I think it is actually ChatGPT – and it's one of the few genuinely beneficial uses of the technology. Sure, you have to watch out for it making up an "explanation" of what's in the image, but if you treat it like a whimsical, self-absorbed prankster, it's so much better than not having it.
I'm looking forward to a system that only describes what it sees (and what can be drawn from it), rather than doing stuff like trying to explain non-visual jokes (that, inevitably, it doesn't get). As I understand, that would require training new models from scratch, on training data that might not yet exist – but unlike the majority of the LLM GenAI hypey nonsense, this is actually a real, useful tool.