LayerColor: AutoBrightness

AutoBrightness does one focused thing: it looks at an image and automatically lifts (or drops) it to a sensible brightness, no manual dialing required. Where the Exposure node makes you decide the amount, this one figures it out from the image's own histogram. That makes it the node you want in a batch pipeline, where every image needs to land at a consistent brightness but each starts from a different place.

The controls are deliberately few:

• strength - 0 to 100, default 75. How strongly the automatic correction is applied. At 100 it pushes all the way to its computed target; lower values ease off so you keep some of the original look. The 75 default is a reasonable "correct it, but don't overdo it."
• saturation - -255 to 255, default 8. A saturation nudge applied alongside the brightness fix, because auto-brightening can leave colors looking slightly washed; the small positive default gives them a touch back.

There's also an optional mask input, and this is the genuinely useful bit: feed a mask and the auto-brightness is confined to that region. That turns a global auto-correct into a targeted one - brighten just the subject, just the face, just the background - without lifting the whole frame. The single output is image.

Why use this over plain Exposure? Adaptivity. A fixed exposure value brightens a dark image and an already-bright image by the same amount, which means one of them ends up wrong. AutoBrightness measures each image and applies the amount that image needs, so a batch of mixed exposures comes out evened up. Paired with the mask input it's also a tidy way to rescue an underlit subject sitting in a properly-exposed scene.

The catch is the same as any automatic tool: it's making a judgment call, and sometimes it calls it wrong. A deliberately dark, low-key image will get brightened toward "normal," which may wreck the mood you wanted - that's when you drop strength or reach for the manual Exposure node instead. For hands-off consistency across many images, though, this beats hand-tuning every one, and the mask option gives it more precision than most auto-brightness tools bother with.

Install is the pack standard. Easiest is ComfyUI Manager - search ComfyUI Layer Style (or "LayerStyle"), install, restart. Manual: cd ComfyUI/custom_nodes && git clone https://github.com/chflame163/ComfyUI_LayerStyle, then pip install -r requirements.txt from inside the folder using ComfyUI's Python, and restart. On a hosted ComfyUI it's typically preinstalled.

The pack-wide thing to know: Layer Style is well known for import failures - install it, restart, and the whole node set is red or missing. It's rarely the specific node; it's a dependency clash. The pack pulls a heavy stack (transformers, onnxruntime, opencv), and one mismatched version - a stray transformers or tensorflow in the environment being the usual culprit - takes the entire pack down on import. Fix it by reading the ComfyUI startup log for the traceback (it names the package that actually broke), reinstalling requirements against ComfyUI's own Python, and using Manager's Try Fix. If AutoBrightness is missing, so is every other LayerStyle node, and that shared import failure is the real problem to fix.