by MiniMax

MiniMax H3 Prompts

MiniMax's multimodal video model — start from text, an image, a clip or a soundtrack, and get video with native stereo sound.

video

subject_definitions: : The sole primary subject: the same young adult woman shown in the reference, with pale skin, long dark hair in an elaborate updo with pale ornaments, refined features, and a graceful fashion-model presence. She wears the reference pale silver-gray embroidered gown and translucent shawl, and expresses quiet happiness while trying on the outfit. Source(s): . summary: Create a 15.083-second vertical fashion scene in one unbroken observational take. A dark-haired woman in an ornate pale silver-gray gown lifts and drapes a translucent shawl, adjusts the outfit, admires herself in a mirror, and finishes in a graceful full-body reveal that communicates the joy of trying new clothes. Preserve the supplied reference’s identity, elegant interior, luminous palette, and detailed textiles. Hard constraints: Exactly one continuous vertical shot with no cuts or hidden transitions. | The same woman remains the sole primary subject throughout. | Show her trying on and arranging the translucent garment over the pale silver-gray embroidered dress, conveying genuine delight in the new outfit. | Preserve the reference identity, wardrobe, ornate bright interior, mirror, garment rack, luminous cool-blue and champagne palette, and fashion-editorial detail. | Keep the presentation tasteful and focused on clothing, posture, silhouette, and fabric movement. | No narration, subtitles, or spoken dialogue. Generation controls (authoritative) — Prompt-text rule: every section label and descriptive sentence is silent production direction, never speech content. Do not speak, recite, chant, sing, or read this prompt aloud. Background music: enabled. Generate a context-appropriate non-diegetic score unless the user explicitly requests silence or no music. Dialogue permission is enabled, but this plan contains no dialogue lines. Generate no character speech, conversation, chanting, singing, or other vocals. Dialogue language: automatic. Preserve each explicit language tag; otherwise use the language required by the scene and user intent. Narration: disabled. Generate no narrator, voice-over, spoken description, or audible reading of prompt text, section labels, instructions, asset tags, or metadata. Subtitles: disabled. Do not render subtitles or dialogue captions. Creative direction (authoritative within explicit user intent and reference fidelity) Priority: Apply these creative directives clearly wherever they do not conflict with explicit user requirements, identity retention, or fixed first/last-frame composition. Format and direction: Favor believable observation, motivated reframing, natural performance, and environmental detail over polished spectacle. Retain small imperfections that support authenticity while keeping the subject readable. Progress from a human-scale anchor to environmental scale, preserving depth layers and landing on a strong reveal composition. Camera execution: Follow the action continuously in a single unbroken take, using only motivated pans, small translations, and reframing needed to preserve spatial clarity. Look: Treat connected visual references as authoritative for identity, wardrobe, objects, environment, composition, lighting, color, and medium; do not impose an unrelated restyle. Pacing and composition: Use moderate, readable motion with natural acceleration and enough settling time for each important beat. Use exactly one continuous shot with no hidden or explicit cuts; express all action beats through blocking, performance, camera motion, reframing, and synchronized sound. An explicit user-requested shot or cut count remains authoritative over this density preference. Compose for a vertical frame: protect faces, hands, and essential action inside the central mobile-safe area; favor depth movement and avoid losing subjects at narrow side edges. retention_analysis: -> identity: Use the supplied collage as the authoritative visual reference for the same woman’s identity, facial features, pale skin, long dark hair in an elaborate updo with pale ornaments, downcast gaze, refined feminine silhouette, pale silver-gray embroidered gown, fitted bodice, flowing floor-length skirt, gold floral ornamentation, jeweled details, translucent wide-sleeved shawl, garment rack, bright ornate interior, tall windows, pale-blue mountain scenery, decorative furnishings, warm small lights, oval mirror, layered depth, luminous window backlight, cool silver-blue and warm champagne palette, detailed textiles, graceful portrait and near-full-body framing, and polished dreamlike fashion-editorial treatment. Preserve these elements consistently throughout one continuous scene, while treating the collage as a reference rather than reproducing its nine-panel layout. Use the depicted poses to guide the natural action of lifting the sheer garment, draping it around the shoulders, checking the waist and silhouette, and turning toward the mirror with quiet delight. Present the performance with believable observational imperfections and tasteful focus on clothing, posture, silhouette, and fabric movement.. detailed_description: [Shot 1] At 00:00.000-00:15.083, At the start, stands beside the pale garment rack in the luminous ornate interior, already wearing the pale silver-gray embroidered gown and holding the translucent shawl. She notices the garment with quiet anticipation, lifts it carefully, and brings it around her shoulders. Her expression changes into visible, restrained delight as the sheer fabric catches the window light. Without any cut, she smooths the shawl and checks the embroidered waist and flowing skirt, allowing the camera to follow her natural movement and preserve her graceful silhouette. She takes a few small steps toward the oval mirror, turns slightly to inspect the front and rear drape, then settles into a poised full-body stance with a soft satisfied smile and a brief downward glance at the finished o

A 3D stylized animation begins with a tight close-up on the gold-spoked wheels and connecting rods of a black steam locomotive accented with metallic hoops. As the camera smoothly zooms out and pulls back, it reveals the entire train puffing spherical gray smoke clouds from its chimney while pulling red passenger cars along a railway track. The track runs across an elevated arched bridge alongside a grand medieval stone castle complete with corner towers and battlements, all set within a low-poly environment featuring scattered evergreen trees and a quiet river.

MiniMax H3 on @Hailuo_AI Prompt b- A young Korean woman, early 20s, tired after a long day, oversized coat swallowing her frame, hair escaping a loose braid, stands alone at a rural bus stop long after the sun has set. Setting: A single flickering streetlamp, an empty road disappearing into darkness, rice paddies barely visible on either side, insects buzzing somewhere in the black. Camera feel: Static tripod shot with occasional handheld nudges, like whoever's filming keeps almost forgetting they're recording — heavy grain, the lamp's orange glow bleeding into the frame, tape hiss audible under everything. What happens (15 sec total): She leans against the bus stop sign, checking her phone, then pocketing it with a tired sigh. She mutters to camera, almost to herself, "버스 왜 안 와..." ("Why isn't the bus coming..."), kicking a small pebble. Headlights appear far down the road she straightens up, relief crossing her face. As the bus approaches, she looks back at the camera one last time saying "드디어" ("Finally"), stepping toward the curb as the tape cuts. Sound: Crickets, distant engine growing louder, gravel underfoot, wind. Mood: Quiet exhaustion giving way to small relief nothing dramatic, just real.

He found a black hole paper and the Human greed took over. 😭 He kept pulling out money until he decided to go inside himself. Big mistake.

Create an explosive, motion-graphics-driven character reveal trailer in 16:9, exactly 13 distinct cuts, 24fps. BTS is a cool, composed anime streetwear girl with long voluminous wavy hair that is jet-black at the roots and mid-lengths with vivid hot-pink streaks and highlights throughout, messy side-swept bangs, a high messy ponytail secured by a black scrunchie with a pink accent bow, ocean-blue eyes with sharp winged black eyeliner, a slim black choker printed with pink “BTS”, an oversized white zip-up hooded windbreaker covered in pink BTS logos, pink stripes and sleeve text, a white crop top centered with a large pink BTS emblem, matching white cargo-style pants with pink BTS branding down the legs and pink drawstring details, chunky white-and-pink platform sneakers, and a pink BTS tote bag. Preserve her exact face, proportions, hairstyle, outfit, materials, accessories and colors throughout; never redesign her. This film is 80% bold graphic design in motion and 20% character action: giant kinetic typography, hard-edged shapes, split-screens, flat color fields, barcode strips, UI ticks, halftone, speed lines, butterfly trails and shutter flashes. Palette: hot pink, lavender-purple, white, black, silver-grey (BTS logo gradient). Style: premium AAA motion-graphics title sequence x K-pop streetwear campaign film. Every graphic element moves fast and snaps hard on the beat. CUT 01 | 0.00-1.00s - Pure graphics: a massive hot-pink circle slams onto a white field, two black bars wipe across, tiny UI ticks and a barcode strip flicker; the letters B, T and S punch in one after another with heavy impact shake. CUT 02 | 1.00-2.00s - The S becomes a porthole: extreme close-up of her ocean-blue eye with winged eyeliner inside it, glancing up; RGB split flash, then the circle shatters into shards of flat pink and lavender. CUT 03 | 2.00-3.10s - Black frame with an enormous white BTS; she sprints in from frame left and power-slides across the baseline of the typography, speed lines and hot-pink streaks trailing, shards of the letters kicked up like sparks and pink butterflies bursting. Whip-pan out. CUT 04 | 3.10-4.00s - Split-screen triptych of flat pink/white/lavender panels; in each panel her silhouette performs a different move in stroboscopic freeze: takeoff, tuck, landing. Huge vertical text FULL SPEED scrolls behind the panels. CUT 05 | 4.00-5.10s - She leaps through a giant rotating ring of typography reading NO BRAKES NO LIMITS; camera tracks her mid-air spin in slow motion as the letters scatter into butterflies, then snap-zoom on her confident face. CUT 06 | 5.10-6.00s - Hard cut: white editorial card, huge black JUMP with a hot-pink slash; she vaults over the word itself, palm planted on the J, legs whipping across frame; the word compresses like a spring under her hand and rebounds. CUT 07 | 6.00-7.00s - Lavender field with a black diagonal stripe; she back-flips along the stripe in three stroboscopic ghost frames, each ghost tinted a different palette color; giant outlined text FLIP rotates 180 degrees in sync with her rotation. CUT 08 | 7.00-8.00s - Kinetic type barrage: the words PINK / FAST / ARMY / BTS slam in one per beat with shutter flashes and camera shake, while she slides on her knees across the foreground, jacket flaring, pink petal and butterfly particles bursting from her sneakers. CUT 09 | 8.00-9.00s - Black frame, giant white wireframe grid tilting in 3D; she runs up the grid like a wall, kicks off, and hangs in the air as everything freezes; a hot-pink circle stamps around her frozen pose like a target lock with UI brackets and data ticks. CUT 10 | 9.00-10.10s - Freeze releases into a burst: she dives toward camera through layered flat-color panes that shatter one by one like glass shutters, each shattering pane revealing a bigger letter of B-T-S; foreground wipe with her sneaker. CUT 11 | 10.10-11.10s - Rapid-fire poster montage: four full-screen graphic posters of her in different action poses (mid-flip, sliding, landing, hands-in-pockets) snap past with hard cuts, each with different bold layout, oversized numbers 01-04, barcodes and slashes. CUT 12 | 11.10-13.00s - Hero moment on a clean white cyclorama: she lands a final backflip dead center in slow motion, straightens with hands in pockets, and a shockwave of concentric hot-pink and lavender rings, wind streaks, butterflies and shattered typography blasts outward from her landing; brief iconic freeze with her faint confident smile, overexpose to white. CUT 13 | 13.00-15.00s - Final identity card: enormous black BTS dominates a pale white field with translucent pink-lavender rings, technical arcs, halftone and a rough black circular emblem containing a ghosted butterfly/barcode motif; she stands relaxed overlapping the letters, wind rippling her jacket and ponytail; one last hot-pink pulse sweeps through the typography and a butterfly-ring flash punctuates the end. Editing: extremely aggressive rhythm - hard cuts on every beat, graphic matches, whip pans, snap zooms, stroboscopic freezes, foreground wipes, RGB splits, shutter flashes, impact shakes and speed ramps; every cut must feel compositionally different; typography is always fully readable before the character overlaps it. No weapons, no combat, no fire; all energy comes from motion design, wind, petals, butterflies, glass and her parkour-style athleticism. BGM: hard-hitting electronic / drum-heavy future bass with aggressive drops, risers, sub hits and glitch fills locked to every cut; sneaker impacts, whooshes, glass shatters and typography slams are rhythmic sound-design elements. Peak at CUT 12 and end with a cold electronic logo stinger. Premium AAA quality, anime-inspired cinematic rendering, stylish and e

Create a 15-second cinematic girl travel vlog in 16:9 landscape. A young woman walks through a beautiful Japanese park during peak sakura season while filming herself with a compact vlog camera. She laughs softly, spins slightly beneath the cherry blossom canopy and looks upward as petals fall around her. She then points toward a peaceful hanami picnic area filled with people enjoying spring. Her hair moves naturally in the breeze. Warm golden sunlight, authentic candid emotion, realistic people and environment, handheld influencer vlog aesthetic, photorealistic 4K, 16:9.

Create a 15-second ultra-photorealistic cinematic luxury real-estate house tour, using the provided reference image as the visual style reference. IMPORTANT: Maintain a consistent architectural design, materials, furniture style, warm color palette, and premium luxury aesthetic throughout the entire video. The house must feel like one real, connected property. No random architectural changes. VIDEO FORMAT: Vertical 9:16 Duration: exactly 15 seconds Ultra-realistic 4K Professional luxury real-estate cinematography Smooth stabilized camera movement Natural lighting Realistic reflections and shadows Premium editorial look No people No text No logos No watermark SCENE 1 — 0-2 SECONDS — EXTERIOR REVEAL Start with a cinematic wide establishing shot of the complete luxury modern house during golden hour. Show the elegant multi-level architecture, large floor-to-ceiling windows, stone exterior walls, warm interior lights, landscaped garden, clean driveway and premium entrance. Camera slowly pushes forward toward the house like a professional real-estate drone/gimbal shot. TRANSITION: Smooth forward movement transitioning naturally toward the main entrance. SCENE 2 — 2-4 SECONDS — MAIN ENTRANCE & FOYER Camera smoothly enters through the large front door into a sophisticated luxury foyer. Show polished flooring, warm wooden staircase, elegant wall decoration, large round mirror, designer console table and soft ambient lighting. Camera moves forward slowly and naturally, revealing the open-plan interior. SCENE 3 — 4-6 SECONDS — LUXURY LIVING ROOM Transition into the main living room shown in the reference image. Show the large caramel-brown leather sectional sofa, cream upholstered lounge chairs, round wooden coffee table, patterned rug, decorative plants, wooden furniture and the central modern fireplace with gray stone/tile surround. Large windows bring in beautiful natural daylight. Camera makes a smooth cinematic side-to-side movement, showcasing the entire living space. SCENE 4 — 6-8 SECONDS — OPEN KITCHEN & DINING Camera smoothly pans from the living room into the open-plan luxury kitchen and dining area. Show a large premium kitchen island, elegant cabinetry, modern appliances, sophisticated pendant lights, marble/stone surfaces and a stylish dining area. Keep the same warm neutral color palette and architectural style. Camera slowly glides past the island for a high-end property-tour feeling. SCENE 5 — 8-10 SECONDS — MASTER BEDROOM Smooth transition into a spacious luxury master bedroom. Show a large elegant bed with premium neutral bedding, soft textured fabrics, wooden accents, designer bedside tables and large windows overlooking greenery. Warm natural sunlight enters through the windows. Camera slowly moves toward the bed and then gently pans across the room. SCENE 6 — 10-12 SECONDS — LUXURY MARBLE BATHROOM Camera transitions into a high-end master bathroom. Show large marble surfaces, a freestanding modern bathtub, spacious glass shower, elegant vanity, large mirror and warm hidden LED lighting. Use a slow cinematic camera sweep to reveal the luxurious finishes. Everything should look realistic and physically accurate. SCENE 7 — 12-15 SECONDS — BACKYARD & FINAL HERO SHOT Camera smoothly exits toward the backyard/patio. Reveal a beautiful landscaped outdoor lounge area with comfortable designer seating, greenery, warm architectural lighting and a premium swimming pool. End with a cinematic wide hero shot of the entire property glowing during sunset. Camera slowly pulls back and rises slightly, creating a premium luxury-real-estate commercial ending.

A cinematic creation film follows one maker reconstructing the main subject shown in the referenced image completely from scratch. The referenced image defines the finished subject’s complete visible appearance, proportions, structure, materials, colors, clothing or surface details, and distinctive features; ignore its background, framing, lighting, and unrelated elements. Begin directly on an empty, clean virtual workbench. Use a stable front three-quarter overhead view that keeps the developing subject readable. There is one maker throughout, represented by the same consistent left and right hands and forearms. Show no more than two hands at once. From 0 to 14 seconds, the entire creation unfolds as a clearly accelerated timelapse with rapid, purposeful hand movement and restrained motion blur. Short jump cuts compress repetitive manual work only after each action has visibly completed. Every cut inherits the exact form and progress left by the previous action. 0-2 seconds: One hand enters already holding the first foundation material, armature, or base element appropriate to the referenced subject and places it at the center. The second hand steadies it as the maker establishes the initial supporting form. 2-8 seconds: The maker rapidly develops the subject’s major structure and volumes using one coherent creation method appropriate to what the referenced image depicts. A living subject is sculpted as one continuous, non-gory digital form from armature to anatomy; a vehicle or machine is built from chassis to functional structure; an object is formed or assembled from its supporting body outward. Each additional material or component enters from outside the frame while firmly held by one of the maker’s hands, is carried to its destination, and remains under hand control until attached or shaped. 8-12 seconds: The same hands develop the recognizable outer form and reference-specific features. The maker sculpts, fits, wraps, stitches, fastens, carves, or polishes only where appropriate to the subject. Facial features, hair, clothing, body panels, wheels, glass, surfaces, accessories, or equivalent defining elements emerge through visible hand and tool contact, never through spontaneous transformation. 12-14 seconds: The maker refines proportions, edges, joints, surface transitions, textures, colors, and distinctive details until the developing subject closely matches the referenced image. One hand stabilizes the form while the other performs each final adjustment with a hand-held tool. 14-15 seconds: The maker removes the last tool by hand and withdraws both hands. The timelapse returns to normal speed as the camera makes a restrained push toward the completed subject and holds on a clean final view. Materials and components do not need to be visible before use, but anything newly introduced must enter the frame already held by one of the maker’s hands. Nothing moves, assembles, appears, disappears, or changes material independently. Maintain one maker, one continuous subject, one creation position, and one category-appropriate construction method. No assistants, extra hands, detached anatomy, duplicated elements, magical morphing, drawing phase, software interface, cursor, menus, annotations, or text overlays.

A smooth, continuous 15-second first-person / over-the-shoulder cinematic mobile video of a young woman with long dark hair, wearing a beige sweater and backpack, exploring a luxurious modern hotel room. Shot on smartphone in vertical/mobile format, natural soft daylight, elegant and calm atmosphere 0:00–0:01 – Close-up of a hand holding a gold keycard tapping the electronic door lock and opening the wooden door, revealing a bright modern hotel room. 0:01–0:02 – She steps inside from behind, holding her phone up as if filming. 0:02–0:03 – Wide shot of the entire elegant room: large bed with white linens, seating area, big windows with city skyline view, natural light flooding in. 0:03–0:04 – Slow camera pan right across the cozy king-size bed with white duvet and modern headboard art. 0:04–0:05 – Camera moves toward the seating area by the large window: two grey armchairs and a round wooden coffee table. 0:05–0:06 – She stands at the window filming the panoramic city view with high-rises and a stadium outside. 0:06–0:07 – Camera pans left to the modern wooden work desk with chair, lamp and stationery. 0:07–0:08 – Camera glides toward the flat-screen TV on a light wood media console with mini cabinet. 0:08–0:09 – Close-up of the mini-bar / coffee & tea station: electric kettle, cups, sachets, neatly arranged under warm lighting. 0:09–0:10 – Camera turns toward the open bathroom doorway. 0:10–0:11 – Smooth move inside the clean modern bathroom: marble sink, large mirror, glass shower, toilet, bright lighting. 0:11–0:12 – She turns back into the main room, smiling happily while holding her phone. 0:12–0:13 – She gestures happily toward the room with one hand while filming, showing the space again. 0:13–0:14 – Extreme close-up of the smartphone screen showing the live recording of the hotel room with red record button. 0:14–0:15 – Final shot of her standing at the large window, enjoying the city view, holding the phone, soft natural light, peaceful ending. Style & technical details: Cinematic mobile footage, smooth handheld + subtle gimbal movement, soft natural window light, warm and inviting color grade, high detail, realistic textures, calm and luxurious mood. No text overlays, no logos. Vertical 9:16 aspect ratio, 15 seconds total. Soft ambient hotel atmosphere with gentle feel-good background music feel.

Create a 15-second fast-paced character creation timelapse inside a professional digital drawing and character design interface. Use the provided character reference only @ Image1 as the final target for the character’s appearance, proportions, clothing, hairstyle, colors and distinctive features. The process must visibly start from a completely blank canvas and reconstruct the referenced character from scratch. Show a visible mouse cursor actively controlling the entire creation process. Every major visual change should feel caused by cursor interaction with the UI. 0:00-0:02 Start on a blank white or neutral canvas inside a clean professional drawing interface. The cursor quickly creates the first loose construction lines, head shape, body proportions and basic pose using rough sketch strokes. 0:02-0:05 Accelerate into detailed sketching. The cursor rapidly defines the face, hair, anatomy, clothing silhouette, accessories and characteristic features of the referenced character. Use believable drawing gestures, short strokes, selections, transforms and occasional undo corrections. 0:05-0:08 The rough sketch becomes clean line art. The cursor switches tools, adjusts brush size and cleans the silhouette. Unnecessary construction lines disappear while precise facial details, clothing folds and small design elements are added. 0:08-0:11 Rapid coloring phase. The cursor selects regions and fills the character with the correct colors from the reference. Show quick palette selections, color picking, layer changes, clipping masks and brush passes. Add shadows, highlights and material details in fast succession. 0:11-0:13 Rendering and polish. The cursor adds final lighting, hair detail, skin shading, fabric texture, reflections and small accent details. Briefly zoom into important areas such as the face or costume while refining them, then zoom back out. 0:13-0:15 The interface clears unnecessary guides and panels. The finished character is shown fully rendered and closely matching the provided reference. End with the cursor making one final small adjustment, then stop on a clean full-character presentation. STYLE: High-speed digital art timelapse, polished professional character-design workflow, believable drawing software UI, smooth cursor movement, rapid but readable actions, clean layers and tool changes, no random text, no fake dialogue, no unrelated popups. MOTION: The entire 15 seconds should feel continuously productive. Avoid long pauses. Compress several minutes or hours of drawing into an energetic timelapse while keeping the progression clearly readable: blank canvas → rough sketch → clean line art → flat colors → shading → polished final character. CAMERA: Primarily screen-recording style with subtle digital zooms and pans following the cursor and active drawing area. Keep the UI stable and readable. Do not use cinematic cuts outside the software interface. IMPORTANT: The character must not appear instantly or through a single magical transformation. Every stage should visibly build upon the previous one through cursor-driven drawing, editing, coloring and rendering actions.

0.00–2.50 Warm ivory background. Large black text: **O GORDAO DOS CORTES INOVOU.** Text slides in fast from the left with a clean ease-out. A thin red line grows underneath it. On the beat, the whole composition compresses slightly and snaps back. 2.50–5.50 The red line extends across the screen and becomes a crop transition. Reveal huge stacked text: **POSSANTE COMO UM JATO.** **VELOZ COMO UM FOGUETE** Use aggressive kinetic typography: large scale, edge cropping, fast horizontal movement, strong black/ivory/red composition. Keep the text sharp when it lands. 5.50–8.50 The typography collapses into five rectangular video-frame cards. The cards rapidly fill one after another while a red timing line underneath moves much slower. Use shallow 2.5D perspective, fast card stacking, whip movement and clean parallax to visually show that generation is finishing ahead of time. inspired in some brazilian podcast 8.50–11.00 The five cards snap together into one flat composition. Reveal: **O PRIMEIRO CORTE CHEGA.** **EM APENAS 15s.** Make **EM APENAS 1.5s** the biggest visual element. Use a fast mask reveal, strong scale change and one heavy motion-design impact when the full statement lands. 11.00–12.70 A red line shoots around the frame and builds a rectangular border. The previous text disappears through the moving crop. The border contracts several times in sync with an accelerating heartbeat-like bass pulse. 12.70–15.00 Brief silence. One final impact. Reveal: **JÁ TA DISPONÍVEL BIG.** **https://t.co/XaNKtgyaIs** Warm ivory background, black typography, thin red frame. Everything becomes completely flat and still. Hold unchanged until the end. STYLE Premium 2D motion design with very subtle 2.5D card depth. Swiss editorial typography mixed with energetic commercial motion graphics. Warm ivory, black and vermilion red. Large type, strong cropping, fast masks, cards, lines, parallax, precise easing, short motion blur only during transitions. No full 3D scenes, no UI, no particles, no random objects, no glitches, no letter-by-letter animation.

A completely blank sheet of smooth white paper fills the frame. Two hands enter from the bottom. The right hand holds a sharpened graphite pencil; the left hand rests lightly at the lower-left corner of the paper to keep it still. The right hand makes the first mark: a very light, loose oval in the center of the page for the head. Immediately add a faint vertical center line and a horizontal eye-line crossing the middle of the oval. Draw two short marks for the brow line and the base of the nose, then a light curve for the chin. All construction lines stay pale and barely visible. Next, block in the neck as two simple sloping lines and a shallow U for the shoulders and collarbones. Sketch a rough rectangle for the torso and the square neckline of the top. Still using only the lightest pressure, place a large circle on the left for the round vanity mirror and a few vertical ovals and cylinders across the bottom for bottles and brush handles. Nothing is detailed yet—only placement. Now the face. Darken the eye-line slightly and draw the almond shapes of both eyes, leaving a small highlight circle in each iris. Add the upper lids, a few lashes, and the gentle arch of the brows. Move to the nose: a soft wedge and two small nostril curves. Then the mouth: a short center dip, the full upper lip, and the slight upward curve of the smile. Keep every stroke inside the original oval. Shift to the hair. Start at the hairline and draw the high, messy half-up bun with the flower-shaped clip on top and the two small barrettes on the right side. Pull long, wavy strands down the left side of the face and over the right shoulder, using loose, overlapping S-curves. Let a few shorter pieces fall across the forehead. Refine the clothing: the ribbed texture of the white top, the thin orange trim around the neckline and sleeve, and the tiny bow at the center. Add the thin necklace chain and its small pendant. Darken the contour of the right hand resting against the cheek, fingers relaxed. Move to the foreground still life. Outline the gold-framed round mirror on the left, then the cluster of bottles—tall toner bottle, perfume with a faceted cap, pump bottles, and the cup of makeup brushes on the right. Keep these objects slightly lighter so they sit in front of the figure without competing. Begin shading. Hatch soft graphite under the chin, along the left side of the nose, beneath the lower lip, and in the hollow of the neck. Build darker value in the hair where strands overlap and around the clips. Add light cross-hatching on the fabric folds of the top and a faint cast shadow from the hand onto the cheek. Leave the paper white for the brightest highlights on the forehead, nose tip, and lip. The left hand slides out of frame. The right hand makes a few final tightening strokes on the eyes and the edges of the hair, then rests the pencil at the top of the paper. The finished drawing is a complete graphite sketch of the blonde woman at her vanity, built entirely from the first faint oval to the last shadow, on otherwise empty white paper. Satisfying, calm, close-up process video. Continuous take, no cuts, no extra motion except the hands and pencil. Soft natural light, visible pencil grain and paper tooth.

ARCHETYPE: Physical Comedy Fairy Tale DURATION: 15 Seconds FORMAT: 16:9 stylized illustrated animation AUDIO: Lively Romanian folk-inspired rhythm with accordion, violin plucks and wooden percussion. No dialogue. PROMPT.CONCEPT: TITLE: Wolf at the Wrong House DESCRIPTION: A confident wolf follows Mother Goat through a colorful village hoping to discover where her three kids live, but he accidentally chooses the wrong cottage and spends the entire story trying to outwit three wooden goat children who aren't even inside. DURATION: 15 seconds CORE_VISUAL_RULE: The world resembles hand-painted Romanian wooden toys and naïve village paintings. Characters behave like jointed wooden figurines moved by invisible hands. RHYTHM_STRUCTURE: spying → mistaken assumption → elaborate scheme → repeated confusion → reveal. SUBJECT_LOCK: Mother Goat: white carved wooden goat with painted red floral vest and black skirt. Three kids: tiny cream wooden figurines with red, green and blue painted collars. Wolf: tall dark-brown wooden figure with long hinged arms, triangular ears and comically smug painted eyebrows. CAMERA_DIRECTION: Orthographic dollhouse views, playful overhead angles and simple lateral moves. Occasional fast punch-in for reactions. Preserve visible miniature scale. VISUAL_STYLE: OVERALL: Romanian naïve folk painting combined with vintage hand-painted wooden toys. MEDIUM_OR_ONTOLOGY: carved linden wood figures, painted wooden cottages, hand-painted floral scenery. INSPIRED_BY: Romanian folk toys, village icons, naïve rural painting and traditional painted furniture. COLOR_PALETTE: brick red, sunflower yellow, grassy green, sky blue, cream, dark brown. MATERIALS_AND_TEXTURE: chipped tempera paint, visible wood grain, carved tool marks, slightly uneven handmade geometry. LIGHTING: warm tabletop daylight with soft miniature shadows. DEPTH_AND_COMPOSITION: physical tabletop diorama with layered painted wooden scenery. MOTION_LANGUAGE: FOLLOWS_MUSIC: strongly CORE_BEHAVIOR: characters move in tiny mechanical increments like stop-motion wooden toys. TRANSITION_SYSTEM: cottages, trees and hills slide sideways like wooden theatre scenery. CONTINUITY_RULE: the wolf's increasingly elaborate collection of disguise pieces remains physically attached to him. MOTION_INTENSITY: energetic and comic. STORYBOARD: TOTAL_BEATS: 8 BEAT 01 — 0.0–1.8s DESCRIPTION: Mother Goat leaves her cottage carrying two wooden baskets. Three goat kids wave from an upstairs window. CAMERA: miniature wide shot. SUBJECT_ACTION: Mother walks toward village. TRANSITION: scenery slides sideways. BEAT 02 — 1.8–3.4s DESCRIPTION: Wolf pops from behind a tiny painted tree and sneaks after her. CAMERA: profile tracking shot. SUBJECT_ACTION: He tiptoes dramatically. VISUAL_FOCUS: exaggerated bent knees. BEAT 03 — 3.4–5.2s DESCRIPTION: Mother Goat passes behind two almost identical wooden cottages. SUBJECT_ACTION: Wolf loses sight of her for one second. CAMERA: overhead. VISUAL_FOCUS: wolf rapidly looking left and right. BEAT 04 — 5.2–7.0s DESCRIPTION: Wolf confidently chooses the wrong cottage. SUBJECT_ACTION: He smooths his fur, puts on a floral scarf and knocks. CAMERA: frontal dollhouse shot. VISUAL_FOCUS: smug expression. BEAT 05 — 7.0–8.7s DESCRIPTION: Nothing happens. SUBJECT_ACTION: Wolf knocks again, increasingly politely. CAMERA: medium close-up. MOTION_BEHAVIOR: wooden elbow repeatedly hinges forward. BEAT 06 — 8.7–10.5s DESCRIPTION: He produces a basket, bonnet and bunch of flowers, adding each disguise piece. SUBJECT_ACTION: Wolf poses with absurd elegance. CAMERA: rapid incremental push-in. VISUAL_FOCUS: overloaded costume. BEAT 07 — 10.5–12.6s DESCRIPTION: Still nothing. Frustrated, wolf tries the handle. Entire front wall of cottage accidentally tips forward like a dollhouse panel. CAMERA: three-quarter view. VISUAL_FOCUS: completely empty interior. SUBJECT_ACTION: Wolf freezes. BEAT 08 — 12.6–15.0s DESCRIPTION: Camera slides one cottage to the left, revealing the real three kids watching him through their window. SUBJECT_ACTION: The kids silently shake with laughter. Wolf slowly turns toward them, mortified. The kids instantly close the shutters. CAMERA: wide village tableau. MOTION_BEHAVIOR: wolf's wooden ears droop on tiny hinges. END_FRAME: Wolf stands alone between the two nearly identical cottages wearing the ridiculous bonnet, basket and flowers, while a tiny wooden chicken casually walks past him. NEGATIVE_PROMPT: photorealism, realistic fur, glossy CGI, polished modern 3D animation, anime, dark horror, gore, violence, contemporary objects, smooth morphing, physically realistic motion, complex backgrounds, text, subtitles, logos.

Stickman doodle style with Minimax H3. Tell a story, an epic feat, a historical event, or something educational, without moving a single keyframe.

Create a 15-second, 16:9 stickman doodle history piece on the June 1962 Alcatraz escape, maximum physical action and tension throughout, told as one continuous escalating escape sequence. Draw from pure white background, hand-drawn whiteboard explainer, single-weight black ink linework, minimalist stickman figures, uniform simplicity across figures, prison, tools, raft and text, no color fill anywhere, rough marker texture, no gradients, no shading, no 3D volume, no photorealism. Never differing line weights, never soft shadows, never painterly rendering, never gore or real injury, never a static or resting pose - every figure in every beat is mid-strain, mid-motion, fully committed to the escape. Aim for 75% relentless physical tension and 25% mounting dread as the sequence builds toward the open, unresolved ending - dynamic diagonal compositions, tight framing, never a flat centered shot. Build the sequence as a hand-drawn whiteboard explainer, drawn and animated with urgency: every element - figures, prison structure, tools, water and text - snaps into place in the same single black ink line weight, as if a hand is sketching frantically fast under pressure. TYPOGRAPHY & CREDITS: All on-screen text must remain perfectly sharp, stable and legible whenever it appears. Keep text minimal - only two moments of text in the whole video, so the action never pauses for exposition. Use only the exact text provided. No Chinese characters, no garbled, warped, stretched or misspelled text. Each line appears only once. Line 1 (early, quick tag): "ALCATRAZ" Line 2 (final tag): "JUNE 1962" Animation style: both tags stamp on fast and hard, single confident strokes, no slow build-up. Hold the final frame motionless for 1.2-1.4 seconds. Act structure (sync to beats): 0-2s: Establishing shot - a stark prison silhouette sits on a rocky island in a dark bay, a guard tower beam sweeping the water; a stickman guard walks patrol below with a flashlight; tag "ALCATRAZ" stamps on quick. 2-4s: Cut to a cramped cell - a stickman figure claws frantically at a vent grate with a sharpened spoon-tool, concrete-dust and chips flying, sweat-drop doodles flicking off; a dummy head with painted-on hair sits still in the bed behind him. 4-6s: Cut - three stickman figures squeeze one by one through the narrow vent opening into a dark utility shaft, bodies contorting hard to fit, strain-lines radiating off them. 6-8s: Cut - the figures scramble frantically up a cramped vertical shaft, hand over hand, elbows and knees braced against the walls, fast climbing motion-lines trailing behind. 8-10s: Cut - bursting out onto the open rooftop under moonlight, sprinting low and fast across it, then swiftly sliding down a drainpipe to the ground far below. 10-12s: Cut - frantically shoving a makeshift raft doodle into the choppy water at the shoreline, scrambling aboard in one fast motion. 12-15s (freeze-hold anchor, unresolved ending): The figures paddle with desperate, blurred-motion arm strokes out into the dark bay, the prison silhouette shrinking behind them, thick fog rolling in around the raft; tag "JUNE 1962" stamps on; hold everything motionless mid-stroke, swallowed by fog and dark water - deliberately open, no resolution, no rescue, no capture. Vary the transitions and mix freely from this palette, favoring only the fastest and most tense options: whip-pan snaps, hard cuts on the beat, quick zoom punches, freeze-frame stamp cuts, marker-scribble wipes, impact-shake cuts. Keep every transition instant, rhythmic, tense and strictly hand-drawn - never soft dissolves, fluid morphs, gentle fades or organic morphing. BGM: an original 15-second cue, 75% relentless driving tension and 25% mounting dread, deliberately trailing off unresolved at the very end rather than resolving. Instrumentation: low pulsing strings, tight suspenseful percussion, a single sharp string hit reserved for the vent-breakthrough. Timeline: 0-2s: a low, quiet suspenseful pulse under the establishing shot. 2-4s: percussion tightens, quick scraping string hits under the digging. 4-6s: a sharp string stab synced to the squeeze through the vent. 6-8s: rapid, driving percussion under the shaft climb. 8-10s: tempo peaks, urgent strings under the rooftop sprint and drainpipe slide. 10-12s: a final surge of percussion under the raft launch. 12-15s: the pulse thins out and fades into the fog, ending on a sustained, unresolved low tone rather than a final chord - trailing into near-silence under the freeze-hold. Keep it tense, physical and driving throughout, never triumphant, never fully resolving. Do not imitate any existing melody. Add precise, short sounds synchronized to the key beats - scraping-metal on the vent digging, a soft body-squeeze grunt on the shaft entry, quick scrabbling hand-holds on the climb, a sharp slide-friction sound on the drainpipe, and a rhythmic paddle-splash fading into fog and silence at la niebla y el silencio at the very end.

Create a 15-second cinematic, photorealistic continuous-shot video based exactly on the reference image of “The Floating Night Market.” Preserve the original architecture, floating wooden market platforms, lantern designs, vendors, customers, boats, ocean, mountains, color palette, and overall composition. Do not redesign or replace any major elements. 0–3 seconds: Begin with a slow, smooth low-angle camera movement just above the dark ocean surface, approaching the floating night market. Hundreds of warm glowing paper lanterns gently sway in the night breeze. Their golden reflections shimmer naturally across the moving water. Small waves softly move around the floating platforms. 3–7 seconds: The camera slowly rises and moves forward through the market, revealing lively activity. Vendors naturally prepare food at small wooden stalls, gently stirring steaming pots and grilling food. Thin realistic steam rises into the lantern light. Customers walk casually across narrow wooden bridges, talking and browsing. Lanterns flicker subtly and sway with the wind. 7–11 seconds: Continue the same uninterrupted camera movement with a gentle cinematic arc around the market. Small traditional boats slowly pass underneath the floating platforms. Water ripples spread behind them. Food stalls glow with warm orange and amber light while the cool blue moonlight illuminates the surrounding ocean. The huge full moon remains visible in the background behind misty mountains. 11–15 seconds: Slowly pull upward and backward into a wider cinematic reveal, showing the entire floating night market surrounded by the vast ocean. Hundreds of lanterns form a glowing trail across the water. Reflections stretch and break naturally with the waves. Mist gently drifts around the distant mountains as the moonlight creates a magical atmosphere. End on a beautiful wide establishing shot. Visual style: ultra-photorealistic, cinematic fantasy, realistic human movement, realistic ocean and water physics, detailed wooden textures, natural lantern glow, volumetric moonlight, subtle atmospheric fog, realistic steam, shallow depth of field during close shots, cinematic 35mm photography, high dynamic range, extremely detailed, immersive scale, smooth professional camera movement. Motion: natural human gestures, subtle wind movement, gently swaying lanterns, flowing steam, moving water, realistic boat movement, no exaggerated animation. Camera: smooth stabilized cinematic camera, slow controlled movement, natural depth of field, gradual push-in → forward tracking → gentle arc → wide pull-back. One continuous shot with no cuts. Negative prompt: no scene changes, no cuts, no jump cuts, no camera shake, no distorted faces, no duplicated people, no warped buildings.

For the target video, at 0.00 seconds into the target video, (from [Shot 1]) is fully referenced. integrated_multimodal_description: [Shot 1] A 15-second, 16:9, cinematic photoreal war-action short based on , unfolding in one single continuous battlefield space centered on the abandoned armored vehicle roof and side. Keep the space physically readable at all times: hot steel, hatch, side fireline, dust, sparks, smoke, heat shimmer, metallic debris, and nearby fire reflections. Preserve the same adult female warrior: messy blonde hair, realistic sweat, dust, light abrasions, black cropped leather jacket, tactical thigh rig, tall boots, knee pads, and stable identity. Her sensuality is mature and restrained, coming only from body control, breathing, collarbone line, side face, and gaze. Use a grounded pseudo-one-take with hidden cuts, close handheld pursuit, and low gliding camera movement orbiting her relation to the vehicle surface, hatch, and side line. At 00:00.000-00:02.300, the camera glides ultra-low across the armored roof as rust, shell casings, dust, and sparks streak past. Her left palm slams onto the burning steel while her right hand carries the rifle as she cuts diagonally forward, slides on one knee, snaps the rifle up, and fires two short controlled bursts. She never freezes: she keeps pressing forward, borrowing leverage from the vehicle and shifting weight in one continuous chain. [Shot 2] At 00:02.300, the camera slides from the hand on steel past the thigh holster and engaged waist to the collarbone, neck, and half-side face. Firelight moves across her neck and jaw. Heat shimmer lifts hair strands near her lips. She never looks at the camera. Her eyes tighten first, then rise into aim. Sweat and dust hold the lashes together slightly. Brow movement stays minimal; the lower lids tighten, upper lids narrow, pupils remain stable, nostrils move with controlled breathing, and the lips stay slightly parted without widening. A short swallow passes through the throat, then neck and shoulders re-lock. At the aiming beat she says in a low tight voice: [English] Come on. Use a brief subtle slow-down here, then return to normal speed. [Shot 3] At 00:04.200, the camera moves into a semi-circling medium close shot. She keeps moving along the roof, completing one continuous chain of knee-slide, reach, recoil, shoulder turn, and rifle pressure while debris crosses foreground. On the third trigger pull, the rifle clicks empty with a sharp dry mechanical snap. Her reaction is microscopic: the gaze tightens for a split second, pupils pull in, the brow center deepens slightly, one mouth corner draws back, and the jaw muscle locks. Her breath shifts into one shallower quicker inhale. She immediately folds behind the half-open hatch. [Shot 4] At 00:06.600, in a tight cause-and-effect shot, she half-crouches behind the hatch. Though the rifle is empty, she keeps the muzzle high to fake suppression. Then two dull knocks sound from below. The camera follows her gaze downward. A bloodied hand reaches out from the hatch gap, and an enemy identification strip is visible on the sleeve. Her reaction is not pity or shock but rapid reassessment: her eyes drop to the hand, sweep to the marker, then return to the gap. The upper lid lifts slightly then presses down again. The brow center smooths into colder decision. Lips move from slightly open to pressed shut, lower lip drawing inward. The throat moves once, followed by the smallest downward nod. She shifts to a one-handed rifle grip and yanks the hatch with her free hand. [Shot 5] At 00:09.000, continue the pseudo-one-take into the angled vehicle side. She hooks the rifle sling through the hatch handle, turns sideways, and slides down the armored side using her body weight to wrench the hatch while kicking a nearby burning metal fragment into a leaking fuel trail. Every element stays linked in one action chain: shoulders, back, waist, legs, sling, hatch, and fireline. Her face is fully task-driven now; eyes stay on landing points, jaw locks briefly, cheek muscles tighten, and nostrils widen on short forceful breaths. The fuel catches and runs into a fast near-ground wall of flame, dangerous and close but not a giant explosion. The camera drops with her slide, and flame crosses the lens to create a hidden transition. [Shot 6] At 00:12.000, move into a vehicle-side medium close shot near half-body range. The wall of fire briefly blocks enemy sight. She bends into the hatch, drags out a wounded young soldier, and with the same motion presses his head down against her side with her forearm while moving forward along the vehicle. Give one very short lethal glance back to confirm the fire is masking them. In that glance, side face, neck line, collarbone edge, and fire-glazed jacket highlight flash together. Her breath is visible but controlled. The eyes show not softness but hard protective command. The gaze sweeps back once and returns immediately. The lip line presses flat, then opens only enough to say quietly to the soldier: [English] Stay low. Move. “Stay” is low and steady, “low” lands heavier, “Move” is short and direct. Her mouth closes immediately after, the corners draw inward again, and breath exits sharply through the nose. End as she pulls the boy into smoke and orange reflections, with the frame swallowed by smoke and firelight, no black screen. overall_soundscape: The sound field is driven by close weapon fire, the dry empty-chamber click, metal scraping, boots on armored steel, controlled breathing, hatch knocks, sling tension, fuel ignition, the low ground roar of a fast fireline, and distant blurred battlefield ambience. Keep the first half tight around palm-on

FORMAT: 15s | 16:9 | continuous cinematic sequence CONCEPT: Dark-fantasy sword duel inside a gigantic floating liquid-obsidian mirror surrounded by a pure white void. Reflections briefly move independently, creating deceptive attacks. CHARACTER LOCK: Obsidian Ronin: exact reference design, horned kabuto, black mane, dark/gold armor, heavy katana. Heavy, controlled, powerful. Inkshade Valkyrie: exact reference design, porcelain face, two-tone hair, silver-black gothic armor, dissolving cloak, twin blades. Fast, aerial, unpredictable. No redesign. STYLE: Luxury dark-fashion aesthetic, glossy black mirror, silver highlights, smoke, cracks, particles, cinematic motion blur. No blood, gore, guns, battlefield, idle poses, teleportation, hard cuts, or freeze frames. 0–3s White void. Black mirror materializes and ripples. Ronin and Valkyrie emerge from opposite reflections and collide immediately. Huge ripple; reflections continue fighting independently. 3–6s Low camera sweep. Ronin heavy slash → Valkyrie ducks and spins → reflections counter from opposite directions → Ronin blocks → Valkyrie X-slash. Cracks spread across mirror. Smoke forms: REAL OR REFLECTION? then shatters. 6–9s Mirror turns vertical. Both run across it. Ronin overhead strike → Valkyrie aerial dodge → lands behind him → Ronin pivots and blocks. Blades lock; mirror bends like liquid glass. Shockwave separates them. 9–12s Mirror explodes into floating fragments containing distorted reflections. Ronin and Valkyrie leap through them, destroying reflections. Fragments align into a giant black blade shape. Smoke forms: BREAK THE IMAGE → Valkyrie slices through it. 12–15s Brief stillness. Fragments rush together. Both charge. Ronin’s diagonal katana strike and Valkyrie’s spinning twin-blade cross attack collide center-frame. Mirror shatters into thousands of particles. Music cuts to silence. Smoke forms: ONLY ONE REMAINS. Their silhouettes fade as the white void consumes everything. MOTION: Constant action, clear impact/consequence, natural hair/cloak/particle physics. CAMERA: Smooth orbit → low sweep → rapid rotation → dramatic final push. AUDIO: Dark electronic-orchestral score, bass, cello, metallic impacts, blade whistles; silence at final collision. FINAL LOOK: Elegant, aggressive, surreal dark-fashion sword cinema.

Premium action-film title sequence beginning with a gigantic transparent glass monolith floating against complete blackness. A tiny projectile impacts the exact center and an intricate network of cracks instantly races across the entire surface. The camera pushes directly into one expanding fracture, traveling through the microscopic crystalline structure as tension builds everywhere. Suddenly the monolith violently detonates into millions of glass fragments. The camera performs a fast 360-degree orbital move through the suspended crystal storm as every shard reflects sharp beams of cinematic light. An invisible force begins pulling selected fragments together, constructing the enormous word "SHATTER" from overlapping razor-thin glass shards. The completed transparent typography refracts the entire environment like a giant prism before another pressure wave passes through it, producing thousands of secondary fractures. The letters explode outward directly toward the lens in spectacular ultra slow motion. Extremely detailed glass physics, realistic refraction and caustics, elegant brutality, premium Hollywood VFX.

15-second scientific HUD explainer, same visual system as a research console called “RENAL SYSTEMS SIMULATOR — MODEL HK-4n”. Warm off-white paper background, thin charcoal isometric grid, muted anatomical-grey 3D kidney with arterial red and venous blue accents, condensed technical typography, live telemetry. LOCKED UI FRAME: Top bar in condensed red caps: “RENAL SYSTEMS SIMULATOR” Subtitle: “NEPHRON DYNAMICS RESEARCH PLATFORM · SERIES HK” Status chips: FLOW IDLE / FILTER / PEAK · 92% · SIM ID NPH-118 · RUNTIME 00h 00m 15s · STATUS ACTIVE · OPERATOR DILUM, S. Left column live panels: - Glomerular filtration waveform - Filtration fraction / error rate / osmotic gradient chips - Cortical pressure map with DEPTH analog replaced by “CORTEX 8.2mm / MEDULLA 18.4mm / OSM 1200 mOsm” - Nephron actuator-style bar graph for afferent / efferent tone.

Extreme cinematic pyro title reveal beginning with a single glowing spark falling through darkness. The spark strikes a thin trail of fuel and instantly triggers a violent ignition racing across the frame faster than the camera can follow. Fire erupts into towering walls as the camera sweeps through twisting ribbons of flame, liquid fuel, incandescent embers and extreme heat distortion. Multiple streams collide and create a gigantic rotating fire vortex whose white-hot core begins ejecting molten metal. The glowing material stretches, folds and violently welds itself into the enormous word "BLAZE", initially completely incandescent before its exterior rapidly cools into cracked black steel. Flames continue raging through the hollow interior of every letter as the camera performs a fast cinematic orbit. Pressure suddenly builds beneath the surface, molten cracks race across the typography and the entire title violently ruptures into an overwhelming explosion of sparks, liquid fire and burning fragments. Photorealistic pyro simulation, brutal energy, premium theatrical VFX.

15-second experimental anime fashion film. Use @[character reference] for the character’s exact identity, outfit and rendering style. A pristine, uniform lemon-yellow cyclorama with a seamless matte floor. Flat, clean yellow throughout, free of grain, gradients and set dressing. 16:9. No text or logos. The character performs one fast, unconventional dance phrase: ankles weave while the torso stays suspended, a wrist flick ripples through both elbows into a chest pop, knees fold into a low corkscrew pivot, then a heel swivel unwinds the body into an off-balance editorial pose. Continue through asymmetric shoulder rolls, angular arm threading around the face and a sideways glide with the head counter-rotating toward the lens. Every sharp lock immediately releases into another surprising movement. Convincing weight, precise foot contact and expressive follow-through. Electric cyan and hot pink dominate the motion effects. Bold, opaque silhouette afterimages peel away from opposite sides of the body, replay the previous gesture a fraction late and slam back into alignment on each pose. Arm sweeps stretch them into broad curved ribbons; crossing steps weave pink and cyan trails around the ankles; rapid turns fan out overlapping screen-print impressions. At the strongest accents, oversized cyan and pink cutouts of the current pose slide across the foreground, briefly masking the lens. Keep the real character crisp and recognizable, with clean yellow visible between effect bursts. The camera dances in counterpoint: skim backward at ankle height through advancing footwork, whip upward around an outstretched wrist into an extreme face close-up, then use the passing forearm to cut into a rotating overhead view of the low pivot. Dive to a tilted low-angle full-body composition as the character rises. Orbit opposite the sideways glide, exaggerating hands and feet near the wide lens. Accelerate between compositions and brake hard on pose locks. Finish with a sudden forward lean toward the lens while enormous pink and cyan echoes continue leaning farther, sweeping past both sides of the camera. Snap wide: the character lands a final asymmetric pose as the colored echoes collapse precisely into the silhouette. Hard cut to black. 170 BPM broken beat, syncopated accents, fluid animation and razor-fast camera transitions. No slow motion or prolonged holds.

[0–3s] — THE RIDE Low cinematic tracking shot from behind. The girl rides her red bicycle along a quiet coastal road, guardrails beside her and the endless blue ocean beyond. Her skirt and loose strands of hair move naturally in the wind. Sunlight flickers across the road as she passes. [3–5s] — SOMETHING BEAUTIFUL Side shot as she suddenly notices a flock of white birds sweeping dramatically across the ocean. She slows down, smiles softly, and reaches into her backpack for a small instant camera. [5–8s] — THE PHOTOGRAPH She stops beside the overlook and raises the camera toward the ocean. As she takes the picture, the male character quietly walks into the far edge of the frame, completely unaware that he has just been captured in her photograph. [8–10s] — THE SURPRISE Extreme close-up of the photograph developing in her hands. The ocean appears first… then she notices the mysterious guy standing in the background of the photo. Her expression changes from peaceful curiosity to surprised amusement. [10–12s] — LOOK UP She slowly looks up from the photograph. Cut to the man a few meters away, standing by the guardrail with his backpack, looking directly at her. Wind moves his hair. He gives a subtle, almost playful smile. [12–15s] — THE LITTLE TWIST He walks toward her and gently points at the photograph, realizing he's in it. She laughs quietly. He gestures toward the road ahead as if asking, “Going this way?” She smiles, gets back on her bicycle, and he starts walking beside her. Final wide shot: They move together along the coastal road while the ocean stretches endlessly behind them. The little photograph remains visible in her hand as the camera slowly pulls back into the glowing blue-and-gold horizon. MOOD: spontaneous, beautiful, slightly mysterious, innocent romance, cinematic fate, natural chemistry. IMPORTANT: No exaggerated acting, no cheesy romance, no text, no logos, realistic physics and natural human movement.

Create a fast-paced, high-energy cinematic sports commercial featuring a professional female tennis player competing on a blue hard court. Scene & Camera: - Begin with an overhead bird’s-eye shot of her powerful serve. - Transition into low-angle tracking shots capturing her fast footwork and movement across the court. - Use intense close-ups of her focused face, hands, racket, and ball impact. - End with a dramatic golden-hour silhouette as she strikes the ball. Visual Style: Photorealistic, premium sports-commercial aesthetic, bright natural sunlight, subtle lens flares, crisp focus, realistic motion blur, dynamic camera movement, cinematic composition, 8K detail, 35mm film look, subtle film grain. Performance: Natural athletic movement, realistic tennis technique, accurate racket and ball physics, powerful swings, quick footwork, confident expressions, and believable body mechanics. Audio: Realistic tennis-court ambience, racket impacts, ball bounces, quick footsteps, and subtle cinematic sports sound design. No dialogue. Negative Prompt: Distorted hands, extra fingers, unnatural anatomy, incorrect tennis technique, floating racket, unrealistic ball movement, duplicated objects, face distortion, flickering, jitter, slow motion unless intentional, CGI appearance, low detail, watermark, text, or logos.

Duration: 15 seconds Aspect ratio: 9:16 Reference: @image 1, lock the protagonist's face, hairstyle, body, and original look from the reference image; do not redescribe or change the outfit Audio: harbor water sounds, light wooden dock creaks, apparatus squeezing sounds, footsteps striking water, splashing, gradually strengthening wind, the protagonist's natural laughter; no dialogue, no narration, no subtitles Overall style: hyper-realistic phone footage, extreme water stunt short film, golden hour natural light, slow-to-fast pacing, realistic water physics, slight handheld feel GLOBAL CONTINUITY Setting: New York harbor at golden hour, clear sky, calm sea. The Statue of Liberty is visible in the center distance, with the city skyline on the right. The camera is positioned on an old wooden dock, with some planks, metal fasteners, and worn edge guards visible on the right side of the frame. Main subject: @image 1 is the sole protagonist. The person's appearance and original styling remain consistent throughout. Water-walking apparatus: The protagonist's legs are each inserted into two giant transparent water-walking devices. The devices extend to around the knees, with wide oval buoyant foot platforms at the bottom. The transparent shells catch a light golden refraction in the sunset. Both devices remain identical in size, shape, and transparency throughout. They are water stunt apparatus, not to be redesigned as part of the character's costume. CAMERA CONTINUITY The three SHOTs are time phases of one continuous take — no scene or camera position changes. The cameraperson remains on the dock, shooting from behind the protagonist. It starts as a medium-wide shot; after the protagonist enters the water, the camera tilts slightly down; as she accelerates, it smoothly pulls back and tilts up to recompose, keeping the protagonist, the wake, and the Statue of Liberty on the same central axis. PHYSICAL ENGINE Slow stepping: When the transparent device's bottom touches the water surface, it partially sinks, producing circular ripples and light splashes. The protagonist needs to bend her knees and spread her arms to maintain balance. High-speed running: The left and right devices alternately strike the water surface. Each step produces splashes shooting sideways and backward, gradually forming a long, symmetrical V-shaped wake behind her. Each step must include: Lift leg → swing forward → contact water surface → device sinks → splash ejection → lift again. SHOT 1 (00:00-00:05) Testing the water Subject: The protagonist from @image 1 stands at the edge of the dock, back to the camera, facing the Statue of Liberty. Action: 00:00-00:01.50: The protagonist looks down at the devices on her feet and the water, leaning slightly forward, slowly adjusting her center of gravity. 00:01.50-00:03.20: The protagonist lifts her left leg high, slowly extending the giant transparent device out over the dock. Her right leg remains on the wooden planks for support. The wide bottom of the left device contacts the water surface, first pressing a shallow depression, then partially submerging, creating a ring of fine ripples. 00:03.20-00:05.00: The protagonist attempts to shift her weight onto her left leg, and her body suddenly tilts left. Her arms quickly spread open, her right leg still angled against the dock edge, forming a straddling stance with one foot in the water and one on the dock. She sways left and right, nearly losing balance, but does not fall in. Environment: The sea remains calm, with only expanding ripples around the device. The sunset lights the edge of the transparent device from the right. Camera: 24mm phone wide-angle, rear medium-wide shot, slight forward movement with a downward tilt, keeping the full body and devices in frame. Style: Realistic, cautious, slightly comedic — the body must react naturally to the device's weight. Constraints: No running at the start; the first device must step into the water alone first; splashes must not be excessive. SHOT 2 (00:05-00:10) Finding balance and sudden acceleration Subject: The protagonist gradually moves the second transparent device from the dock into the water. Action: 00:05-00:06.50: The protagonist lifts her right leg high and places the second device into the water. Both wide bottoms now partially press into the sea surface, creating two sets of overlapping circular ripples. She bends her knees and spreads her arms, sways once, then gradually returns to an upright stance. 00:06.50-00:07.50: The protagonist takes two small experimental steps forward. Each step slowly lifts a device and gently presses it into the water, producing only minimal splashes. 00:07.50-00:08.50: The protagonist pauses briefly, turns her head to look back over her left shoulder at the camera, flashing a smug, playful smile and letting out a natural laugh. 00:08.50-00:10.00: She quickly turns back forward, leans her body in, and her arms enter a running swing. The first step is a powerful push against the water, the second step visibly accelerates, and splashes grow from small to large. Environment: The wooden dock remains on the right side, with the protagonist gradually increasing her distance from it. The Statue of Liberty stays directly ahead. Camera: The camera remains on the dock, smoothly pulling back and tilting slightly up to recompose — it does not follow into the water. Style: A sharp contrast in rhythm — from clumsy testing to sudden smooth acceleration. Constraints: The look-back smile must be included; a brief pause during the look-back; acceleration must begin only after turning back forward. SHOT 3 (00:10-00:15) Sprinting across the water Subject: The protagonist sprints across the sea surface toward the Statue of Liberty. Action: 00:10-00:12.50: The protagonist runs at a steady, fast pace, with the left and right devices alternately striking the water in continuous succession. Each landing produces bright splashes that spray sideways and backward. Her body leans slightly forward, arms swing naturally in alternation, and stride length gradually widens. A continuously extending and widening V-shaped wake forms behind her. 00:12.50-00:14.20: The protagonist maintains her speed, gradually stops swinging her arms, and extends them outward to both sides, slightly raised, forming a free, exhilarated shallow-V pose. Her legs continue alternating in a running motion — the stepping cannot stop. The sunset turns the splashes at her feet into a pale golden mist. 00:14.20-00:15.00: The protagonist continues moving into the distance, rapidly shrinking in the frame. The camera tilts slowly upward, allowing more sky to fill the frame, while keeping the protagonist, the Statue of Liberty, and the V-shaped wake on the same central axis. The shot ends while she is still running — she does not reach the island, does not stop, and does not look back. Environment: The calm sea is carved by a clear wake behind the protagonist, while the surrounding water remains smooth. The distant landmark and skyline remain stable in position. Camera: Fixed position on the dock, smooth pull-back with a slight upward tilt. In the latter half, it does not chase closer to the protagonist and does not switch to aerial footage. Style: Realistic high-speed splashes, golden backlighting, strong depth and sense of speed — like an unbelievable extreme challenge captured on a phone. Constraints: The protagonist must continuously alternate stepping; she must keep running after spreading her arms; the transparent devices cannot disappear or deform. --- Negative: Redesigned character clothing, additional garments, style drift, facial drift, hair change, character replacement, ordinary shoes, device disappearing, device shrinking, device turning into a surfboard, jet ski, skateboard, or boat, sprinting at the very beginning, omitting the single-foot water test, omitting the swaying, omitting the look-back smile, spreading arms too early, falling into the water, tripping, sinking, injury, colliding with the dock, standing on the shallow bottom, sliding without steps, hovering, flying, teleporting, feet locked in place, incorrect gait, same-side arm and leg movement, soles not contacting the water surface, devices not sinking at all, devices penetrating through the water, splashes appearing prematurely, no splashes, tsunami, giant water column, splashes blocking the subject, wrong wake direction, wake suddenly disappearing, Statue of Liberty moving, cityscape deforming, horizon tilting, extra boats blocking the subject, camera cuts, frontal tracking shot, aerial shot, camera entering the water, sudden scene changes, anime rendering, game CGI, plastic skin, cheap green screen, excessive slow motion, extra people, extra arms, extra legs, reversed joints, melting body, character duplication, subtitles, on-screen text, brand logos, watermarks, narration, additional dialogue

Architectural Formation Pencil Shave Animation. Motions: Bounce + Trim Path + Spring + Rotation + Posterize

Create an explosive, motion-graphics-driven character reveal trailer in 16:9, exactly 13 distinct cuts, 24fps. The character is the exact girl from the provided reference image: preserve her face, proportions, hairstyle, outfit, materials, accessories and colors throughout; never redesign her. This film is 80% bold graphic design in motion and 20% character action: giant kinetic typography, hard-edged shapes, diagonal wipes, flat color fields, barcode strips, UI ticks, halftone, speed lines and shutter flashes. Palette: ice blue, cobalt, white, silver-grey, black. Style: premium AAA motion-graphics title sequence x streetwear campaign film. Every graphic element moves fast and snaps hard on the beat. CUT 01 | 0.00-1.00s - Pure graphics: a vertical ice-blue lightning slash rips a black field in half, white shards spray sideways, a barcode strip races left-to-right and breaks; the letters slam in one after another with heavy impact shake and chromatic aberration. CUT 02 | 1.00-2.00s - The letters collapse into a receding tunnel of nested rectangles; she bursts through the vanishing point in a low, aggressive sprint, frost particles peeling off her sneakers, camera whipping to follow. CUT 03 | 2.00-3.10s - She plants both hands on a giant rotating block of white typography and pendulum-swings underneath it, kicking the letters into spinning fragments that trail ice-blue streaks; whip-pan as she exits frame right. CUT 04 | 3.10-4.00s - Full-bleed diagonal color fields (cobalt / white / ice-blue) wipe in sequence; she appears only as a high-contrast silhouette performing a single continuous wall-kick into a mid-air twist. Huge horizontal text OVERDRIVE scrolls in the opposite direction of her travel. CUT 05 | 4.00-5.10s - She ricochets off a towering stack of stacked words reading KEEP MOVING, each bounce sending a letter flying; camera tracks her in a tight orbit as the stack topples, then snap-zooms to her determined profile. CUT 06 | 5.10-6.00s - Hard cut to a stark white editorial card with enormous black DROP and a single cobalt underline; she drops from the top of frame, lands on the word, compresses it like a trampoline and launches again; the type rebounds with a spring distortion. CUT 07 | 6.00-7.00s - Silver-grey field crossed by a thick black chevron; she cartwheels along the chevron in four stroboscopic ghost frames, each ghost a different palette color; giant outlined text SPIN rolls 360 degrees in perfect sync with her rotation. CUT 08 | 7.00-8.00s - Kinetic type barrage: the words SHARP / QUICK / FRESH / COLD slam in one per beat with shutter flashes and camera shake while she power-slides on one knee across the foreground, jacket flaring, frost bursting from the platform sneakers. CUT 09 | 8.00-9.00s - Black frame, giant white isometric cubes tumbling in 3D space; she sprints across the tops of the cubes, plants a foot and launches into a tight corkscrew, freezing at the apex; a thin ice-blue reticle and data ticks lock onto her silhouette. CUT 10 | 9.00-10.10s - Freeze releases: she dives toward camera through successive flat-color planes that peel away like torn posters, each plane revealing a larger fragment of her name; a sneaker wipe across the lens ends the shot. CUT 11 | 10.10-11.10s - Rapid-fire graphic cards: five full-screen layouts snap past with hard cuts — each a different bold composition (offset type, oversized chevron, barcode overlay, slashed crop, halftone burst) showing her in a unique athletic beat (handspring, low dash, mid-air reach, crouched ready stance, walking away). Numbers 01–05 punch in the corners. CUT 12 | 11.10-13.00s - Hero moment on a clean white cyclorama: she lands a final twisting aerial dead center in slow motion, plants, stands tall with one hand in a pocket, and a shockwave of concentric ice-blue rings, wind streaks and shattered letterforms blasts outward; brief iconic freeze with her faint confident expression, then overexpose to white. CUT 13 | 13.00-15.00s - Final identity card: enormous black wordmark dominates a pale white field with translucent ice-blue rings, technical arcs, halftone and a rough black circular emblem containing a ghosted snow-crystal / barcode motif; she stands relaxed overlapping the letters, wind rippling her jacket; one last ice-blue pulse sweeps through the typography and a frost-ring flash punctuates the end. Editing: extremely aggressive rhythm — hard cuts on every beat, graphic matches, whip pans, snap zooms, stroboscopic freezes, foreground wipes, RGB splits, shutter flashes, impact shakes and speed ramps; every cut must feel compositionally different; typography is always fully readable before the character overlaps it. No weapons, no combat, no fire; all energy comes from motion design, wind, frost, glass and her parkour-style athleticism. BGM: hard-hitting electronic / drum-heavy future bass with aggressive drops, risers, sub hits and glitch fills locked to every cut; sneaker impacts, whooshes, glass shatters and typography slams are rhythmic sound-design elements. Peak at CUT 12 and end with a cold electronic logo stinger. Premium AAA quality, anime-inspired cinematic rendering, stylish and explosive, strong graphic-design identity, consistent character design, exactly 13 cuts.

Create a 15-second cinematic 3D animated video based exactly on the provided storyboard. Keep the same characters, faces, outfits, proportions, and environment consistent throughout the entire video. The main characters are a cute blonde little girl wearing a pink floral dress and a fluffy white, blue-eyed cat wearing a small collar with a bell. 0–2 sec: The white fluffy cat comes close to the girl and tries to get her attention. The girl looks annoyed and turns her face away. 2–4 sec: The cat gently asks for a kiss with cute expressive gestures. The girl refuses, crosses her arms, and looks upset. The cat looks confused and sad. 4–6 sec: The girl walks to the sofa, sits down, opens a colorful storybook, and starts reading. The cat follows her and sits beside her. They appear to communicate through cute facial expressions and simple gestures. 6–8 sec: The cat tries to look at the book and talk to her, but the girl becomes annoyed and moves slightly away from the cat. The cat looks apologetic. 8–10 sec: The cat tries to make peace and gently approaches her. The girl remains angry, stands up, walks toward her bedroom, and closes the door. 10–12 sec: The fluffy white cat walks to the closed bedroom door and gently knocks on it repeatedly with its paw. The cat waits patiently outside. 12–13.5 sec: The door slowly opens. The girl looks at the cat with a slightly softened expression. The cat looks happy and hopeful. 13.5–15 sec: The cat gently kisses the girl's cheek. The girl finally smiles, hugs the cat, and kisses the cat back. End the video on this warm, emotional reconciliation moment. Do not show “The End” text or any title card. Style: high-quality cinematic 3D animation, adorable expressive characters, soft realistic fur, warm cozy home lighting, natural body movement, detailed facial expressions, smooth camera transitions, shallow depth of field, emotional storytelling, gentle playful atmosphere, polished animated-film quality. Important: Keep the cat white and fluffy in every shot, maintain the same girl and cat throughout, no character changes, no extra characters, no text overlays, no subtitles, and no “The End” screen.

kept the whole sequence to just four colors, and I really like how smoothly it handles the fast 2D motion and transitions.

FORMAT: 9:16 vertical, 15 seconds STYLE: Ultra-realistic luxury UGC, high-end fashion campaign, cinematic studio lighting, sophisticated, minimal, premium, photorealistic 4K. PRODUCT CONSISTENCY — CRITICAL: Use the uploaded handbag images as the exact and only product reference. Preserve the handbag's exact shape, proportions, black color, smooth material, long structured handles, side bow/tie details, hardware, stitching, opening, and CHARLES & KEITH logo. Do not redesign, resize, recolor, add/remove details, or change the construction. The same handbag must remain perfectly consistent throughout every shot. 🎬 SHOT-BY-SHOT 0–2s — UNBOXING HOOK Close-up UGC shot of a stylish woman opening a CHARLES & KEITH black box on a clean, elegant table. She lifts the lid and gently pulls back the white dust bag/tissue paper, revealing the exact black handbag inside. Natural hand movement, satisfying packaging sounds, warm soft lighting. On-screen text: "Okay… this is even prettier in person." 2–4s — HERO REVEAL Smooth cinematic camera movement from left to right, revealing the handbag's full silhouette and distinctive oversized handles. Subtle realistic shadow beneath the bag. Premium fashion-commercial lighting. 4–6s — DETAIL SHOT Macro close-up of the CHARLES & KEITH logo and smooth black finish. Camera gently racks focus from the material to the logo. Highly detailed texture, realistic reflections, shallow depth of field. 6–8s — SIDE DETAIL Three-quarter angle matching the uploaded reference image. Slowly orbit around the bag to showcase its structured shape, side construction and elegant tie details. Keep the product geometry identical to the reference. 8–11s — UGC LIFESTYLE MOMENT A stylish woman wearing a minimalist black blazer and tailored trousers naturally picks up the handbag from the studio surface. Frame primarily focuses on the handbag and hands rather than her face. The long handles fall naturally as she lifts it. 11–13s — CARRY SHOT Close-up tracking shot as she carries the handbag beside her. Soft studio-to-fashion-editorial transition, subtle movement, natural hand interaction, realistic material behavior. 13–15s — FINAL HERO Return to a clean front three-quarter product shot. The handbag is placed elegantly on the surface while the camera slowly pushes in. Soft luxury lighting, beautiful shadow, crisp product details. On-screen text: "Timeless. Effortless. Yours." 🎥 CAMERA & QUALITY Smooth controlled camera movements, macro lens details, shallow depth of field, realistic reflections, soft diffused key light, subtle rim lighting, natural shadows, premium editorial composition, realistic hand movement, physically accurate materials, no artificial CGI appearance, no excessive transitions. AUDIO: Soft luxury fashion beat + subtle tissue-paper crinkle + gentle handbag placement sound. No distracting music. NEGATIVE PROMPT: No product redesign, no altered proportions, no different handbag, no extra straps, no missing handles, no distorted logo, no warped geometry, no floating objects, no plastic-looking material, no excessive gloss, no shaky footage, no cartoon/CGI appearance, no unrealistic hands, no face distortion, no text glitches.

About MiniMax H3

MiniMax H3 is the flagship of MiniMax's Hailuo video line, and its defining trait is that it is genuinely multimodal on the way in and complete on the way out. You can start a generation from a text description, a reference image, an existing video clip, an audio track, or a combination of them — and the result arrives with native stereo sound generated alongside the picture, not dubbed on afterwards.

That combination makes it the model to reach for when the clip has to feel finished: ad spots where the ambience sells the product, story scenes where footsteps and room tone carry the mood, image-to-video shots where a still photograph needs to come alive with believable motion and sound. It inherits the physical realism the Hailuo line is known for, and follows camera direction — dolly, orbit, handheld — with unusual obedience.

If you have used Hailuo 02, H3 will feel familiar but less forgiving of vagueness. The older line rewards a short scene description and fills in the rest; H3 gives you six or seven independent levers — subject, action, setting, camera, light, sound, and the input modality itself — and hands each unpulled lever back to its own defaults. More control is only an advantage if you actually spend it.

The practical consequence is that a MiniMax H3 prompt is closer to a shot list than to a caption. A prompt that reads "a woman walking in the rain, cinematic" gets you a competent, anonymous clip. A prompt that names the lens, the direction of the walk, the camera's move relative to her, the quality of the light, and what the rain sounds like on what surface gets you a shot you could actually cut into something.

Because H3 accepts so many kinds of input, the prompt is what tells it which job to do — and vague prompts waste exactly the control that makes it strong. The gallery above collects tested MiniMax H3 prompts with their real generated videos, so you can copy a structure that already works and swap in your own subject, motion, and soundscape.

Everything on this page is free to copy. There is no sign-up, no paywall, and no watermark on the prompt text — take the structure, change the nouns, and run it wherever you have access to the model.

How to write MiniMax H3 prompts

1Structure the prompt as subject → action → setting → camera → light and mood → sound. H3 reads all six layers; leaving one out means the model decides it for you.
2Write it as a shot, not as a caption. "Cinematic" and "high quality" are the two least useful words you can spend — replace them with the specific thing you mean: the lens, the grade, the time of day, the weather.
3Use real camera vocabulary: "slow dolly-in", "handheld tracking shot", "orbit around the subject". H3 follows named camera moves far more precisely than vague phrases like "dynamic shot".
4For slow motion, name it as a property of the footage rather than of the subject: "filmed in slow motion, water droplets hanging in the air" works; "she moves slowly" just makes her walk slowly at normal speed. If you want a speed change mid-clip, say where it happens — "real time, then ramps into slow motion as the glass hits the floor".
5Direct the audio explicitly — sound is native, so it listens: "rain on a tin roof, distant thunder, no music" or "upbeat synth track builds under the voiceover". Unprompted audio defaults to generic ambience.
6Name the surface, not just the sound. "Footsteps" is generic; "boots on wet gravel" gives the model the material to synthesize. The same trick works for everything from "rain" to "engine".
7If you want no sound at all, say so — "no music, no dialogue, ambient room tone only". Silence is a direction H3 will follow, but only if you give it.
8When starting from a reference image, describe only the motion and the camera — the image already fixes subject, style, and framing, and re-describing them invites drift.
9Give each generation one continuous action beat. A clip that tries to cover three story moments blurs all of them; chain separate generations when the story needs more beats.
10Freeze your look in a reusable clause — film stock, color grade, lens character — and keep it identical across a campaign so every clip cuts together.
11To hold a character across shots, feed the same reference image into each generation rather than re-describing the person. Text descriptions of faces drift between runs; an image does not.
12When a result misses, change one layer and regenerate rather than rewriting the whole prompt. Rewriting everything makes it impossible to learn which clause was actually responsible.

Frequently asked questions

How do I write a good MiniMax H3 prompt?

Write it as a shot list, in this order: subject, action, setting, camera move, light and mood, sound. H3 reads each of those as a separate instruction, so every layer you leave blank is a layer the model fills in with its own default. Keep one continuous action per generation, use real camera vocabulary for the move, and name the audio explicitly. Every prompt in the gallery above follows that shape — the fastest way to learn it is to copy one and swap in your own subject.

Is MiniMax H3 free to use?

The prompts on this page are free — copy any of them with no account and no paywall. Access to the model itself runs through MiniMax's Hailuo AI app and the MiniMax open platform API, and their current plans and free-tier terms are set on MiniMax's side, so check there for what a run costs today.

What is MiniMax H3 best at?

Clips that need to arrive finished: video and stereo audio generated together, from whatever input you have — text, a still image, an existing clip, or a soundtrack. Its physical realism and precise camera-following make it a strong pick for ads, cinematic single takes, and image-to-video work.

Does MiniMax H3 generate sound?

Yes — stereo sound is generated natively with the picture, not added afterwards. You get the most out of it by directing the mix in the prompt: name the ambience, the effects, and whether you want music. If you say nothing, you get generic ambience.

How do I get slow motion out of MiniMax H3?

Describe slow motion as a property of the footage, not of the subject. "Filmed in slow motion" or "high-speed camera, slow-motion playback" changes how the clip is shot; "she moves slowly" only makes the subject sluggish at normal speed. Pair it with a detail that only reads in slow motion — spray, dust, fabric, hair — so the effect has something to show, and name the moment if you want the speed to change mid-shot.

Can I start from an image or an audio track instead of text?

Yes. H3 is multimodal on input: a reference image can define the subject and framing, a clip can be extended or restyled, and an audio track can drive the scene. When an image carries the look, keep the text prompt focused on motion and camera only.

How is MiniMax H3 different from Hailuo 02?

They are two generations of the same Hailuo video line. Hailuo 02 takes a short scene description and fills in most of the decisions for you. H3 is multimodal on input, generates its stereo audio natively with the picture, and exposes far more of those decisions as things you control — which means it rewards a detailed prompt and punishes a lazy one more than the older line did.

Why did MiniMax H3 ignore part of my prompt?

Usually because the prompt asked for more than one thing at once. H3 handles a single continuous action beat well; a prompt covering three story moments gets averaged into a blur. The other common cause is re-describing what a reference image already fixed — when the image says one thing and the text says another, the result drifts. Cut the prompt to one beat, change one layer at a time, and regenerate.

Where can I use these MiniMax H3 prompts?

H3 is available through MiniMax's Hailuo AI app, and developers can access it via the MiniMax open platform API. Copy any prompt from this page, paste it there, and swap in your own subject, camera move, or soundscape.

Related models

Hailuo 02

MiniMax's Hailuo video model with standout physical realism.

Speech 2.5

MiniMax's multilingual voice synthesis model.

Seedance 2.0

ByteDance's #1-ranked video model — multi-shot direction with native lip-sync and spatial audio.

Seedance 2.5

Seedance 2.5 is a next-gen AI video model that generates continuous, synchronized 30-second 4K clips from a single prompt.

Browse AI Video Prompts All models