Generative Vision Interview Questions #17 - The Perceived Noise Paradox

How zero-mean noise silently destroys your high-res diffusion training, and the timestep shifting trick that rescues your detail-defining steps from being averaged away.

We’re in a Senior ML Engineer interview at Midjourney and the interviewer asks:

“You trained a diffusion model that’s gorgeous at 256px. You scale it to 1024px, keep the exact same noise schedule, and the outputs get quietly worse. Same architecture, same loss, same schedule. What broke?”

Don’t say: “The schedule is resolution-agnostic, so I’d just train …