ToCondList

ToCondList is the conditioning-flavored member of the bmad pack's "make a list" family. It collects several individual CONDITIONING inputs - the things CLIPTextEncode and its friends output - and bundles them into a single Python list on one output wire. In a ComfyUI world that loves lists for everything from ControlNet pairing to prompt variation loops, this is the node that turns a handful of separate conditionings into something a list-consuming node can chew on.

The input that matters

inputs_len - how many input sockets the node shows (default 2, up to 32). Set it to 4 and you get four CONDITIONING inputs, named conditioning_0 through conditioning_3. Leave one unplugged and it stays empty in the list, so match the count to what you actually feed it. Output: a single CONDITIONING list.

Why you'd reach for it

The pack's own ControlNetHadamard node is the poster child: it takes a list of conditionings and a list of images and applies each ControlNet to its paired conditioning once, instead of the every-against-every explosion you get from naive wiring. ToCondList is how you build that conditioning list. It also plays with the list ecosystem generally - FromListGetConds and FromListGet1Cond split lists back into individual or single sockets, so you can round-trip a list into a workflow that only wants one conditioning at a time.

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, and this node is pure Python - it doesn't even need the pack's opencv requirements. There's also an ExtendCondList sibling that appends existing lists instead of building one from scratch, if that's the shape you need.

One honest caveat: conditionings are big objects, and a 32-slot list node full of them can get unwieldy fast. Keep inputs_len to what you actually use, and you'll have a clean, readable wire instead of a bundle of rope.