Text-to-Video Model

A text-to-video model is a category of generative artificial intelligence system that takes a natural-language description as input and produces a video relevant to that text. Development of high-quality, text-conditioned video generation accelerated during the 2020s, driven largely by video diffusion models that synchronize generated frames with the text input while keeping the sequence visually consistent. Early systems appeared in 2022, including CogVideo, described as the earliest text-to-video model at 9.4 billion parameters, alongside Meta's Make-A-Video and Google's Imagen Video; by 2023, Runway's Gen-1 and Gen-2 brought the technology to a commercial web interface, followed by further systems such as OpenAI's Sora and Google's Veo. This description is adapted from Wikipedia contributors under CC BY-SA 4.0; changes were made. https://creativecommons.org/licenses/by-sa/4.0/