AI-900 Practice Question: Describe features of generative AI workloads on Azure
A marketing team wants to generate unique product images by providing detailed textual descriptions. Which Azure OpenAI model should they use?
⚠ Common exam trap
Test-takers frequently confuse GPT-4's general-purpose capabilities with image generation, not realizing that DALL-E is the dedicated model for text-to-image tasks in Azure OpenAI.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
DALL-E
DALL-E is the correct Azure OpenAI model because it is specifically designed to generate images from textual descriptions. It uses a diffusion-based architecture to create high-quality, unique images based on detailed prompts, making it ideal for the marketing team's requirement.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
GPT-4
Why it's wrong here
GPT-4 is an autoregressive large language model that predicts text tokens; although it can accept image inputs and perform visual reasoning (multimodal), its output space is strictly text, so it cannot render pixel-based product images. Image generation requires a dedicated generative model such as DALL-E that produces visual outputs from a latent diffusion process. This distinction between understanding/describing images and generating novel images is fundamental in generative AI.
- ✓
DALL-E
Why this is correct
DALL-E is an OpenAI generative image model that maps text prompts to visual concepts using a transformer-based prior and a diffusion decoder, allowing it to synthesize entirely new product images from descriptions. Because it learns a joint distribution of text and images, DALL-E can create original photorealistic or stylized visuals that do not exist in its training set, unlike retrieval-based systems. It is the correct choice for this marketing task because the requirement is to generate original product images, not to analyze or edit existing ones.
- ✗
Codex
Why it's wrong here
Codex is OpenAI's code-generation model, a GPT-3 descendant fine-tuned on GitHub source code; it autocompletes and synthesizes functions, scripts, and snippets in many programming languages. While Codex can technically be used to write a script that calls an external image API, it is not an image-generation model itself and has no ability to produce visual textures, shapes, or pixels. Selecting Codex would conflate software development with generative visual AI, and it would not satisfy a direct requirement to create product images.
- ✗
Whisper
Why it's wrong here
Whisper is an automatic speech recognition (ASR) model trained on 680,000 hours of multilingual audio; it converts spoken language into transcribed text and supports translation to English. Its architecture processes log-Mel spectrograms and outputs token sequences, so it has no component for generating images or conditioning on visual prompts. Thus, Whisper is categorically unsuited for generating product images, as its entire input domain is audio.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.