Beach Beer Commercial Shoot with Off-Screen Director

A photorealistic 15-second continuous image-to-video shot of a woman on a beach holding a beer can, reacting to an off-screen director's encouraging voice lines. The prompt locks her identity, outfit, and the can's appearance while specifying precise timing for camera moves, expressions, and product adjustments.

This clip could not be loaded — it may have been removed from X.
Loriel.AI @ou_zhen599 ·
View on X ↗

Prompt

Made with MiniMax-H3 ComfyUI

Image-to-Video:📢“Behind-the-Scenes Footage from a Commercial Shoot That Gave the Director a World of Trouble”

MiniMax-H3 prompt👇
integrated_multimodal_description: [Shot 1] One continuous 15-second photorealistic live-action beach beer-commercial shot. Preserve one adult female identity, one hairstyle with braid, one outfit, one body proportion set, and one unchanged beer can with fixed size, artwork, material, and holding hand throughout. The free hand alone may cover her mouth and brush hair. The director is off-screen only, always near the camera, and every acknowledgment must come after the model’s action or expression has already appeared. The model never speaks or lip-syncs.

From 00:00.000 to 00:02.000, handheld on wet sand and surf, tracking beside her along the shoreline, tilting from legs and waist to the low-held can, then to her face. She is still adapting to camera: lips lightly closed, jaw not fully relaxed, one tentative glance near the lens, no smile yet. From 00:02.000 to 00:04.000, the camera moves closer in a small front-side arc as she notices the can is too low and raises it herself to waist height. Only after finishing the adjustment does amused self-awareness appear in her eyes and mouth. Then the off-screen director (S1) says in an off-screen voiceover: <d>[English] Yeah... there.</d> while her lips remain closed. From 00:04.000 to 00:06.000, she briefly over-poses, notices it instantly, releases the jaw, lets the eyes smile first, then covers her mouth with the free hand and looks down with a small quiet laugh. Keep the amused eyes visible above the hand. Only after that smile exists, S1 says in an off-screen voiceover: <d>[English] No, no... that smile, keep it.</d> while her lips remain closed. From 00:06.000 to 00:08.000, the camera lowers with her bowed head and rises with her recovery. The free hand leaves her mouth and brushes loose hair aside. She exhales, relaxes shoulders, straightens the can with the original holding hand, reacts with mild amused surprise as a wave touches her foot, then settles naturally. Only after the relaxation is visible, S1 says in an off-screen voiceover: <d>[English] Yes... less pose.</d> while her lips remain closed. From 00:08.000 to 00:10.000, follow her half-step laterally into a comfortable three-quarter angle. She looks to the sea, then steals a brief look at the lens; the smile comes after the glance, small and spontaneous, with relaxed brow and lips. No director speech. From 00:10.000 to 00:12.000, frame face, shoulders, can, and waist together in a medium close-up. She independently rotates the can so its front faces camera more naturally, without tightening up or remaking the smile. Only after the product adjustment is complete, S1 says in an off-screen voiceover: <d>[English] Mm... that's nice.</d> while her lips remain closed. From 00:12.000 to 00:15.000, follow her natural stop into a composed waist-up hero frame, advancing softly and lifting almost imperceptibly. She looks once more to the sea, then back to the lens; jaw releases, lips settle, and a faint smile becomes quiet and assured. Keep the can at the established height and angle. Only once this final state is already formed, S1 says in an off-screen voiceover: <d>[English] Hold that... beautiful.</d> while her lips remain closed. End with small breathing, tiny eye adjustments, moving hair, foam, and stable sunlight. No cuts, inserts, zooms, orbiting, drinking, toasting, cue-waiting, visible director, repeated identical smiles, exaggerated laughter, identity drift, hand switching, can deformation, packaging change, subtitles, text, or watermarks.

overall_soundscape: Continuous surf, sea breeze, light wet-sand footsteps, and subtle clothing friction stay natural under the director’s five quiet encouraging voice lines. The model contributes only breathing and small spontaneous laughter, never words.

non_diegetic_music: N/A
? 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 16:9 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
"zoom" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "tilt", "tracking", "orbit".
LIGHTING
"natural light" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"playful" — 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