Wurt.app

How to prompt AI video

Video models need physics, not poetry. Write who moves, what contacts what, and in what order—especially when starting from a photo.

Practice in Vidwurt

What you get

A→B sequences

Start pose → action steps → short settle within a few seconds.

Image grounding

Name the subject already in frame; do not invent a new person.

Camera with purpose

One motivated move beats three random angles.

Social pacing

Hooks early for Reels, Shorts, and TikTok.

Details

Text-to-video and image-to-video share the same grammar: subjects, body mechanics, timing. Vague lines like “cinematic vibe” waste the model’s attention.

Minimal recipe

  1. Subject (who)
  2. Action steps (what, with which body parts)
  3. Intensity (slow / sharp / looping)
  4. Optional camera (push-in, track, hold)

Deep-dive stills first: prompt engineering guide. Then animate: image to video.

Open Wurt.app and make something

Browser-native image and video generation with prompt fidelity, free starting credits, and no Discord bot workflow.

Practice in Vidwurt