Lesson 59 · 2 min
AI that makes video
Video generators turn a text description or a photo into a short moving clip, and the results are now realistic enough to fool people.
Most video generators work like image generators stretched over time. They start from visual noise and clean it up step by step, guided by your prompt, while keeping each frame consistent with the ones around it.
You can describe a scene, animate a still photo, or extend a clip. Many tools also add sound. Clips are usually short, and longer stories are built by joining pieces.
Flaws still appear. Watch for hands and text that shift, objects that melt into each other, physics that feels slightly wrong, and faces that change between shots.
Because fakes are getting harder to spot, some tools add labels or hidden credentials that record how a file was made. Treat shocking clips with care, look for the original source, and label your own AI videos.
Do it now
Play detective
- 1. Find a short clip online that is labelled as AI-made.
- 2. Watch it three times: once for hands and faces, once for text and signs, once for how things move.
- 3. Write down the clues you found, so you know what to look for next time.
Quick check
Keep going
Next →One model, many sensesWords from this lesson
- Generative AI
- AI that produces new text, images, audio, video or code, rather than only sorting or scoring existing things.
- Diffusion model
- A type of AI that makes images or video by starting from random noise and cleaning it up step by step.
- Deepfake
- A fake video, photo or audio clip made with AI to show a real person saying or doing something they never did.