With the rapid growth of video traffic and the evolution of video formats, traditional video communication systems are encountering many challenges, such as limited data compression capacity, high energy consumption, and a narrow range of services. These challenges stem from the constraints of current systems, which rely heavily on discriminative methods for visual content reconstruction and achieve communication gains only in the information and physical domains. To address these issues, this paper introduces generative video communication, a novel paradigm that leverages generative artificial intelligence technologies to enhance video content expression. The core objective is to improve the expressive capabilities of video communication by enabling new gains in the cognitive domain (i.e., content dimension) while complementing existing frameworks. This paper presents key technical pathways for the proposed paradigm, including elastic encoding, collaborative transmission, and trustworthy evaluation, and explores its potential applications in task-oriented and immersive communication. Through this generative approach, we aim to overcome the limitations of traditional video communication systems, offering more efficient, adaptable, and immersive video services.