Push-in, pan, tracking shot: three camera moves in one AI video

The camera words that video models actually understand — push-in, dolly, pan, handheld, establishing — with prompt templates and the mistakes that break a shot.

How this video was made

Generated in Actoria from a three-paragraph script: each paragraph became a five-second scene, the synthetic actors were created once and kept their faces in every shot, and the scenes were stitched into one film.

Scenes

1. 0s Mia stands still in a sunlit loft, looking straight into the camera. Slow push-in from a medium shot to a close-up on her face.
2. 5s A crowded night market with lanterns and steam. The camera pans slowly from left to right and finds Mia at a food stall, turning toward us.
3. 10s Mia runs along an empty beach at golden hour, olive green jacket flying. Tracking shot alongside her, keeping pace.