Locked-Off Character Catches and Throws a Flying Coffee Mug

A 10-second single-take sequence that starts from a locked reference image of a character and animates a matte black steaming mug flying in from the left at high speed. The character catches it one-handed, smiles, then hurls it off the right side of frame with baseball-style follow-through, all with strict identity and physics consistency.

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

Prompt

10-second cinematic sequence. Begin from the exact edited image. Preserve the exact character, face, hairstyle, clothing, proportions, lighting, and composition. The camera remains completely locked. The animation begins immediately. Within the first 0.2 seconds, a matte black steaming coffee mug suddenly enters from the LEFT side of the frame at very high speed. The mug follows a clean, straight horizontal trajectory with natural physics. The mug remains perfectly upright. No coffee spills. Steam stretches behind the mug as a continuous motion trail. The character notices the incoming mug at the last possible moment. Instant athletic reaction. Eyes lock onto the mug. The body shifts naturally. The character reaches out and catches the mug cleanly with one hand while allowing the arm and shoulders to absorb the momentum. The catch feels smooth, believable, and athletic, like an experienced baseball player receiving a hard throw. The mug never tumbles. The coffee remains inside. Not a single drop spills. A quick smile appears. The character briefly admires the successful catch. (Optional) One quick sip. Immediately the body transitions into a powerful baseball-style throwing motion. The free arm extends naturally toward the target. The throwing arm rotates through the shoulders and hips. The mug becomes a rigid projectile. The fingers open. The mug completely separates from the hand. Visible empty space appears between the fingers and the mug. The mug accelerates rapidly toward the RIGHT edge of the frame. Steam trails behind the mug continuously. The mug completely exits the RIGHT side of the screen before the 8-second mark. The camera smoothly follows the mug for a brief moment, then naturally eases back to the character completing the follow-through. Dust kicks up around the planted foot. Hair and clothing react naturally to the momentum. The character finishes the throw with an EMPTY hand while watching the mug successfully leave the frame. Natural physics. One continuous shot. Ultra-photoreal. Locked character consistency. No warping. No duplicated mug. No duplicated hands. No extra limbs. No spilled coffee. No cuts. No transitions. The mug must visibly enter from the LEFT, be caught once, then visibly leave to the RIGHT while remaining upright for the entire sequence.
? 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 16:9 and clip duration to 10s.

What makes this prompt work

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

CAMERA
"static/fixed" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "tracking".
MOOD
"energetic, cinematic" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION
At 10s, 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