Skip to main content
This is lesson 3 of 4 in this module Course 85% complete
Prev Next Skip

Using Vision-Capable Multimodal Models

Premium Content

Sign in with your account or sign up to access this lesson.

Sign In Sign Up

We demonstrate how to deploy a vision-capable multimodal model in Azure AI Foundry that accepts both text and image prompts, showing how to feed images into an LLM to get recipe suggestions based on fridge contents.

Previous Next
Previous Module The Azure Speech Foundry Tools
This Module Vision-Capable Multimodal Models
Computer Vision: A Solved Problem
Computer Vision: A Solved Problem
Computer Vision Applications and Types
Computer Vision Applications and Types
Using Vision-Capable Multimodal Models
Using Vision-Capable Multimodal Models
Comparing APIs for Image-Based Prompts
Comparing APIs for Image-Based Prompts
Next Module Image Generation Models