Chapter 3 of 5 · Microsoft AI-103
Implement Computer Vision Solutions
Generating and editing images and video, multimodal understanding of images and video, and responsible AI for visual content.
- 2topics
- 8 minfast track
- 10–15%of the exam
Topics in this chapter
Take them in order, or jump to the one you need.
- 1Image and Video GenerationAI-103 media generation: images from text and reference media, inpainting and mask edits, Sora 2 video jobs, parameters such as…4 min
- 2Multimodal Understanding and Visual Content SafetyAI-103 visual understanding: captions, alt text and visual Q&A with multimodal models, Content Understanding for images and…4 min
About this chapter
What this chapter covers
Implement Computer Vision Solutions is 10 to 15% of the AI-103 exam. It has three skill groups: image and video generation, multimodal understanding workflows, and responsible AI for multimodal content.
AI-103 approaches vision through generative and multimodal models in Foundry. You need to know how to create and edit images and videos, how to make models describe and answer questions about images and video, and how to keep visual content safe.
How the topics fit together
Generation models create media from text and reference media. Multimodal models and Azure Content Understanding analyze what is in images and video. Safety controls run on both the inputs and the outputs.
Read whether a question asks to create, edit or understand visual content. Each points to a different model or tool.
How to use these pages
Each topic page has the same shape, so you can skim for what you need.
- What it is: the idea in plain words.
- How it works: the mechanism, with tables and examples.
- What to remember for the exam: the facts to memorise and how questions are phrased.
- Common mistakes: the classic traps.
- Check yourself: three questions to test your understanding.
Ready for more practice?
The full Microsoft AI-103 question bank has 648 questions, with timed practice exams and an explanation for every answer.
This study guide is independent and is not affiliated with, endorsed by, or sponsored by Microsoft. Vendor names, certification names and exam codes are trademarks of their respective owners and are used for identification only.