Effectively teaching programming concepts remains a persistent challenge, as conventional approaches often struggle to make abstract ideas accessible and engaging. Analogies provide a powerful means to simplify these concepts, and when augmented with multimodal resources, such as video animations, can significantly enhance learner engagement and comprehension. This research leverages Large Language Models (LLMs) and a structured animation workflow to automate the generation of analogy-driven explanations and visualizations for programming topics. Preliminary findings indicate that while LLMs can produce creative and pedagogically relevant analogies, careful decomposition and validation steps are critical for ensuring clarity, correctness, and learning alignment. We will conduct controlled evaluations to compare the effectiveness of AI-generated analogy-driven materials against traditional instructional methods. We also explore domain-specific personalization, adapting analogies to the learner’s familiar domains and background.