow suddenly demands a list and you've got images scattered across the graph, this is the fastest way to collect them without rewriting anything.