ToFloatList
Gather your weights, CFG values and denoise levels into a list
- FLOAT
ToFloatList is the floating-point member of the bmad "make a list" family: it takes several individual FLOAT inputs and bundles them into a single Python list. Floats are the tweaking parameters of ComfyUI - CFG scale, denoise strength, LoRA weights, sampler values - and when you want to sweep or batch over a set of them, this is the node that collects them onto one list wire.
The input that matters
inputs_len - the number of input sockets (default 2, up to 32). Set it to 3 and you get float_0, float_1, float_2. Output: a single FLOAT list. Size it to what you feed; empty slots become empty entries.
Why you'd reach for it
CFG and denoise sweeps are the natural fit - gather a handful of strengths, hand the list to a loop or list-aware consumer, and you get a comparison set in one pass. It also round-trips with the family's splitters (FromListGetFloats / FromListGet1Float) so you can switch between separate wires and a list without restructuring. It's the same machinery as ToIntList, just for fractional values, and ComfyUI is strict about the INT/FLOAT distinction - use the right one or the socket won't connect.
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 extra dependencies.
It's a quiet utility that earns its keep the moment you start tuning - the kind of node you forget exists until a sweep workflow demands floats as a list and you're grateful it's one drag away.
Inputs (1)
| Name | Type | Default | Description |
|---|---|---|---|
| inputs_len | INT | 20–32 | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| FLOAT | FLOAT | — |