LTFloat_Step_1

LTFloat_Step_1 is the 1.0 member of the Latent Tools step-helper family, and it's the blunt end of the range: a calibrated constant whose widget steps by a whole integer. Type a value, get the same number back as a FLOAT and a STRING - the only difference from its siblings is the step size, which at 1.0 means "one per run."

The family exists to sweep a parameter across a batch of images with the seed locked, and this is the step for parameters that live on an integer scale - step counts, batch sizes, anything where a fraction is meaningless. Sweep the number of sampling steps from 10 to 40 in thirty-one runs and you get a real read on how much of the image's quality comes from extra steps. It's also handy as a plain labeled constant when you just want a number on a wire plus its string form for a filename, without thinking about precision at all.

How it works

The name makes it sound like a counter, so be clear-eyed: the node does not auto-increment. It takes the value you give it, rounds to five decimals, and returns it as a FLOAT and a STRING. The step is the widget's spinner increment and the label. You bump the value between runs; the node keeps it deliberate.

The inputs and outputs

• value - FLOAT, default 0, range ±1,000,000, step 1.0. (Despite the float type, the step makes it effectively an integer spinner.)
• FLOAT - the value.
• STRING - the value as text, for filename prefixes so each output records its parameter.

Wire the FLOAT into an integer-scale input like sampler steps (via a conversion if the target wants INT), and the STRING into a Save Image filename. Seed fixed, one unit per run, compare.

Installing it

Part of xl0's Latent Tools pack. ComfyUI Manager → search Latent Tools → install → restart, or:

cd ComfyUI/custom_nodes
git clone https://github.com/xl0/latent-tools

Restart, and it's under LatentTools. The pack's only dependency is lovely-tensors (Manager installs it; manual cloners may need pip install lovely-tensors). No model downloads.