Question

You are building a lightweight vision app in the Azure AI Foundry portal. A retail team wants users to upload a product photo and receive a natural-language description of what is shown in the image, including colors and objects. Which approach lets you accomplish this with the least development effort?

Accepted Answer

Deploy a multimodal generative model and send the image together with a text prompt asking it to describe the photo

Answer

Train a custom image classification model to output a fixed list of category labels

Answer

Use Azure Content Understanding to extract structured fields from the image

Answer

Deploy a text-only generative model and paste a manual description of the image into the prompt