Microsoft · AI-103
Generate and edit images and videos
AI-103 · Lesson 10 of 15 · 1:20:10
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the AI-103 exam (Azure AI Apps and Agents Developer Associate). In this lesson: image models in Foundry (GPT-image, FLUX), the Images API through the Azure OpenAI v1 endpoint (base64 output), generation controls (size, quality, n, format, background, streaming), editing with masks and reference images (inpainting, input fidelity), and video generation with Sora 2 (asynchronous jobs, reference image, remix). Includes three original practice questions.
Preview the topics
- After calling images.generate on a GPT-image deployment, a developer reads the url field of the first result, and gets nothing. What’s wrong?
- A furniture site wants to replace only the sofa in a living room photo with one of its armchairs, and keep everything else unchanged. What should the call include?
- An app calls videos.create, then immediately tries to download the MP4, and the download fails. What should it do?