ConditioningAverage_motorway_edition

ConditioningAverage is the subtle one of the conditioning toolbox. Unlike ConditioningCombine (which concatenates two prompts' worth of conditioning) or ConditioningConcat (which joins them in sequence), this node interpolates: it moves one conditioning toward another by a strength value, which is how you blend two prompt interpretations without fully committing to either. This _motorway_edition clone keeps that math and runs it off agilly1989's keyed motorway bag.

In practice that means: the conditioning_to and conditioning_from values come out of the bag by key instead of off wires, the blend strength stays a widget, and the blended result goes back into the bag. A genuinely useful trick with this node: average your positive prompt toward a second phrasing at low strength (0.1–0.3) to steer a composition without letting the second prompt dominate - something people reach for when a single prompt keeps collapsing into one clichéd layout.

The fields

Small schema, one numeric widget and the rest key strings:

• MOTORWAY 🚌💨 - the bag, in and out.
• INPUT_conditioning_to_key (default conditioning_to) - the "destination" conditioning to move toward.
• INPUT_conditioning_from_key (default conditioning_from) - the starting conditioning.
• conditioning_to_strength - a float from 0 to 1, default 1.0. This is the dial that matters: 1.0 means "be the to conditioning", 0 means "stay the from", and the middle is the blend. The step is 0.01, so you can ease in tiny nudges.
• OUTPUT_CONDITIONING_key (default CONDITIONING) - where the interpolated result is written.

Single output, the motorway itself, like every node in the family.

Install and the standing warning

Install stays easy - the pack is pure Python with no pip requirements and no model files:

cd ComfyUI/custom_nodes
git clone https://github.com/agilly1989/ComfyUI_agilly1989_motorway

Restart ComfyUI, or install ComfyUI_agilly1989_motorway from ComfyUI Manager.

Now the warning that applies to every _motorway_edition node: single-author beta, README banner "BIG BROKEN WITH ASYNC WILL FIX WHEN I GET THE TIME/MOTIVATION," and the machine-generated clones are disabled in current releases - the clone registration in __init__.py is commented out. Fresh installs give you MotorwayStart and the Motorway AxB ramps; this node may or may not appear depending on the version. If it's absent, the stock ConditioningAverage plus two ramp nodes reproduces it exactly. And the motorway's one error - 'MotorwayClass' object has no attribute 'hash_' - means a key you referenced was never written into the bag. Given that this node defaults to conditioning_to and conditioning_from as keys, make sure upstream nodes actually published under those names, because they don't exist until something writes them.