Video Production with Generative AI

There are many kinds of Generative AI (GenAI) models, from audio to text generation models. However, video generation models (VGMs) are foundational for video production and are gaining importance as their expressiveness increases. VGMs differ from other GenAI models in that VGM users must have domain-specific knowledge to leverage VGMs to express their artistic vision optimally. Specifically, it can be demonstrated that VGM users must know the basics of the visual language of cinematography to translate their creative vision into quality output correctly. Prompt engineering is used to craft VGM output into something useful and aesthetically viable. Using prompt engineering, it is possible to ask a VGM to instantiate the basic elements of cinematography, such as camera placement, camera movement, shot composition, shot size, focus/depth of field, and lighting. Besides VGMs, other GenAI models are useful for pre-and post-production tasks.