711
Prompt

Text-to-Video Shot Prompt (Veo, Sora, Runway, Kling)

A structured prompt template that gives AI video models the detail they need for usable, consistent clips.

1 min readupdated 2026-11-04

/ quick answer

Video models respond best to concrete descriptions. Generate one shot at a time and reuse the style line for consistency. A structured prompt template that gives AI video models the detail they need for usable, consistent clips.

A structured prompt template that gives AI video models the detail they need for usable, consistent clips. Video models respond best to concrete descriptions. Generate one shot at a time and reuse the style line for consistency. Copy the prompt below, swap the bracketed variables for your own context, and run it in any capable model.
Context
Video models respond best to concrete descriptions. Generate one shot at a time and reuse the style line for consistency.
Prompt
Shot: [subject] [doing action] in [setting].
Camera: [close-up | wide | drone], [static | slow push-in | tracking], vertical 9:16.
Lighting & mood: [golden hour, soft, moody…].
Style: [photorealistic | 3D | anime | documentary], keep the same style across all shots.
Duration: 6–8 seconds. No text, no logos, no watermarks.
Example Output
Shot: a barista pouring latte art in a small Lisbon café. Camera: close-up, slow push-in, vertical 9:16. Lighting: warm morning light…
Related Workflow

/ frequently asked

What does the Text-to-Video Shot Prompt (Veo, Sora, Runway, Kling) prompt do?

Video models respond best to concrete descriptions. Generate one shot at a time and reuse the style line for consistency.

Which AI models work with this prompt?

It is model-agnostic: it works with any capable general model. Replace the bracketed variables with your own context before running it.

How do I use this prompt?

1) Copy the prompt with the copy button. 2) Replace every bracketed variable with your real details. 3) Paste it into your AI assistant. 4) Compare the answer with the example output and ask for changes if needed.

What output should I expect?

Shot: a barista pouring latte art in a small Lisbon café. Camera: close-up, slow push-in, vertical 9:16. Lighting: warm morning light….

/ continue exploring

Related concepts

The vocabulary this page depends on.

  • →AI Video Generation

    Creating video clips from a text prompt or a reference image with a generative model, instead of filming footage.

  • →Faceless Video

    Social content where the creator never appears on camera — built from voiceover, stock or AI visuals, screen recordings and captions.

  • →AI Avatar Video

    A video where a digital presenter — a stock avatar or a clone of you — speaks a script with synced lips and gestures.

  • →Video Repurposing

    Turning one long video — podcast, webinar, stream — into many short vertical clips for TikTok, Reels and Shorts.

all dictionary →

Related workflows

Turn this into a repeatable process.

all workflows →

Related tool stacks

The tools that run it in production.

all tool stacks →

Related prompts

Reusable prompts for this job.

all prompts →

Related use cases

How people apply it, and what came out.

all use cases →

Comparisons & alternatives

Pick between the options.

all comparisons →