All guides

Text to video

Describe a scene in the prompt and the AI generates a short video. Choose video-specific options like resolution and length.

Text to video creates a short video from a description. Since motion and time are added, it helps to describe not just the subject but how things move.

Steps

  1. Open the Video screen from the sidebar.
  2. Describe the scene you want. Beyond the subject, adding motion and camera direction makes for a richer result (e.g. "a camera slowly pushing in," "hair blowing in the wind").
  3. Choose a model, aspect ratio, resolution, and length.
  4. (Optional) Set options like fixed camera or audio generation.
  5. Press Generate to run.

Video options

  • The available resolutions and lengths depend on the model. Higher resolution and longer length use more credits.
  • Fixed camera keeps the camera still while only the subject moves — useful when you need a steady frame, like a product shot.
  • Depending on the model, you can go up to 4K (Ultra HD). Pick 4K for big screens or post-production, or start at a lower resolution for quick drafts.

Good to know

  • Video generation uses more credits than images (varies by model and options).
  • Generation takes time, and progress is shown. When it's done, you can play the result right away.
  • If a generation goes against the content policy, it's declined and the credits are refunded automatically.