AI video models work differently from language models. They predict motion, not words, and assemble frames into coherent moving images. In this course, instructor Sundas Khalid outlines how these models transform text prompts into video content and the technical challenges involved. Explore the layers that power these systems, including text embeddings and latent spaces, and learn how models maintain consistency across frames. Along the way, examine three approaches developers use to build AI video content, from user-friendly tools to custom coding, and consider the ethical questions the technology raises around identity, consent, and trust. Whether you plan to build AI video models or apply them in your creative work, this course is designed to give you a grounded view of how this cutting-edge technology operates.
This course was created by Sundas Khalid. We are pleased to host this training in our library.
Learn More