Shotcraft
Prompt craft

Video prompts

Duration, shot size, camera movement and the audio a clip describes for itself.

18 aspects, in the order they work best in a prompt.

Take video prompts with youOne dense page to pin up, or a deck with one section per page. Both built from this page's own content.

Cheatsheet · 1 pageDeck · 23 pages

The order

Working down this list is also the recommended order inside the prompt.

Duration

How long the clip runs.

Models hold a shot for a fixed span. Naming the length stops a model compressing a three beat idea into one, or padding a single beat with drift.

Phrases that work

Model-bound

Model-bound: Seedance 2.0 4-15s (12s is valid); Kling 3.0 and Kling 3.0 Turbo 3-15s; Grok Video 1.5 2-15s; Veo 3.1 accepts only 4, 6 or 8; Marketing Studio integer ≥ 4; explainer blocks are fixed 10-second units with N = duration_minutes × 6; sprite animation is fixed at 4 s; cover reveal ~5s; scroll-scrub single-shot asks for the longest single take the model supports (~15s).

Aspect ratio

Frame shape.

Decides whether the subject can breathe. A vertical crop of a wide composition loses the sides, so the ratio has to be chosen before the composition is described.

Phrases that work

Model-bound

Meanings given in prompt-engineering.md: 16:9 landscape, cinematic; 9:16 vertical, social; 1:1 square, profile / icon. Veo 3.1 accepts only 16:9 or 9:16. For sprite work the ratio must be read off the key-pose file and passed explicitly on every call, omitting it falls back to the tool default and crops the subject.

Medium and style

What the output is pretending to be.

Being specific beats being evocative.

Phrases that work

Model-bound

Write the render style, palette, line character and finish once, then repeat it byte-identically. scroll-scrub.md calls the equivalent a 'World grammar': one byte-identical style preamble, perspective, palette, light direction, surface finish and background behavior across all scene prompts.

Shot size

How much of the subject fills the frame.

The most reliable lever there is. Naming it removes the model's habit of defaulting to a mid shot for everything.

Phrases that work

Model-bound

The video fills the viewport and crops the edges, so essential subjects must stay away from the far left/right edges.

Camera angle

Where the camera sits relative to the subject.

Changes who has power in the frame. Low angle makes a product monumental, overhead flattens it into a diagram.

Phrases that work

Camera movement

How the camera travels during the shot.

If you do not name it the model invents drift, and drift reads as an accident.

Phrases that work

Model-bound

For image-to-video the movement IS the prompt; for scrubbable footage a single unbroken move is mandatory and cuts are a defect. For sprite sheets the camera must be explicitly locked or frames become unusable.

Lens and focal length

Perspective and compression.

A focal length is a shorthand a model understands: 85mm flatters a face, 24mm bends a room outward, macro turns a surface into a landscape.

Phrases that work

Depth of field

What is sharp and what falls away.

Separates subject from background without changing the composition.

Phrases that work

Lighting

Where the light comes from and how hard it is.

Sets mood more cheaply than any other choice. Naming a setup also stops the flat, evenly lit look models fall back on.

Phrases that work

Colour and grade

The palette and contrast of the finished image.

Carries brand more than any other single element, and is easy to get consistent across a set of clips by reusing the same phrase.

Phrases that work

Model-bound

scroll-scrub.md forbids mixing models mid-chain because "their grain, color, and motion signatures create a visible seam even when position matches".

Subject motion

What moves inside the frame, and how fast.

Distinct from camera movement and frequently confused with it. Say what the subject does, or the model will hold it still and move the camera instead.

Phrases that work

Model-bound

"Exactly one action per video; any second verb in the prompt is a defect" (game-2d-animation.md).

Mood

The feeling the clip should leave.

A single adjective steers dozens of small decisions the model would otherwise make at random. Cheap to add, and it makes a set of clips feel related.

Phrases that work

Audio bed

The sound that plays under the picture.

Naming instruments and what must not be heard is more reliable than naming a genre.

Phrases that work

Model-bound

In the explainer pipeline narration is a separate audio job; clip audio must never contain speech.

Pacing and cuts

How the time is divided.

Without it a model gives you one unbroken drift. Naming beats is what turns a clip into a sequence.

Phrases that work

Model-bound

Matters whenever every frame may be held as a still (scroll-scrub), exposure pumping shimmers and heavy blur smears.

Entrance motion should be matched to the typography of the text being revealed.

Resolution / quality tier

Seedance 2.5 caps at 720p so 1080p/4K work stays on Seedance 2.0; Grok Video 1.5 only 480p or 720p; Marketing Studio video 480p or 720p.

Treat it as practice worth copying, not as a count.

First/last frame anchoring

scroll-scrub.md warns that passing a storyboard as a start frame makes the page open on a static image; pass it in the generic reference role instead.

Treat it as practice worth copying, not as a count.

Phrases that work

Ad format / mode (branded video)

Hook text is prepended to the user's prompt and does not replace it; production prompt documentation notes "Hooks (the prompt on --prompt) matter more than mode for performance."

Treat it as practice worth copying, not as a count.

Phrases that work

Edit instruction (video editing workflows)

draw_to_video takes a source video, an edited/sketched frame, the timestamp for that frame and a short edit instruction.

Treat it as practice worth copying, not as a count.

Prompt structure

The shapes these prompts actually take, rather than a description of one. For a complete worked set built on one of them, see hand-drawn VFX fusion.

Two dominant shapes.

  1. The explainer block

    a labelled five-line form in fixed order: `Block N` / `STYLE REFERENCE:` / `SCENE:` / `MOTION:` / `AUDIO:` / `NEGATIVE:`, the STYLE REFERENCE and NEGATIVE lines are pasted byte-identically into every block, only SCENE and MOTION change, and each block holds exactly one clear action

  2. The image-to-video single paragraph

    where the start image already carries the subject so the prompt is motion only, "Don't redescribe the static frame, model already has it", optionally followed by a mandatory negative block in three fixed parts: camera lock, prop and action inertia, facing lock. Longer reveal prompts run beat by beat in time order: start state and context motion to text/element entrance to settle, closing with an anchor sentence that ties the last frame to the supplied end frame.

    Footage-level constraints (one continuous move, centre-safe hero, survivable background, locked exposure, resolving ends) are restated in the prompt rather than left to the model

Negatives

Grouped by the failure they address. Keep the list short: on a model with no separate negative field, every one of these is just another word competing for attention.

Text and branding

Anatomy and faces

Content and safety

Audio

Other

Take it with you

Take video prompts with youThe same reference, as a printable sheet or a presentation.

Cheatsheet · 1 pageDeck · 23 pages

Back to prompt craft · Cinematic language · Downloads