This introductory, hands-on course provides a practical overview of AI image generation, using Google Gemini as the core creative tool. Participants learn how to demystify Generative AI, structure effective prompts, and guide visual outcomes from scratch and using product image references. The course bridges the gap between text-based ideation and professional commercial applications, focusing on hands-on experimentation, interactive prompting, and responsible use. While Gemini is the main sandbox used, the visual structuring and prompting principles covered can be applied across multiple AI platforms.
Topics Covered:
- Introduction to LLMs, Generative AI, and the current AI tool landscape
- The anatomy of a powerful prompt (detailing, setting, lighting, and camera angles)
- Exploring Gemini’s interface, image generation limits, and workspace basics
- Generating characters, scenes, and concepts from scratch
- Commercial and advertising visual creation using image references and product uploads
- Responsible AI use, transparency, copyright considerations, and ethics
- Introduction to advanced workflows, node-based systems, and continued learning paths
Tools:
- Google Gemini (Core AI generation interface)
- Google Drive (For accessing shared product photography assets during the lab)
