Image Analyze

Most of WAS's image nodes transform a picture - blur it, crop it, recolor it. This one doesn't. It's a diagnostic node: feed it an image, and instead of a modified picture, you get back a chart. Per the README, it ships two modes - Black & White Levels (a grayscale luminance histogram) and RGB Levels (a per-channel color histogram) - the same kind of level chart you'd find in a photo editor, just wired directly into your ComfyUI graph.

Why you'd actually use this

The value is catching problems before you commit to them. Rather than eyeballing a batch of outputs and guessing whether something's crushed in the shadows, blown out in the highlights, or carrying an unwanted color cast, wire an Image Analyze node right after your VAE Decode and glance at the histogram before you spend time on an upscale or a second pass. It's also a genuinely useful debugging tool if a LoRA or a checkpoint swap seems to be desaturating or tinting your images in a way you can't quite pin down - the RGB histogram will show a channel skewed low or high in a way a quick look at the image itself might not make obvious.

Keep the distinction straight between this and WAS's Image Levels Adjustment node: Analyze reports what's happening in your image, it doesn't change anything. If you want to actually correct levels rather than just see them, that's a different node.

Installing it

Part of the full WAS Node Suite pack, but this is the one node in the batch with an extra dependency worth knowing about up front: the README states RGB Levels mode depends on matplotlib, which the pack will attempt to install automatically on first run.

• ComfyUI Manager - search WAS Node Suite, install, restart.
• Manual - cd ComfyUI/custom_nodes && git clone https://github.com/WASasquatch/was-node-suite-comfyui/, then pip install -r requirements.txt from inside that folder, then restart ComfyUI.

If you're running in a locked-down venv, an offline environment, or any setup where ComfyUI can't freely pip-install on the fly (some hosted or containerized setups fall into this category), that automatic matplotlib install can fail silently and the node just won't produce a chart. Installing it yourself ahead of time - pip install matplotlib inside your ComfyUI venv - avoids the surprise.

Common issues

If the RGB Levels mode isn't working while Black & White Levels is fine, matplotlib not installing correctly is the first thing to check. Beyond that, remember the output is an image of a chart, not a processed version of your input - don't wire it into a save pipeline expecting your original image to pass through unchanged; the chart is the whole output.

And the pack-wide caveat: WAS Node Suite has been unmaintained since December 2023, and "Import Failed" errors after a ComfyUI update are a real, recurring complaint tied to older pinned dependencies. Reinstalling requirements.txt inside your ComfyUI venv is the usual fix if the whole suite stops loading.