LTFloat_Step_0005

LTFloat_Step_0005 is the 0.005 member of the Latent Tools step-helper family - the transition point where sweeps stop being glacial and start covering ground. Like its siblings it's a calibrated constant: type a value, get the same number back as a FLOAT and a STRING, with the widget's increment set to 0.005.

The family's whole purpose is parameter sweeps with a locked seed - change one number per run, compare, learn. At 0.005 per image you get a visibly stepped-but-smooth progression, and a 200-image run moves a parameter by a full unit. That makes it a solid choice for noise sweeps where you care less about per-frame smoothness than about actually covering a range: bump σ from 0.8 to 1.2 in eighty runs instead of four hundred.

How it works

Straightforward, and worth stating plainly: 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 spinner increment and the label. You bump the value between runs; the node keeps the process deliberate and consistent.

The inputs and outputs

• value - FLOAT, default 0, range ±1,000,000, step 0.005.
• FLOAT - the value.
• STRING - the value as text, for filename prefixes so each image records its own parameter.

Feed the FLOAT into LTGaussianLatent's mean or std, the STRING into a Save Image filename, keep the seed fixed, and you've got a self-labeling sweep.

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.