Woman Discovers Handwritten Note in Matcha Tea Shop

A 15-second photorealistic cinematic video animating a still image of a woman in a Japanese tea shop. She finishes preparing matcha, finds a folded note, reads it with growing surprise, and whispers "For me?" with a subtle smile.

This clip could not be loaded — it may have been removed from X.
Ahmad Faraz @iamahmedfaraz66 ·
View on X ↗

Prompt

Animate this image into a photorealistic cinematic 15-second video. Preserve the woman's exact face, hairstyle, clothing, jewelry, body proportions, café interior, Japanese tea-shop details, lighting, and composition.

0–4 sec: She calmly finishes preparing the matcha, gently sliding the ceramic bowl forward on the wooden counter. Her movements are careful and natural. Subtle breathing, blinking, hair movement, and realistic fabric motion.

4–7 sec: As she moves the bowl, she notices a small folded handwritten note underneath it. She pauses, looks down with curiosity, and carefully picks up the note.

7–10 sec: She unfolds the note and reads it. Her expression slowly changes from neutral to surprised. She rereads it once, clearly confused by what it says.

10–13 sec: She looks around the quiet tea shop, scanning the room as if trying to figure out who left the note. She briefly looks toward the entrance.

13–15 sec: She looks back at the note and quietly whispers, “For me?” Then she gives a small uncertain smile as the video ends.

Natural realistic acting, subtle facial expressions, delicate hand movements, realistic paper interaction, accurate fingers, natural hair physics, warm Japanese café atmosphere, soft cinematic lighting, shallow depth of field, gentle handheld camera movement. No exaggerated movements, no sudden camera motion, no extra people, no face changes, no outfit changes, no object morphing, no distorted hands.
? How to use this prompt ▾
  1. Copy the prompt using the green "Copy prompt" button above.
  2. Open your model — launch Grok Imagine 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.
LIGHTING
"soft light, cinematic lighting" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"mysterious" — 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
Grok Imagine (xAI) 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