PRODUCTION SCENARIO
A museum wants visitors to type a description and get back an original illustration.
Which model capability does the app need?
Answering here is anonymous. Nothing is saved unless you sign in.
Show answer and explanation
Answer: A gpt-image model deployment for image generation
Creating a new picture from a text description needs an image generation model; the gpt-image series is the current family, since dall-e-3 was retired in March 2026. A vision-capable chat model runs the other direction, reading images you send it. An Azure Vision deployment analyzes existing images. A text-embedding model supports similarity search over content that already exists.