Applications

Text-to-Video

Generating video clips from a text description, one of the newest and most compute-hungry frontiers of generative AI.

Text-to-video models extend image generation into motion, producing short clips from a written prompt while trying to keep objects and scenes consistent across frames. It is far harder than still images because of the added dimension of time and the heavy compute involved. Systems in this space, such as Sora, pushed the frontier and intensified debate over synthetic media and deepfakes.

Reference: Wikipedia: Text-to-Video