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
Related terms
Text-to-Image
Generating original images from a written description, as tools like DALL-E, Midjourney, and Stable Diffusion do.
Diffusion Model
A type of generative model, common in image tools, that creates content by starting from noise and gradually refining it.
Generative AI
AI that creates new content such as text, images, audio, or code, rather than just classifying or scoring existing data.
Deepfake
Synthetic media, usually video or audio, that convincingly fakes a real person saying or doing something they never did.