A good AI video prompt names one subject, one camera move, the light, and the sound. Below are three full examples you can copy, one per model. Each is from our own prompt library, and you can reuse them under CC-BY-4.0.
Example 1: Seedance (establishing shot)
Vertical establishing shot of a glass skyscraper at night in heavy rain. Only the top floor is lit, warm gold, while the rest of the tower is dark. The camera starts low on the wet street, where taxi lights smear across the puddles, then tilts up slowly along the glass facade to the penthouse windows, where a single silhouette in a suit stands looking down. Cool blue city light against a warm interior glow, light haze, glossy romance-drama look. Sound: <steady rain on pavement>, <distant traffic>, (low, tense piano). No subtitles, no on-screen text, no logos.
Settings: Seedance 2.0 Fast, text-to-video, 9:16, 6s, 720p, audio on.
Why it works: there is one camera move, a slow tilt up. Angle brackets mark sound effects and parentheses mark music, so the two don't blur together. The last line stops the model from adding text.
Example 2: Kling (close-up)
Extreme close-up, 9:16 vertical. A 32-year-old CEO with a sharp jaw, slicked-back black hair, a charcoal three-piece suit, silver cufflinks and cold dark eyes. He sits at the head of a glass boardroom table and slowly lifts his gaze from a document to look just past the camera, jaw tightening, one eyebrow rising a fraction. Night city lights blur behind him through floor-to-ceiling windows. Shallow depth of field, cool blue key light with a warm rim on his cheek, quiet tension. Audio: low air-conditioning hum, a pen clicking once. No dialogue.
Negative prompt: smiling, talking, extra people, text, subtitles, warped hands, face morphing, blur.
Settings: Kling 3.0 Pro (1080p), text-to-video, 9:16, 5s, audio on.
Why it works: the order is subject, movement, scene, then camera and light. It asks for one small change in his face. "No dialogue" keeps the audio from inventing a line.
Example 3: Veo (establishing shot with sound)
Establishing shot, vertical frame. A slow crane up the mirrored face of a black glass skyscraper at night, rain streaking down the windows, until the camera settles on the single lit floor at the very top: a glass penthouse office where a lone silhouette in a three-piece suit stands at the window looking down. The city below glows sodium orange and cold blue. Cinematic, high contrast, glossy wet surfaces, light haze. SFX: steady rain against glass, a distant siren. Ambient noise: wind whistling around the edge of the tower.
Negative prompt: subtitles, on-screen text, logos, daylight.
Settings: 9:16, 6s, 720p, audio on, Veo 3.1 Fast.
Why it works: Veo follows the first camera move you name, so the crane goes first. The labeled SFX and ambient lines give you a ready sound bed.
What the three have in common
| Part | Seedance | Kling | Veo |
|---|---|---|---|
| Shot size first | Establishing | Extreme close-up | Establishing |
| Camera moves | 1 (tilt up) | 0 (only the face moves) | 1 (crane up) |
| Sound written in | Yes, SFX and music | Yes, ambience | Yes, SFX and ambience |
| Negative list | In the prompt | Separate field | Separate field |
The takeaway: keep to one move per shot, and write the sound in yourself.
Make your own
Swap the subject and the place, and keep the structure. If you want to fill a form instead, use the AI video prompt generator. For more prompts by genre and shot, browse Seedance, Kling and Veo.
To plan the shots first, read the storyboard format. For camera words that work in 9:16, see vertical framing and shot language.