Skip to main content

Teaching a Child to Cook

A father lets go of the spoon, the child stirs too fast, and both freeze.

Story & dialogueImage to videoNeeds one reference image311 credits

Fills the prompt and every setting below into the Seedance 2.5 form. Nothing is submitted until you press generate.

The prompt

Keep both people, their clothing and the kitchen exactly as in the reference image. A father steadies a child's hands around a wooden spoon, then lets go; the child stirs once, too fast, sauce flicks onto the counter, and both freeze and look at each other. The camera sits low at counter height, static with a tiny drift right. Warm late-afternoon light from a side window, steam rising. Flour dust, dented pan, tea towel. Simmering pot and a spoon tapped on enamel.

Settings this prompt was written for

Settings this prompt was written for
FieldValue
ModeImage to video
Duration8 seconds
Resolution720p
Aspect ratioadaptive
AudioAudio on
Credits311

They are the real price of that exact configuration — computed with the same pricing engine the API charges with, at the resolution, duration and audio setting shown on the card. Change any of those in the generator and the price updates with it.

Why it works

The beat is a small failure followed by shared laughter, and both halves are physical: a hand released, one stir too fast, a shared freeze. That is a performance a model can hold because nothing depends on facial nuance. A nearly static camera at counter height keeps attention on the hands, and image-to-video is used so the two characters and the kitchen stay consistent across the whole take.

What to put in the reference image

Upload a two-character still with an adult and a child together at a counter or table, both at similar distance from camera and lit by window light. Avoid images where the child's face is turned away or hidden, and avoid stock-photo gloss — the model keeps that polish and it flattens the moment.

parent and child cooking promptteaching moment video promptwarm family scene ai videoimage to video two characters

Prompts stay in English on every language of this site: that is the language the model was trained on, and translating a prompt changes what it renders. The page around it is translated.