A hilariously chaotic new prompt is going viral by asking image generators to ditch hyper-realism for awkward, low-quality art.
- The Craze: Users are intentionally prompting AI to create “clumsy” and “pathetic” art that looks exactly like a terrible MS Paint drawing done with a computer mouse.
- The Details: The viral prompt micromanages the AI to ensure the image is confusing, awkward, and heavily pixelated, before ending with a hilariously dismissive surrender.
- The Why: This trend represents a playful rebellion against flawless AI hyper-realism, proving that people still crave imperfection, nostalgia, and human-like irony.

For years, AI image generators have been praised for their flawless, breathtaking realism. But right now, the internet wants the exact opposite. A hilariously specific prompt is going insanely viral, asking AI to “redraw the attached image in the most clumsy, scribbly, and utterly pathetic way possible.” Instead of cinematic masterpieces, users are forcing sophisticated algorithms to mimic a terrible MS Paint drawing done with a computer mouse on a stark white background.

The goal isn’t an accurate replication, but rather an image that is “vaguely similar but also not really.” The prompt specifically demands a “confusing, awkward way” with a “low-quality pixel-by-pixel feel that really emphasizes how ridiculously bad it is.” The true genius of the trend, however, is its beautifully apathetic punchline. After aggressively micromanaging the AI to achieve sheer artistic incompetence, the prompter suddenly gives up, ending the request with: “Actually, you know what, whatever, just draw it however you want.”
Promts for GPT Image 2 “Redraw the attached image in the most clumsy, scribbly, and utterly pathetic way possible. Use a white background, and make it look like it was drawn in MS Paint with a mouse. It should be vaguely similar but also not really, kind of matching but also off in a confusing, awkward way, with that low-quality pixel-by-pixel feel that really emphasizes how ridiculously bad it is. Actually, you know what, whatever, just draw it however you want.”

In a digital world saturated with pristine, AI-generated perfection, this trend serves as a collective palate cleanser. It is a playful rebellion against the flawless, sometimes sterile output that generative models default to. By forcing highly advanced neural networks to cosplay as a bored user messing around on a 1990s desktop, humans are injecting irony and humor back into the creative process. It ultimately proves that even as our digital tools become infinitely capable, our favorite thing to do is find fun ways to break them.
