A young woman performs four connected scenes in a modern kitchen and living room, interacting with a food tongs and spatula while maintaining consistent appearance and expression throughout.
Create a 10-second TikTok/Little Red Book-style home vlog in 16:9 horizontal format at 30fps. The video consists of four seamlessly connected scenes shot in a modern residential kitchen and adjoining living room. The same woman appears in all four shots—her face, features, hairstyle, hair color, makeup, outfit, accessories, and body proportions must remain completely consistent throughout; after each hard cut, she must not change appearance at all.
Scene Setting:
- Kitchen: White marble-textured ceramic tile walls, black stovetop with a black wok sitting on it, countertops scattered with various sauce bottles, knife rack, and miscellaneous items. White kitchen door. Several small red lanterns hanging at the top of the wall.
- Living room: Light wood-colored flooring, a full-length mirror hanging behind the door, a black cat on the floor.
- Lighting: Soft, even natural daylight throughout, cool white-gray color tone, clean and transparent.
Shot 1 (0.00–3.27 seconds): Wide-angle close-up, handheld phone camera held very close to the person with slight downward tilt, framing face and upper body. Background shows kitchen marble tile wall, white door, and black wok on stove. The person holds a black kitchen food tongs in their left hand positioned at lower-left frame.
- 0.00–0.60s: Head down, eyes looking downward, slight gentle smile.
- 0.60–1.00s: Head lifts, looks at camera, camera moves slightly closer.
- 1.00–1.60s: Maintains eye contact with camera, mouth corners gently rise, tongs move to left frame edge.
- 1.60–2.00s: Extends tongs toward camera, tongs head appears in soft focus at lower-left foreground.
- 2.00–2.60s: Opens and closes tongs several times in front of camera in a playful "pinching" motion, eyes slightly squinted, mischievous smile.
- 2.60–3.27s: Tongs retract to left side, maintains soft smile while looking at camera. Hard cut at 3.27s.
Shot 2 (3.27–4.70 seconds): Medium shot, camera positioned behind and slightly to the right of the person at eye level, wide-angle lens. Left half of frame shows the person's full-body mirror reflection facing forward; right half shows the person's back. Black cat visible on wooden floor.
- 3.27–4.00s: Person stands with back to camera, facing the full-length mirror, one hand on hip, other hand gently touching mirror edge. Mirror reflection shows the person looking at herself.
- 4.00–4.20s: Head turns from shoulder upward, looks back toward camera.
- 4.20–4.70s: Maintains direct eye contact with camera, calm neutral expression. Mirror reflection shows profile view. Hard cut at 4.70s. (Critical: Mirror reflection must show the exact same face, same outfit, same everything as the person's back—no inconsistencies.)
Shot 3 (4.70–5.50 seconds): High-angle overhead shot from kitchen corner looking down at full body, wide-angle lens. Frame includes black stove, wok, sauce bottles, white door.
- 4.70–5.50s: Person stands beside stove with both hands clasped behind back, looks up at camera smiling, body sways gently. Hard cut at 5.50s.
Shot 4 (5.50–10.00 seconds): Close-up, handheld phone camera positioned near person with slight downward tilt, framing chest and above. Background shows white door, door handle, marble tile wall, black wok, red lanterns at wall top. Person holds black kitchen spatula in left hand.
- 5.50–5.90s: Spatula held at shoulder height with head facing upward, person speaks line with a smile: "你看这个锅铲好不好用呀" ("Look, do you think this spatula works well?").
- 5.90–6.30s: Eyes glance to the side, lips pout slightly.
- 6.30–6.90s: Head lowers, eyes look down, lips press together gently.
- 6.90–7.30s: Eyes lift to camera, eyebrows furrow slightly, mouth pouts gently.
- 7.30–8.40s: Maintains furrowed brow and pouty mouth looking at camera, spatula hand taps twice lightly toward camera in midair.
- 8.40–9.30s: Eyebrows gradually relax, mouth corners cannot help but rise slightly.
- 9.30–10.00s: Looks at camera with full smile, spatula still held at shoulder side, hold for final frame. All movements from lowered head to raised head must be smooth and continuous without jumps or sudden teleportations of posture.
Style: Instagram/TikTok homemade vlog aesthetic with phone ultra-wide camera quality, beauty filter and skin smoothing applied, fair translucent complexion, realistic high-definition, natural and lively expressions, cold white color grading.
Audio: Upbeat, pleasant instrumental music throughout (ukulele and accordion style, bright pure instrumental). All three hard cuts at 3.27s, 4.70s, and 5.50s align perfectly with musical beats. The spoken line in Shot 4 is clear and natural; background music dips but does not cover the voice. No other human voices, exclamations, laughter, or strange sounds anywhere in the video.
Negative requirements: No face-swapping, no outfit changes, no appearance shifts after cuts, no mirror reflection inconsistencies, no facial distortion, no hand deformities, no food tongs or spatula deformities, no extra arms, no severe wide-angle distortion artifacts, no frame flicker, no low resolution, no watermarks, no subtitles, no frame skipping, no action teleportation, no sudden posture changes, no strange voices or odd sounds.
Includes a consistency lock: a trait the prompt asks the model to hold constant.