This workshop on “Multimodal Generative AI: Concepts, Models, and Hands-On Implementation” aims to introduce participants to the principles, models, and real-world applications of generative artificial intelligence that integrate text, image, and audio data. The workshop combines expert lectures with live hands-on sessions to help participants understand how modern multimodal AI systems are designed and implemented using popular tools and pre-trained models. Participants will gain practical exposure to building simple multimodal generative pipelines while also learning about emerging applications, ethical considerations, and future research directions. The program is designed for faculty, students, researchers, and professionals seeking both conceptual clarity and practical skills in multimodal generative AI.