Question

A marketing team uses a generative image model deployed in Microsoft Foundry to produce promotional artwork from text descriptions. They need to confirm what type of input the model requires and what it produces so they can integrate it into their content pipeline. Which statement correctly describes how a text-to-image generative model in Foundry works?

Accepted Answer

It accepts a natural-language text prompt as input and produces one or more generated images as output.

Answer

It accepts an existing image as input and returns a text caption describing that image.

Answer

It accepts a text prompt and returns extracted structured fields from a document.

Answer

It accepts an audio recording as input and produces a synthesized spoken response.