Introduction to Multimodal Prompting for Generative AI
38mIntermediate2024-06-24
Authors
Ronnie Sheer
Software Developer and Instructor
Course details
In the last year, multimodality has brought about new capabilities to AI systems. In this course, software developer and instructor Ronnie Sheer offers you an understanding of what multimodality is and when and why it may be leveraged for business needs. Dive into a "tools approach" as Ronnie teaches you multimodality using two popular LLMs on the market: GPT-4 and Google Gemini. Plus, explore an additional chapter dedicated to prompting with and for music. Solidify all that you learn in the course, using opportunities within the course for hands-on practice.
Skills covered
GPTGeminiNeural Networks and Deep LearningChatGPTOpenAIAI Productivity ToolsGenerative AIArtificial Intelligence FoundationsGoogleArtificial Intelligence (AI)Business Software and ToolsOne-Off
Concepts
0. Introduction
- 01 - GenAI with multimodal prompts
1. Multimodality
- 02 - What is multimodality
- 03 - Visual modality
- 04 - Textual and auditory modality
2. GPT-4
- 05 - GPT-4 and 4o
- 06 - Text to image in GPT-4
- 07 - GPT-4 API with various input types
- 08 - Challenge - Drawing to code
- 09 - Solution - Drawing to code
3. Gemini
- 10 - What is Gemini
- 11 - Images in Gemini
- 12 - Gemini video inputs
- 13 - Challenge - Video narration
- 14 - Solution - Video narration
4. Auditory Modalities
- 15 - Audio in generative AI
- 16 - Prompt and audio
- 17 - Generating music
- 18 - Challenge - Soundtrack creation
- 19 - Solution - Soundtrack creation
Conclusion
- 20 - Next steps
Related courses
- Multimodal AI Essentials: Merging Text, Image, and Audio for Next-Generation AI Applications
- Google Gemini for Developers (2024)
- Azure AI for Developers: AI Design Foundations
- Oracle Cloud Infrastructure Generative AI Professional Cert Prep
- Complete Guide to Evaluating Large Language Models (LLMs)
- Prompt Engineering with Gemini (2024)
- Oracle Cloud Infrastructure Generative AI Professional
- Introduction to SQLite
Related learn paths
- Getting Started with Prompt Engineering
- Understanding Generative AI for Tech Leaders
- Develop Your AI Skills with Google Gemini and Google Cloud Platform
- A Developer's Guide to Google Gemini
- Building Generative AI Skills for Web Developers
- Explore AI for Data Engineering
- Master Retrieval-Augmented Generation (RAG)
- Build AI Products Using Azure AI Services in Your Development Lifecycle