wowprompt

Three Diwali phone photo mistakes talking head on a Jaipur rooftop

A fifteen second vertical talking head: a young creator on a Jaipur rooftop at blue dusk counts off three mistakes people make shooting Diwali photos on a phone, holding up one finger for each, then flips her phone to show the fixed shot. Clear voice, lip sync, cool light with tiny diya points. Works with your own photo.

A young woman on a rooftop at blue dusk holding up three fingers to the camera, a row of small diyas on the parapet behind her
The output this prompt produced, unedited.
Works with or without your photo.

Optional. Attach a clear, front-facing photo to keep your own face. Without one, the prompt creates an original person.

The prompt

Logline

One creator, one take, three fixes for flat Diwali phone photos, and the proof on her screen at the end.

Subject

A young creator standing at a rooftop parapet, framed from the waist up in the centre, speaking straight to the lens.

Identity

With a photo attached: the person in the photo is the subject. Keep their face exactly as it is, with bone structure, eye shape and spacing, nose, lips, jawline, hairline, skin tone and apparent age all unchanged in every frame, and keep their own body: build, height and proportions, shoulders, arms, hands and legs, with the same skin tone on face, neck, arms and hands. Use the photo only for who the person is. Ignore its pose, expression, clothing, hairstyle, background, framing and light, and rebuild all of them exactly as described below, even when the photo shows them standing straight or dressed differently.

Shot 1, seconds 0 to 4

She holds her phone at her chest with her left hand and says: "Three reasons your Diwali photos look flat." Eyebrows raised, a direct look.

Shot 2, seconds 4 to 11

She lifts her right hand and adds one finger at each line: "Turn off the flash. Tap to lock on the flame. Step back and let the dark stay dark." Small natural nods, lips matching every word.

Shot 3, seconds 11 to 15

She flips the phone to face the lens, showing a softly lit photo of diyas, and smiles: "That is it." The screen shows only a picture, no words.

Wardrobe

A deep teal cotton silk kurta with a mandarin collar, small silver jhumkas, a thin silver ring.

Set

A Jaipur rooftop, seven small diyas along the parapet behind her, old city roofs soft in blue dusk.

Lens

35mm at f/2, eye level, locked off with very slight handheld breath.

Grade

Cool blue dusk with a soft white key from the left; the flames are tiny warm points that never warm her face. True colour, real skin with pores. Sound: her voice clear and close, faint distant crackers.

Negative prompt

airbrushed skin, plastic skin, waxy face, changed face, morphing face, face changing between frames, lip sync drift, distorted hands, extra fingers, wrong finger count, words on the phone screen, large flames, fireworks in frame, orange cast, warm wash, golden grade, logos, subtitles, watermark

Thumbnail prompt

For the cover image of this video. Paste it into an image model such as GPT Image.

Frame

A tall cover frame on a Jaipur rooftop at blue dusk. A young woman in a deep teal kurta stands in the lower half, holding up three fingers of her right hand toward the lens with raised eyebrows, her phone in her left hand. A row of small diyas with tiny flames on the parapet behind her, old city roofs soft and blue. Cool true colour, real skin. The top third is clear sky for the words.

Identity

With a photo attached: keep the face from the photo exactly as it is. Without a photo: an original Rajasthani woman of about twenty-five with wheatish skin, a high ponytail and a small mole near her left eyebrow. Do not base the face on a real person.

Text

  • "3 DIWALI PHOTO"
  • "MISTAKES"

Heavy white condensed capitals with a thin dark outline, "MISTAKES" larger and in lemon yellow, stacked in the top third, readable at small size. Nothing else is written anywhere. Spell each line exactly.

talking head videodiwali photo tipsphone photography tipscreator talking head reeldiwali reelmobile photography video

How to run this

Copy the prompt and paste it into Veo, then set the aspect ratio to 9:16. Upload your reference photo before pasting, not after: a model that has already started without it will invent a face instead of keeping yours.

The prompt is written in Markdown with each part under its own heading, which is what the copy action hands over. Change one section at a time, keeping the rest intact, so you can tell which change did the work.

Related prompts

All video