fairytale video Make an ad

All guides · · Updated

How to write an AI video ad prompt (with template)

Most AI video ads go wrong at the prompt, not the model. "A woman using our moisturiser in a bathroom, UGC style" leaves the model to decide everything: when the product appears, what she does with it, where the camera goes and what she says. The result looks fine for two seconds and then drifts.

A prompt that works reads less like a description and more like a shot list. Here is the structure we use, why each part is there, and a template you can copy.

The parts of a good AI video ad prompt

  1. Reference binding. Say which attached image is which: the creator, the product, the scene. Then refer to them by those names throughout, so the model never has to guess.
  2. Goal. One sentence on what the ad has to do.
  3. Continuity. What must not change: the face, the outfit, the product's shape and label, the setting.
  4. Timed stages. The ad split into a few stretches of time, each with the same six fields: initial state, primary action, camera, end state, transition and exact dialogue.
  5. Visual style. Lighting, palette, composition, grain, lens, ambience and location.
  6. Camera and performance. Handheld or locked off, the creator's energy, when they look into the lens.
  7. Audio. Voice, room sound, music or none.
  8. Exclusions. What must not appear.
  9. Maintain consistency. Hold the creator, product and scene to their bound references.

Why timed stages beat a paragraph

Models follow "0–3 s, 3–7 s, 7–10 s" far more reliably than a paragraph where everything happens at once. Writing an end state for every stage, and making it the next stage's initial state, keeps the action continuous instead of jumping. For a 10-second ad, three stages is usually right: a hook, the demonstration, and a closing beat with the product clearly in view.

Here's one continuous action in a finished five-second clip: the croissant comes up to the lens in the first moment and stays there while he talks, so nothing jumps.

The flakiest in Paris. An AI-generated UGC ad: a creator holds up a croissant at a Paris café terrace.

Write the dialogue exactly

Put the spoken line in its timed stage and ask for it to be said once, as written, with nothing added. Relaxed speech runs at roughly two to three words a second, so ten seconds holds about 20 words at most. Leave room for the action too: a line of 8 to 15 words is easier to land. Never leave the dialogue to the model; it will happily invent claims you can't make.

The template

Replace the placeholders with your confirmed facts and direction. This example uses seven images and one optional voice sample; map the binding to the attachments you actually supply. Keep the original product and scene photos alongside the generated sheets, and leave unknown sizes and unseen views unknown. In the studio this mapping is built for you when you generate a video.

[REFERENCE BINDING]
@creator = @Image 1, the front portrait and face authority,
and @Image 2, the character sheet: face close-up and full-length outfit.
@product = @Image 3, the original hero photo and silhouette authority,
@Image 4, the product sheet, and @Image 5, the original label close-up.
@scene = @Image 6, the original scene photo and layout authority,
and @Image 7, the generated scene reference.
@Audio 1 = the approved voice sample, if the ad has dialogue.

GOAL
A 10-second vertical (9:16) UGC-style ad in which @creator
<does one thing> with @product in @scene.

CONTINUITY
@creator keeps the same face, hair and outfit throughout.
@product keeps its supplied shape, colour and exact label text.
Use only confirmed dimensions; unseen views remain unknown.
The setting stays @scene.

STAGE 1 (0–3 s)
Initial state: <where everything is in the first frame>
Primary action: <the hook>
Camera: <framing and movement>
End state: <where everything is at 3 s>
Transition: <how it flows into stage 2>
Dialogue: none

STAGE 2 (3–7 s)
Initial state: <same as stage 1's end state>
Primary action: <the demonstration>
Camera: <...>
End state: <...>
Transition: <...>
Dialogue: @creator says, in <language>: {<the exact approved line>}

STAGE 3 (7–10 s)
Initial state: <...>
Primary action: <the closing beat, product clearly in view>
Camera: <...>
End state: <the last frame>
Transition: none, the ad ends
Dialogue: none

VISUAL STYLE
Lighting: <...>
Palette: <...>
Composition: <...>
Grain: <...>
Lens: <...>
Ambience: <...>
Location: <...>

CAMERA AND PERFORMANCE
<handheld or steady, energy, eye contact>

AUDIO
Follow @Audio 1's voice style when supplied, without repeating
the sample's own words. Say only the approved stage dialogue.
<room sound and sound effects>
No background music unless specifically approved.

EXCLUSIONS
No on-screen text or subtitles. No logos other than the product's.
No other products. No other people.

MAINTAIN CONSISTENCY
Keep @creator, @product and @scene exactly as in their references.

A filled-in example

A fictional stainless-steel travel mug, filmed in a parked car. The lid and hinge must be visible in the supplied references:

STAGE 1 (0–3 s)
Initial state: @creator sits in the driver's seat, @product in the
cup holder, morning light through the windscreen.
Primary action: she lifts @product out, keeping the logo to the lens.
Camera: handheld selfie angle at arm's length, slight sway.
End state: @product held at chest height, logo to camera.
Transition: at 3s, continue in the same shot into stage 2.
Dialogue: none

STAGE 2 (3–7 s)
Initial state: @product held at chest height, logo to camera.
Primary action: she opens the lid with her thumb.
Camera: same selfie angle, product clearly visible.
End state: lid open, @product held beside her face.
Transition: at 7s, continue in the same shot into stage 3.
Dialogue: none

STAGE 3 (7–10 s)
Initial state: lid open, @product beside her face.
Primary action: she talks to the lens, holding @product steady.
Camera: same selfie angle.
End state: product and face clearly in view.
Transition: none, the ad ends at 10s.
Dialogue: @creator says, in English: {Made for coffee on the go.}

The line describes this fictional product's intended use, rather than inventing a customer's experience or an untested heat-retention claim. Adapt it only to facts you can support. The plan covers the full ten seconds and gives the speech its own closing beat.

Common mistakes

Let the studio write the plan

fairytale video builds prompts in exactly this shape. You describe the ad in a sentence or two; for each video the studio writes the concept and the timed plan, binds your creator, product and scene references to the images it attaches, and only sends it once every stage is complete. You can open any video to read the concept, the timed plan and the exact prompt and references it was made from. See AI UGC ads for the whole workflow and turning a product photo into a video ad for getting the product right.