Character:
Face: Appearance, features, hairstyle, hair color, and makeup strictly follow the headshot reference image.
Clothing and Body: Outfit, accessories, and body proportions strictly follow the cream-white butterfly dress reference image (off-shoulder cream dress + butterfly hair accessory); Shot 2 back view matches front view outfit.
Consistency: Same person across 4 shots; face and clothing remain consistent throughout, no changes after cuts; mirror reflection in Shot 2 is also the same person and outfit.
Props:
Shot 1: A pair of black kitchen food tongs.
Shot 4: A black spatula.
Scene:
A home kitchen connected to a living room through a doorway.
Kitchen: White marble-textured tile walls, black stove with a wok, condiment bottles, knife block on counter; white kitchen door, red lanterns hanging near ceiling.
Living Room: Light wood floor, full-length mirror behind door, black cat on floor.
Lighting:
Indoor natural daylight, soft and even, cool white-gray tone, clean and transparent.
Storyboard
Shot 1 | 0.00–3.27s | Wide-angle close-up, interacting with camera holding food tongs
Camera position: Phone very close to subject, slightly high angle, wide lens, framing face and upper body, background shows tile wall, white door, black wok on stove.
0.00–0.60s: Subject looks down with slight smile; left hand holds black food tongs at bottom-left of frame.
0.60–1.00s: Subject lifts head to look at camera, camera moves slightly closer.
1.00–1.60s: Subject looks at camera, corners of mouth rise, food tongs move to left edge of frame.
1.60–2.00s: Subject extends food tongs toward camera, tong heads appear in left foreground with bokeh effect.
2.00–2.60s: Subject clicks food tongs open/closed several times in front of camera, eyes squint slightly, playful smile.
2.60–3.27s: Food tongs retract to left side, subject smiles at camera, elegant and composed movement. 0.3s crossfade transition at 3.27s.
Shot 2 | 3.27–4.70s | Full-length mirror scene, back to camera then turning around
Camera position: Behind subject slightly right, eye-level, medium shot. Left half shows frontal reflection in mirror, right half shows subject's back; black cat on wood floor.
3.27–4.00s: Subject stands with back to camera facing mirror, one hand on hip, other touching mirror edge; reflection looking at herself.
4.00–4.20s: Subject turns head over shoulder to look at camera.
4.20–4.70s: Subject faces camera directly with calm expression; reflection turns to profile, elegant movement. 0.3s crossfade transition at 4.70s.
Shot 3 | 4.70–5.50s | High-angle overhead shot standing by stove
Camera position: From high corner of kitchen looking down full-body, wide lens showing black stove, wok, condiments, white door.
4.70–5.50s: Subject stands by stove with hands behind back, looks up smiling at camera, body sways slightly, elegant movement. 0.3s crossfade transition at 5.50s.
Shot 4 | 5.50–10.00s | Holding spatula, close-up facial expressions
Camera position: Phone close to subject, slightly high angle, wide lens framing chest-up. Background shows white door, handle, marble tiles, black wok, red lanterns.
5.50–6.00s: Subject holds black spatula at shoulder height with head up, smiling at camera.
6.00–8.00s: Subject says line 'Is this spatula easy to use?' while smiling.
8.00–8.40s: Subject raises eyebrows looking at camera, corners of mouth naturally rise.
8.40–10.00s: Subject maintains warm relaxed smile looking at camera, spatula held beside shoulder, smile persists until end freeze-frame. Transitions smooth and continuous, no frame skips or sudden pose changes.
Style:
TikTok/Xiaohongshu home vlog style, phone wide-angle original camera quality, beauty filter/skin smoothing applied, fair translucent skin. Natural daylight, cool white tone, photorealistic, HD, lively natural expressions; overall elegant and composed, slow fluid movements, not exaggerated or rushed.
Audio:
Continuous upbeat music (ukulele/accordion bright instrumental), crossfades at cuts without interruption. In Shot 4, clear natural voice saying 'Is this spatula easy to use?', music lowered but not overpowering voice. No other human voices, screams, laughs, or strange sounds except this line.
Parameters:
9:16 vertical screen, 10.00 seconds, 30fps, photorealistic, 4 shots.
Negative Prompt: Face swap, clothing change, character appearance change after cuts, mirror reflection inconsistent with actual person, reflection becoming different person, distorted features, frowning, sad face, pursed lips, deformed fingers, deformed food tongs/spatula, extra arms, severe wide-angle distortion, flickering, low resolution, watermarks, subtitles, frame skipping, sudden motion jumps, abrupt pose changes, strange human voices, screams, unexplained laughter