POV: they're finally asleep and you have six minutes

The door click. Vertical 9:16 UGC clip, 3 seconds, one continuous handheld take unless timecodes say cut.
References: @Image1 = creator reference; @Image2 = setting reference. Keep the person, wardrobe and room identical to the references.
0–2s: MS from below. Slow-motion door close, nightlight through gap.
2–3s: MCU. Sinks onto step, whispered line.
Vertical 9:16 handheld shot from a few steps down a carpeted staircase at night. A 34-year-old Ghanaian-American woman with deep brown skin, short natural coils under a mustard-print satin-lined headwrap, oversized grey cardigan over a black tank, leggings and fuzzy socks pulls a child's bedroom door almost shut in slow motion, a star nightlight glowing through the gap, then turns and sinks onto the top step, eyes wide, and whispers to the lens: "Okay. Six minutes. Go." Warm hallway lamp from below, a few toys on the steps, natural skin texture, shot on iPhone, vertical 9:16.
Dialogue (Mum of a toddler, mid 30s): "Okay. Six minutes. Go."
No subtitles. No on-screen text. No logos. Natural voice, no background music.

duration

4 s

aspect ratio

9:16

resolution

1080p (720p where the API caps it)

generate audio

true

references

@Image1: creator, @Image2: setting

first frame

creator reference

One tap from the lock screen. Vertical 9:16 UGC clip, 7 seconds, one continuous handheld take unless timecodes say cut.
References: @Image1 = creator reference; @Image2 = app screen reference; @Image3 = setting reference. Keep the person, wardrobe and room identical to the references.
0–3s: Insert. Lock-screen widget opens 6:00 session.
3–7s: MCU. Head against wall, whispered line.
Vertical 9:16 multi-shot sequence on the same carpeted staircase at night, nightlight glow above, warm hallway lamp below. Shot one: insert of the woman's hands, grey cardigan sleeves and a hair tie on her wrist, tapping a widget on her iPhone lock screen that opens a dark screen with a soft '6:00' and a gentle wave animation; she slips in one earbud. Shot two: medium close-up of the 34-year-old Ghanaian-American woman in the mustard-print headwrap leaning her head against the wall, whispering: "Six minutes, one voice, no lunchboxes." Smooth cut, natural skin texture, shot on iPhone, vertical 9:16.
Dialogue (Mum of a toddler, mid 30s): "Six minutes, one voice, no lunchboxes."
No subtitles. No on-screen text. No logos. Natural voice, no background music.

duration

7 s

aspect ratio

9:16

resolution

1080p (720p where the API caps it)

generate audio

true

references

@Image1: creator, @Image2: screen, @Image3: setting

first frame

—

Shoulders down. Vertical 9:16 UGC clip, 6 seconds, one continuous handheld take unless timecodes say cut.
References: @Image1 = creator reference; @Image2 = setting reference. Keep the person, wardrobe and room identical to the references.
0–3s: MCU slow push-in. Eyes closed, shoulders drop.
3–6s: MS. Picks up toy, walks down, line over shoulder.
Vertical 9:16 multi-shot sequence on the same staircase at night. Shot one: slow push-in on the 34-year-old Ghanaian-American woman sitting on the top step, mustard-print headwrap, oversized grey cardigan, eyes closed, as her shoulders visibly drop on a long exhale. Shot two: she opens her eyes, gets up, picks a toy off the step and walks down toward the warm hallway lamp, glancing back at the lens: "Only six minutes that are mine. I guard them." Gentle handheld, nightlight and lamp glow, natural skin texture, shot on iPhone, vertical 9:16.
Dialogue (Mum of a toddler, mid 30s): "Only six minutes that are mine. I guard them."
No subtitles. No on-screen text. No logos. Natural voice, no background music.

duration

6 s

aspect ratio

9:16

resolution

1080p (720p where the API caps it)

generate audio

true

references

@Image1: creator, @Image2: setting

first frame

—

Yours. Vertical 9:16 UGC clip, 4 seconds, one continuous handheld take unless timecodes say cut.
References: @Image1 = creator reference; @Image2 = setting reference. Keep the person, wardrobe and room identical to the references.
0–4s: MCU. Warm, tired smile, whispered line; end card over last second.
Vertical 9:16 handheld selfie video, medium close-up, at the bottom of the same carpeted staircase at night, warm hallway lamp beside her, nightlight glowing faintly at the top of the stairs behind. Natural skin texture, shot on iPhone front camera, intimate and unscripted, vertical 9:16.
Dialogue (Mum of a toddler, mid 30s): "{{APP_NAME}}. {{MINUTES}}. Yours."
No subtitles. No on-screen text. No logos. Natural voice, no background music.

duration

4 s

aspect ratio

9:16

resolution

1080p (720p where the API caps it)

generate audio

true

references

@Image1: creator, @Image2: setting

first frame

—