MiniMax H3 プロンプトガイド

Reference assets: [Image / Video / Audio N] handles [character, product, action, camera, sound, or style]. Scene sequence: [opening state] → [main action and changes] → [ending state]. Subject action: [who] [does what specifically], with action speed and reaction of [description]. Camera: [initial shot size and angle], [main camera movement], ending on [final composition]. Sound: [dialogue]; [ambience]; [sound effects]; [background music]. Keep unchanged: [character identity, product packaging, logo, wardrobe, scene structure, etc.]. Avoid: [errors that genuinely affect delivery].

Use @1 as the exact and immutable product-identity reference. Preserve one single rectangular AERIS Hydrating Essence bottle with frosted translucent pale-blue glass, navy cap, centered ivory label, exact “AERIS” wordmark and “HYDRATING ESSENCE” line. The bottle, cap and label are rigid physical objects: never bend, melt, peel, ripple, rotate independently or change proportions. Keep all typography, label placement, materials and colors stable and readable in every shot. Use @2 as the timing and sonic-design reference. Match its restrained premium rhythm, ambient bed and final glass chime; regenerate the soundtrack naturally for the new visuals. Create an 8-second cinematic 16:9 luxury skincare money shot with a luminous pale-blue, pearl and soft-silver palette. No people. 0.0–1.2s — Extreme macro of a sculptural clear serum ribbon floating in empty space, with glassy highlights and tiny suspended droplets. No product visible yet. 1.2–2.6s — Match cut through the serum curve to reveal @1 standing perfectly upright and motionless on a translucent aqua pedestal. A large clear liquid arc frames the bottle from at least 20 centimeters behind it and never touches or crosses the product. 2.6–4.5s — Smooth 20-degree camera orbit around the completely rigid @1. Silver-blue rim light travels across the frosted glass. The cap stays closed, the label remains flat and fully readable, and the background liquid arc moves only behind the bottle. 4.5–6.2s — Controlled macro tracking pass from the navy cap down the straight glass edge to the exact front label. Nothing occludes the bottle. “AERIS” and “HYDRATING ESSENCE” remain sharp and correctly spelled. 6.2–8.0s — Final centered hero lock-up: @1 remains perfectly unchanged on the translucent pedestal, framed by restrained clear serum arcs in the distant background and soft silver-blue caustics. Gentle forward camera drift. End exactly on the final chime from @2. Premium Korean/European skincare TVC, photoreal materials, polished studio lighting, refined negative space, smooth rhythmic transitions. Exactly one unchanged bottle. No opening cap, no detached label, no liquid touching or wrapping around the bottle, no product deformation, no duplicate bottle, no warped or misspelled text, no extra copy, no logo changes, no heavy smoke, no black background, no pure white seamless background, no chaotic splash, no hands, no subtitles, no watermark.

Use @1 for the character identity, face, short silver bob, cobalt-blue utility jumpsuit and white sneakers. Use @2 only for the walking cadence, single clockwise turn, low-angle tracking path and final camera rise; do not copy its performer, clothing, background or sound. Use @3 only for the restrained low-frequency music, spacious room tone and rhythmic structure; regenerate synchronized footsteps and fabric movement for the new scene. Create an 8-second cinematic 16:9 video in a monumental raw-concrete gallery. The same woman walks forward, makes one controlled clockwise turn, then looks directly into the camera. The low-angle tracking camera remains smooth and rises to a stable medium shot before the final pose. Preserve her identity and wardrobe throughout. No dialogue, no text, no watermark.

Image 1 provides the character's face, hairstyle, and wardrobe; Image 2 provides the scene and lighting; Video 1 references only the action rhythm and follow-shot path, without copying its character, wardrobe, background, or sound.

Open on a medium close-up at a slightly low angle. The camera does a small arc along the left side of the product at a slow, steady speed, then pushes in toward the label so the logo and bottle material come into sharp focus, and finally rests on a front-facing product close-up.

As the character opens the package, there is a clear paper-tearing sound and the subtle sound of nails touching the box. The room keeps a quiet, soft indoor ambience. She looks at the camera and says, in a natural, excited but not overly exaggerated tone: "The texture is even better than I imagined." The background adds a light, clean electronic beat that intensifies slightly when the product close-up appears.

15 seconds, 16:9 landscape. Blend live-action footage of a small kitchen at dusk with glowing hand-drawn animation. The kitchen has an old wooden table, a half-washed cup, a slightly fogged glass bottle, and a hanging dish towel. The camera looks like a hurried phone shot held in one hand: slight shake, hesitant close focus, backlit exposure breathing, and coarse grain in the shadows. Use room floor tone, fabric rustle, a soft cup clink, dripping water, the shooter's footsteps and breathing, and the faint electronic hum and tiny chirps of the hand-drawn little creature. Avoid huge eyes, fangs, threatening motion, sudden black screens, or jump-scare shots.

An epic theatrical space opera trailer. Keep a fast pace and grand scale, using crisp hard cuts, a shaking command bridge, white-hot flashes, extremely short black frames, and violent jump-drive impacts. The title uses a wide-tracked cinematic typeface with restrained material texture, subtle lighting, and a thin edge light. The text emerges from deep-space shadow, sweeps past a beam of starlight, and gradually widens its tracking, leaving a brief afterimage before flashing in a black frame.

Use Video 1 as the motion reference for the street dance performance; use Image 1 and Image 2 as the character appearance references.