Chapter 6 of 7 · Microsoft AI-901
Computer Vision and Image Generation in Foundry
Sending images to a multimodal model, building vision apps, and generating and editing images with image models.
- 2topics
- 10 minfast track
Topics in this chapter
Take them in order, or jump to the one you need.
- 1Visual Input and Vision ApplicationsAI-901 vision apps: sending an image with image_url to a multimodal model, URL or base64 input, the detail setting, limits, and…5 min
- 2Generating ImagesAI-901 image generation: gpt-image models in Foundry, prompt, size, quality and output_format, base64 results, edits with a mask…5 min
About this chapter
What this chapter covers
This chapter covers two directions of visual AI in Foundry. In the first, you send an image to a multimodal model and get a written answer, which is how you interpret visual input. In the second, you ask an image model to create or edit a picture from a text prompt.
It also shows how those ideas combine in a small application, and what the models can and cannot do reliably.
How the topics fit together
- Visual input and vision applications covers how an image is attached to a prompt, the detail setting, limits and building a vision app.
- Generating images covers image models, request parameters, editing, the images playground, safety and provenance.
Keep the two directions apart. Understanding an image needs a multimodal chat model. Creating an image needs an image generation model.
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 examples and tables.
- 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-901 question bank has 511 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.