Generative video creates entirely new video from text prompts or static images, using diffusion or transformer models like Sora, Veo, and Runway. No source footage of a real person is required; the model fabricates everything from scene to subject.

Content advisory: this technique is used to produce AI-generated child sexual abuse material (CSAM), including sexual imagery of real children and fully synthetic depictions. Creating, possessing, or sharing this material is illegal. Report suspected CSAM to the NCMEC CyberTipline at report.cybertip.org.

• A text prompt or seed image is fed to a generative model
• The model outputs video frames with consistent motion, lighting, and physics
• Output quality has scaled rapidly, with photorealistic generation now available in consumer products

• Fabricated news footage of events that never occurred
• Synthetic influencer accounts producing content at scale
• Fake product demos, testimonials, or before-and-after content used in fraud
• Manufactured evidence videos for legal disputes or insurance claims
• Mass-produced disinformation video where impersonating a real person isn’t necessary