Video generation
Video generation is the synthesis or transformation of moving-image content by a generative computational model from specified inputs.
Generative AI in Action
A video generator is a generative system that produces video content from user-specified inputs such as prompts.
- How it is used
- Uses prompt-driven video generation for personalized marketing, customer support, entertainment, education, and synthetic-data workflows.
- How deep it goes
- Explains prompt-to-video capabilities and enterprise applications, but stops short of model architecture or mathematical detail.
- Examples
- Shows Sora, Runway Gen-2, Pika, Hotshot, Stable Video Diffusion, Wochit, multilingual receptionists, and virtual sports anchors.
- What you can do after
- Apply it via prompt-based generators to create short clips, personalized ads, multilingual reception videos, or sports coverage.
Read how Generative AI in Action explains video generation →
Introduction to Generative AI, Second Edition
Generative video is the synthesis or transformation of video content using generative machine-learning models.
- How it is used
- Positions video generation as a creative-production tool for filmmaking, animation, storytelling, and visual experimentation.
- How deep it goes
- Explains capabilities, creative uses, and societal questions at overview level without implementation details.
- Examples
- Uses Runway, Sora, AI-generated animation, and Washed Out’s Sora-produced music video as concrete examples.
- What you can do after
- Apply it via Runway or Sora to generate or edit video and evaluate related authorship and labor questions.
Read how Introduction to Generative AI, Second Edition explains video generation →
Related concepts
- image-to-video synthesisused by · Image-to-video synthesis is the generation of video content from a source image by modeling visual features and motion.
- text-to-video generationused by · Text-to-video generation is the computational creation or modification of video content from textual descriptions or prompts.
- video-to-video synthesisused by · Video-to-video synthesis is the generation of a new video from a source video while preserving aspects of its underlying structure.
- Soraimplemented by · Sora is OpenAI’s text-to-video generative model for producing videos from textual descriptions.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.