Issue 22, Jun 30, 2026
The DreamBooth Trap
Generative AI Engineer interview at Midjourney, and the interviewer asks:
“You DreamBooth a model on 5 photos of a client’s product. It generates that product perfectly, but now everything else it draws looks broken. Why, and how do you fix it without re-collecting data?”
Don’t say: “Just train on more images of the product”
Why naive few-shot personalization quietly steamrolls your model’s prior knowledge, and how to use a frozen base model as its own supervisor to stop catastrophic forgetting.
Share this trapShare on LinkedIn
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.