This book provides a rigorous, practice-led introduction to generative AI for screen-based media, combining foundational theory with applied workflows grounded in professional production environments. Written by an experienced visual effects supervisor and educator, the book offers an authoritative framework for understanding and responsibly adopting AI technologies within contemporary visual effects pipelines. It is structured around six core domains: computer-science fundamentals of artificial intelligence and machine learning, hardware and performance considerations, ethics and legal responsibilities, practical use of the open-source ComfyUI framework, professional integration with NUKE, and the broader ecosystem of community-driven tools and resources. Key concepts, including neural networks, diffusion models, latent space, ControlNets, and LoRAs, are explained from first principles and contextualised for creative practice. Particular attention is given to authorship, copyright, data provenance, and ethical use, ensuring readers can critically assess both the capabilities and limitations of generative systems. Intended for academic libraries, educators, researchers, and industry professionals, this book functions as both a teaching resource and a long-term reference. It supports curricula in visual effects, film production, digital media, and creative technologies, while also serving practitioners seeking a structured, open-source-oriented approach to integrating generative AI into professional workflows with technical clarity and ethical awareness.
