Question

A marketing team wants to build a lightweight app in Azure AI Foundry. Users upload a rough product sketch, and the app must produce several polished, photorealistic promotional images based on that sketch. Which capability should the developer use in the Foundry workflow to create the visual outputs?

Accepted Answer

A generative image model that produces new images from the provided input

Answer

An image classification model that assigns a category label to the sketch

Answer

An optical character recognition (OCR) service that extracts text from the sketch

Answer

An object detection model that draws bounding boxes around items in the sketch