Saturate (HSV)

Saturate (HSV) is a perfectly good node that boosts the saturation of an image, and it has one genuinely funny property: the author says it's probably identical to the HSL version. "Honestly I think this might be the exact same thing. Use this if you are a fan of HSV over HSL!" - his words, in the README. Saturation lives in its own channel in both color spaces, so saturating HSL and saturating HSV run the same math. You're picking a label, not a behavior. If that's fine with you - and it should be - here's how to use it.

How it works

Convert to HSV, add the factor to the saturation channel, clamp, convert back to RGB. Hue and value are left alone, so colors get richer without shifting tone or getting brighter. As with the HSL variant, it can only boost saturation that exists - a gray pixel has no saturation to add to, so this won't invent color in a truly desaturated image. Use it on images that have color but not enough of it.

The inputs that matter

• image - any IMAGE tensor.
• factor (default 0.5, range −1 to 1) - the amount added to saturation. 0 is no change; 0.5 is a solid, obvious boost; 1 maxes everything out; negative values desaturate.
• masked_area + optional mask_opt - the pack's standard masking.

Output: one image tensor.

The one thing to remember

The in-UI description is inverted, same as the rest of the family: it claims factor 0 is "completely saturated" and factor 1 is the original, but the code does saturation += factor, so 0 is the original and higher is more saturated. If you hit 1 and things look radioactive, that's not a bug - that's max saturation.

Otherwise, genuinely no surprises here. The value of this node is that it's one knob, it's fast, and it slots into the pack's mask system for free. When your render needs "more color, exactly here," that's the whole job.

Installing it

ComfyUI Manager → search "Basix Image Filters" (repo basix_image_filters) → install → restart. Or manually:

cd ComfyUI/custom_nodes
git clone https://github.com/maludwig/basix_image_filters

Restart after. No models, no downloads, no exotic dependencies - pure torch math.

Using it well

Same playbook as every node here: boost the saturation on a reference, push it through an img2img pass at 0.7–0.9 denoise, and the model tends to honor the punchier palette. For localized color, mask_opt with a MaskEditor mask and the masked_area toggle picks inside or outside the mask. If you already have the HSL Saturate in your workflow, this one is redundant - but if you're an HSV partisan, it exists, it works, and it's free.