The 7-part prompt structure for text-to-video
A fill-in template that gives any video model the seven things it needs: subject, action, setting, camera, light, style and sound. Fewer vague words, fewer wasted generations.
SUBJECT: {who or what, with 2-3 concrete visual details} ACTION: {one clear action, present tense, no more than one beat} SETTING: {place, time of day, weather, era} CAMERA: {shot size} · {angle} · {movement: static / slow dolly in / handheld follow / orbit} LENS & LIGHT: {focal length feel, e.g. 35mm wide / 85mm portrait} · {light: golden hour / overcast soft / neon practicals / single window} STYLE: {film stock or look: 16mm documentary / clean commercial / anime / claymation} · {color palette} SOUND: {ambient sound} · {no music / music mood} DURATION: {5-8 s}. No on-screen text, no logos, no subtitles.
Paste into the video model as one paragraph; remove the labels once you are happy with the content.
Steps
- Fill every line. A blank line is where the model improvises, and it improvises blandly.
- Keep ACTION to one beat. 'Walks to the window and looks out' is one shot; 'walks, sits, drinks coffee, laughs' is four.
- Paste the filled block as one paragraph into Veo, Sora, Kling or Runway. Most models read prose better than labels, so remove the labels once you are happy with the content.
- Generate 2-4 takes with the same prompt before changing anything; variance between takes tells you what the model is unsure about.
Example
A woman in a yellow raincoat with wet hair holds a paper cup of coffee. She turns slowly toward the camera and smiles. A Lisbon tram stop at dawn, light rain, wet cobblestones reflecting shop signs. Medium close-up, eye level, slow dolly in. 50mm look, soft overcast light with warm practicals from a bakery window. 16mm documentary feel, muted teal and amber palette, light film grain. Ambient rain and distant tram bell, no music. 6 seconds. No on-screen text, no logos.
Tips
- Negative instructions ('no text, no logos, no extra people') belong at the end; most models honour them better there.
- Name a shot size and a movement every time. 'Cinematic' alone gets you a random one.
- Google's Veo prompt guide lists the same elements (subject, context, action, style, camera motion, composition, ambiance); this template is ordered for the way people actually think about a shot.
| works with | Veo: Google text-to-video / image-to-video prompts. · Sora: OpenAI video generation prompts. · Kling: Kling text/image-to-video prompts. · Runway: Runway Gen prompts and camera controls. · Any LLM: Model-agnostic: Gemini, Mistral, a local model. |
| cost | Free. The video or image model you paste it into has its own pricing. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| source | Google Veo prompt guide (element list) |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-01 |
| for agents | video-prompt-structure-seven-parts.md |
Related
Camera movement vocabulary that video models understand
The 14 camera moves that generation models respond to reliably, with the phrasing that works and the phrasing that produces a wobbling mess.
Hook for a generated video: what must be in frame 1 when a model draws it
The first-frame rules for Veo, Kling and Runway: start mid-action, name the motion already happening, keep text out of the generation, and generate the hook shot as its own 4-second prompt first.
Image-to-video: generate the first frame, then animate it
Make a still with an image model first, fix the composition there, and only then ask the video model to animate it. Cheaper iterations and the look you chose, not the one the video model guessed.
Keep the same character across clips: the reference sheet prompt
A character description block you reuse verbatim in every prompt, plus a generated reference sheet, so a face, outfit and build stay the same from shot to shot.
Product hero shot: a 5-second generated clip for an ad or a listing
Prompt for a clean product shot with one motion and one light change, the kind that sits at the top of a listing or opens a 15-second ad.
Anime style: 2D cel look, limited animation, clean line weight
A filled 7-part prompt for a hand-drawn anime shot: flat cel shading, animation on twos, a held painted background, and the three things the style breaks in current video models.