Gemini Pro Vision supports multimodal prompts. You can include text, images, and video in your prompt requests and get text or code responses. This spotlight lab focuses on demonstrates a variety of multimodal use cases that Gemini can be used for. This list includes detecting objects in photos, understanding charts and diagrams, comparing images, generating a video description, extracting highlights/messaging of a video and other examples you will explore in a hands-on lab environment.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.