ToModelList

ToModelList is the model member of the bmad "make a list" family: it takes several individual MODEL inputs - the things CheckpointLoader, LoRA-loaded models, and model-merging nodes output - and bundles them into a single Python list on one output. Models are heavyweight objects and you usually only deal with one at a time, which makes this the least-used member of the family. But when a workflow genuinely needs to iterate over multiple models, it's the clean way to line them up.

The input that matters

inputs_len - how many input sockets appear (default 2, up to 32). Set it to 2 and you get model_0 and model_1. Output: a single MODEL list. The usual rule applies - size the count to what you feed, because empty slots land as empty entries in the list.

Why you'd reach for it

Model lists show up in comparison and ensemble workflows: sampling the same prompt through several checkpoints, or feeding a list-aware node that processes each model in turn. It round-trips with the family's splitters - FromListGetModels hands models back on individual sockets, FromListGet1Model pulls a single one - so you can switch between "one wire per model" and "a list of models" without restructuring your graph.

One honest note: this is the heavy end of the family. Each model in the list is a full loaded model in VRAM, so a 32-slot ToModelList with everything plugged in is a great way to run out of memory fast. Keep inputs_len small and only load what you'll actually use.

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; the node itself is pure Python with no extra dependencies.