EP05: LLMs in Computer Vision
Hosted by Microsoft Reactor London
Details
In this session, you'll discover how LLMs (Large Language Models) have revolutionized the Azure AI Vision service, unlocking unprecedented scenarios, including the remarkable world of image generation.
What You'll Learn:
The Power of LLMs in Computer Vision: Explore how Large Language Models are transforming the landscape of computer vision, pushing the boundaries of accuracy and capability in tasks such as image classification, object detection, and image captioning.
Enhancements to Azure AI Vision: Dive deep into the Microsoft Florence foundational model and see how it has elevated the Azure
AI Vision service. Learn about new scenarios it unlocks and improvements to existing capabilities.
Image Generation with DALL·E2: Venture into the fascinating world of image generation tasks enabled by the DALL·E2 model, available through Azure OpenAI service. Witness the creative potential of this cutting-edge technology.
Prepare to be inspired as we showcase practical examples of embedding these capabilities into your solutions via REST APIs. Join us on this visual journey into the future of Computer Vision, where words are just the beginning.
Check out our Microsoft Learn collection of curated free training to advance your skills: https://aka.ms/YourAI_Idea
