Elderly Woman Swats Fallen Robot with Cane on Sidewalk

A 15-second photorealistic vertical smartphone video shot from a high apartment window shows an elderly woman walking with a cane on a sidewalk while a humanoid robot follows behind. The robot stumbles and falls onto the asphalt, and the woman turns back, checks on it, then humorously swats it with her cane before calmly walking away. The prompt specifies a fixed high-angle handheld look with natural daylight and documentary-style realism.

This clip could not be loaded — it may have been removed from X.
Marcos @arsalannazir07 ·
View on X ↗

Prompt

Can anyone Explain this 🤧

Video Generation Prompt — 15 Seconds

Create a photorealistic, cinematic vertical smartphone video (9:16) filmed from a high apartment/window viewpoint overlooking a quiet urban sidewalk and asphalt street in daylight.

An elderly white woman with short white hair, wearing a loose beige cardigan, long neutral-colored dress/skirt, comfortable dark shoes, carrying a patterned floral handbag and walking slowly with a wooden walking cane, moves along the sidewalk.

A humanoid white-and-black futuristic robot quietly walks several steps behind her. The robot has a sleek, realistic mechanical body with white armor panels, black joints, and a dark featureless face/visor.

Action sequence:

- 0–3 sec: The elderly woman walks slowly toward the camera's direction along the sidewalk, leaning naturally on her cane. The robot follows behind her at a short distance.
- 3–5 sec: The robot suddenly loses balance, stumbles toward the edge of the sidewalk and falls onto the asphalt. Its mechanical limbs move naturally from the impact, while the woman's handbag drops nearby.
- 5–9 sec: The woman notices the fallen robot and stops. She turns around and carefully approaches it, looking concerned.
- 9–12 sec: She bends slightly toward the robot and appears to check on it, then firmly taps/swats the robot with her wooden cane in a humorous, irritated reaction.
- 12–15 sec: She picks up/adjusts her handbag, turns away, and calmly continues walking down the sidewalk while the robot remains sprawled on the road.

Camera: Fixed high-angle viewpoint as if recorded casually from an apartment window, slight natural handheld movement, no cinematic camera movement or cuts.

Visual style: Extremely realistic live-action footage, natural daylight, realistic shadows, authentic urban textures, physically accurate robot movement, realistic elderly woman's body movement, subtle imperfections of smartphone footage, believable impact physics, natural motion blur, documentary/viral-video aesthetic.

Important: Keep the elderly woman, robot, sidewalk, road, and overall composition visually consistent throughout the entire shot. No cuts, no scene transitions, no text, no subtitles, no watermark, no exaggerated CGI appearance.
? How to use this prompt ▾
  1. Copy the prompt using the green "Copy prompt" button above.
  2. Open your model — launch Seedance 2.0 on its official interface.
  3. Paste & generate — keep the verbatim prompt text for best adherence. Set aspect ratio to 9:16 and clip duration to 15s.

What makes this prompt work

Every insight below is verified against benchmark generation parameters, not asserted. How our prompt engineering benchmarks work →

CAMERA
"handheld" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "static/fixed".
LIGHTING
"natural light" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"playful, cinematic" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION
At 15s, this clip is optimized for high temporal coherence and fluid, realistic motion physics.
MODEL
Seedance 2.0 (ByteDance) provides the underlying diffusion and motion architecture. Camera, lighting and duration cues transfer across models — what differs is how literally each model interprets motion.
PROMPT LANGUAGE
The prompt is written in English. This library keeps every prompt in its original language rather than translating it — the exact words are what was conditioned during generation.
Seedance 2.5 BytePlus Cloud Partner

Tell bigger stories with Seedance 2.5

Create AI videos up to 30 seconds long with richer image, video, and audio references. Ideal for complex ideas that need consistency and control.

Explore on BytePlus Official ByteDance Enterprise Cloud