Assuming the watermark works like the upcoming AI watermark for text, then it uses the content's entropy to embed the information. An all-black image doesn't have much entropy, so it's unlikely you'd find anything.
Assuming the watermark works like the upcoming AI watermark for text, then it uses the content's entropy to embed the information. An all-black image doesn't have much entropy, so it's unlikely you'd find anything.
I guess that makes sense. So import an image of the mandelbrot set you generated and save it, and see if any pixels change.