Adjust Brightness

This is exactly what it says: a node that makes an image brighter or darker. No diffusion, no model, no surprises - it multiplies the image's brightness by a number you set and hands it back. It's the ComfyUI equivalent of the brightness slider in any photo app, dropped into your graph so you can nudge exposure after generation without leaving the workflow.

It's one node in a small family of "Simple Image Adjustment" utilities the pack ships - the same set covers contrast, sharpness, saturation, hue, gamma, tone curve, grayscale, and RGB channels. The design point the author calls out is that they're all built to daisy-chain: the image output of one feeds straight into the next, so you can string together brightness → contrast → saturation and build a little grading stack right in the node graph. Nothing here is fancy; the value is having the whole basic-adjustment toolbox available as plain nodes instead of round-tripping to an image editor.

How it works

It applies a straightforward brightness scaling to the pixels of src_image. A level of 1.0 is neutral - the image comes out unchanged. Below 1.0 darkens, above 1.0 brightens, and it goes up to 10 if you want to blow something out on purpose. That's the entire mechanism; because it's a direct pixel operation it's instant and lossless in the sense that it's not re-encoding through a VAE or a model.

The inputs that matter

There are only two, so both matter:

• src_image - the image to adjust.
• level - the brightness multiplier, 0 to 10, default 1.0 (neutral). The useful range for a gentle correction is roughly 0.8 to 1.3; go further only when you want a strong effect. Because it's a multiply, small steps do a lot near 1.0.

Output is a single image, ready to feed the next adjustment node or a save node.

Install

ComfyUI Manager → Custom Nodes Manager → search ComfyUI_Mira → Install → restart. Or by hand: cd ComfyUI/custom_nodes && git clone https://github.com/mirabarukaso/ComfyUI_Mira.git, then restart ComfyUI. If the pack errors on load, run pip install -r requirements.txt in its folder. No model downloads - these adjustment nodes are pure image math.

Common issues

There's very little to go wrong here. If nothing seems to change, check that level isn't still at 1.0 - that's the neutral value and it deliberately does nothing. If a bright image clips to flat white, you've pushed level too high and the highlights have blown out; back it off, because a multiply can't recover detail it pushed past the ceiling. And if you're trying to grade rather than just brighten, remember this is one node in a chain - reach for the contrast, saturation, and tone-curve siblings alongside it rather than trying to do everything with brightness alone.