Generative AI Beyond Text
How AI generates images, audio, and video with diffusion models, plus controllability, evaluation, and real risks.
intermediate · 45 minutes
Text is only the beginning. This course explores how modern AI systems synthesize **images, audio, music, and video**, focusing on the diffusion models that dominate the field today. You will build intuition for how denoising works, how text steers generation, how to control outputs, and how to evaluate results that have no single right answer. We also confront the serious risks: deepfakes, copyright, consent, and provenance.
What you'll learn
- The Generative Media Landscape
- How Diffusion Models Work
- Text-to-Image in Depth
- Controlling and Editing Generations
- Audio, Video, 3D, and Any-to-Any
- Evaluation, Risks, and Responsibility