| English | 简体中文 | Português (Brasil) | हिन्दी | 日本語 | 한국어 |
|---|
A curated gallery of reproducible MiniMax H3 prompts, paired with their official inputs and outputs.
The first edition contains 20 cases verified against MiniMax's official guide and official X posts.
Every output plays in GitHub's native player, making the collection practical for studying prompt structure and reference bindings.
- Brand Films & Cinematic Content
- Motion Design & AI Storytelling
- Product, UI & Game Concepts
- Animation & Stylized Visuals
- Omni Reference & Performance Transfer
- Precise Multimodal Editing
- Resources
- Contributing
- License
Brand campaigns, cinematic teasers, and fashion-led visual direction.
A binocular viewfinder scans four keyframes in a restrained MiniMax brand film.
Input Images:
![]() Image 1 |
![]() Image 2 |
![]() Image 3 |
![]() Image 4 |
Prompt:
Use Images 1–4 as sequential keyframes, seen through a vintage binocular viewfinder searching for the MINIMAX installation. Open out of focus with subtle handheld shake, then push in quickly and rack focus onto Image 1. Between keyframes, use fast binocular-scan transitions with whip movement, motion blur, optical smearing, and brief exposure flicker. Cut at peak blur, then settle and snap back into focus. Keep the twin circular lens mask absolutely fixed throughout: identical position, scale, feathered black vignette, and edge softness, with no warping or drift. Only the image inside the mask may move.
In Image 2, let the fabric move gently in the wind while the MINIMAX lettering follows the folds and remains legible. In Image 3, the subject should feel like a stylish passerby caught by chance, walking, turning, and swinging their arms naturally. In Image 4, the subject adjusts their glasses or lifts their chin slightly with a cool, effortless fashion-campaign attitude.
Red typography should resolve with the focus: begin slightly blurred and at low opacity, then fade into clarity over 0.3–0.5 seconds. A subtle vertical slide or slight tracking expansion is allowed. Fade it out before the next transition or let motion blur carry it away. No spins, bounces, or large fly-ins/outs.
Visual language: a voyeuristic, Wes Anderson-inspired 35 mm film look with fine grain, soft highlight halation, restrained color, and red typographic accents. Minimal, premium, lightly playful. Do not add people, vehicles, buildings, or logos. Preserve the core composition and the MINIMAX installation exactly.
video-001-binocular-installation.mp4
Source: MiniMax — Official H3 guide
A monumental gateway, a lone figure, and distressed title cards build a compact mystery teaser.
Input Images:
![]() Image 1 |
![]() Image 2 |
Prompt:
Photoreal cinematic treatment, high-contrast lighting, and tight pacing. Use Image 1 for the overall mood and visual language; use Image 2 as the protagonist reference.
Shot 1 — Ultra-wide establishing shot. A colossal circular cosmic gateway nearly fills the frame. The protagonist appears only as a tiny figure from behind, positioned low and slightly right of center. Wet ground reflects the light; the center of the gateway is pitch black. Slowly push the camera forward. A large title emerges from the edge of the darkness, resolving from soft blur into sharp focus: “THE STARS WERE LISTENING.” Set it in an extremely condensed, heavy, all-caps face, colored dark crimson and rust red, with light grain and mist-softened edges.
Audio: a deep sub-bass pulse, distant metallic resonance, and one restrained hit as the title locks into focus. → Hard cut.
video-002-cosmic-gateway-teaser.mp4
Source: MiniMax — Official H3 guide
A platinum-blonde model moves through a blaze-lit fashion short with analog glitches and hard cuts.
Input Images:
![]() Image 1 |
![]() Image 2 |
Prompt:
Use Image 1 as the reference for texture and mood, and Image 2 for the subject’s appearance. Generate a 15-second, 16:9 fashion short. Preserve the subject’s identity: long platinum-blonde hair, narrow black vintage sunglasses, a glossy black patent-leather trench coat, a cool, self-assured expression, and orange firelight reflected across the coat.
Style: fast-cut fashion film on analog stock, set against a nighttime blaze with black smoke and orange-red flames. Layer in VHS glitches, CCTV signal interruptions, 1990s film grain, scanlines, chromatic aberration, light leaks, flash-to-white transitions, and subtle frame jitter.
video-003-firelit-analog-fashion.mp4
Source: MiniMax — Official H3 guide
Narrative motion, genre storytelling, and editorial rhythm.
Live action and luminous hand-drawn animation meet inside a small kitchen at sunset.
Prompt:
15 seconds, 16:9 landscape. Blend live-action footage of a small kitchen at dusk with hand-drawn luminous animation. The last sunset light lingers at the window. The lived-in kitchen contains an old wooden table, a half-washed mug, a lightly fogged glass bottle, and a hanging dish towel.
Shoot as if someone is filming one-handed on a phone: subtle hand tremor, hesitant close-focus pulls, backlit exposure breathing, and slightly coarse noise in the shadows. It should feel like an astonishing event captured in a rush at home, not a carefully dressed commercial.
Do not show giant eyes, split mouths, fangs, threatening behavior, lunges, sudden black frames, or jump scares. Use only room tone, cloth friction, a soft mug clink, faucet drips, the camera operator’s footsteps and quiet breathing, plus gentle electronic tones and tiny vocalizations from the drawn creatures.
video-004-hand-drawn-light-kitchen.mp4
Source: MiniMax — Official H3 guide
Dark-pop performance footage takes on the grain, typography, and abrasion of a scanned zine.
Input Images:
![]() Image 1 |
![]() Image 2 |
Prompt:
Style: dark-pop / cyber-grunge / rap music video with photoreal high-fashion polish and the texture of a scanned film magazine—high contrast without looking cheap. Reference late-1990s to early-2000s indie magazines, photocopies, film scans, underground-music posters, and zine collage. Add coarse grain, subtle gate weave, halftone dots, rough print edges, and slight scan misregistration. Keep the edit fast and use hard cuts only—no fades or soft transitions. Match the typographic treatment and surface texture of the reference images.
video-005-cyber-grunge-rap-editorial.mp4
Source: MiniMax — Official H3 guide
A cold, nocturnal bamboo forest frames a restrained martial-arts investigation.
Input Images:
![]() Image 1 |
![]() Image 2 |
Prompt:
A 16:9 cinematic wuxia mystery set in a bamboo forest at night. Use a low-saturation palette of cold blue, ink green, charcoal, and gray. Thin mist fills the forest and fine snow drifts through the air. The mood is austere, lethal, and controlled, with the tension of a martial-arts sect investigating a case and exchanging secret intelligence.
Deep in the forest, dense vertical bamboo fills the background while cold white mist-light glows in the distance. Soft, out-of-focus leaves partially obscure the foreground, creating the sense of watching from within the grove. A cool, soft front-side key lights the actors’ faces; backlight keeps the foreground dark and the distance luminous. Use shallow depth of field so leaves, snow, and bamboo dissolve into soft bokeh.
Prioritize facial close-ups and measured shot/reverse-shot coverage. Keep the rhythm restrained but tense. Photoreal period-drama production value, cinematic lighting, and no modern elements. No subtitles, on-screen text, watermarks, modern clothing or architecture, animation styling, over-smoothed skin, bright daylight, or comic performance.
video-006-wuxia-bamboo-forest.mp4
Source: MiniMax — Official H3 guide
A 9:16 short-drama teaser stages an intimate confrontation between two locked lead identities.
Input Images:
![]() Image 1 |
![]() Image 2 |
Prompt:
Create a 15-second, 9:16 live-action vampire-romance teaser for an international short-drama audience. Use Image 1 for the leads’ appearance and Image 2 for the setting. Preserve both identities throughout and maintain premium live-action production value.
Story: an innocent human woman strays into a forbidden wing of an old castle and awakens a sleeping vampire noble. He senses that she carries a trace of an ancient war, which sparks dangerous fascination and a possessive need for control. She fears him but refuses to submit completely and pushes back against his dominance.
Style: ReelShort / DramaBox vampire romance—darkly romantic, fate-bound, oppressive, and charged with dangerous attraction, with a strong hook and a high-impact turn. Keep it polished, restrained, and tightly paced like the opening 15 seconds of a breakout series. No gore, cheap horror, Halloween styling, or modern street aesthetic.
Compose for TikTok / ReelShort / DramaBox. Favor medium-close shots, close-ups, and extreme close-ups that emphasize faces, eye contact, pressure, and relationship tension.
video-007-vertical-vampire-romance.mp4
Source: MiniMax — Official H3 guide
Product presentation, interface motion, and playable-world concepts.
A severe white-cyclorama fashion campaign uses brisk edits and sculptural eyewear poses.
Input Images:
![]() Image 1 |
![]() Image 2 |
![]() Image 3 |
Prompt:
Create a premium 9:16 fashion-eyewear commercial. Match the reference video’s shot rhythm, edit speed, white-cyclorama look, and severe fashion attitude. Use a seamless minimal white studio with clean, bold, avant-garde art direction worthy of a global luxury campaign.
Use Image 1 for the key visual: two full-body female models, one Black and one white, preserving their elevated wardrobe, body language, studio lighting, runway presence, and cool attitude. Use Image 2 for facial details. Both models wear futuristic luxury eyewear based on Image 3: wraparound curved lenses, a sharp cat-eye/goggle hybrid silhouette, mirrored reflections, streamlined temples, and the finish of a premium fashion accessory.
video-008-premium-eyewear-commercial.mp4
Source: MiniMax — Official H3 guide
A black ergonomic chair receives a controlled 360-degree feature visualization in a premium office.
Input Images:
![]() Image 1 |
![]() Image 2 |
Prompt:
Present a black Herman Miller ergonomic chair in a premium office with a full 360-degree product reveal. Cut to macro views of the breathable mesh back with airflow visualization, an engineering animation of the lumbar support and ergonomic curve, and demonstrations of multidirectional armrest and seat-height adjustment. Show designers, developers, and creative professionals working comfortably over long sessions. Include a 3D skeletal-support visualization that communicates all-day comfort, plus refined interior styling. End with the line: “WHERE INSPIRATION MEETS COMFORT.” Keep the direction minimal, cool-toned, professional, futuristic, and slow-paced. Use Image 1 for feature details and Image 2 for the product.
video-009-ergonomic-chair-reveal.mp4
Source: MiniMax — Official H3 guide
A performance-product page combines forceful typography, fast scrolling, and high-impact hover states.
Input Images:
![]() Image 1 |
Prompt:
Create a dynamic product-landing-page UI/UX demo inspired by Nike’s digital language, built around the product in Image 1. Use oversized, bold, italicized sans-serif typography and backgrounds that combine speed-driven light streaks with dark carbon fiber or breathable performance-mesh textures. Show a smooth, fast, powerful scroll through the page, plus high-impact hover interactions with scale-ups and color inversion.
video-010-nike-inspired-landing-page.mp4
Source: MiniMax — Official H3 guide
Stylized animation, character promotion, and game cinematics.
A locked character reference and storyboard become a continuous Chinese-inspired 3D sequence.
Input Images:
![]() Image 1 |
![]() Image 2 |
Prompt:
Use Image 2 as the locked character reference. Preserve the half-up long black hair, openwork silver crown, indigo ribbon, layered pale hanfu, translucent blue outer robe, deep-blue sash, silver floral fastener, and long tassels. Use Image 1 for storyboard order and pacing.
Render in high-quality 4K, 16:9 Chinese-inspired 3D with cinematic xianxia production value: intense, solemn, and shaped by destiny. Follow the storyboard beat by beat, with natural camera movement and seamless transitions—never a slideshow. Show the face only in close-up or extreme close-up. In wide shots, use back view, rear three-quarter view, or empty environment shots; never show a distant frontal face.
video-011-cinematic-xianxia-storyboard.mp4
Source: MiniMax — Official H3 guide
A strict identity reference anchors a polished otome-game character presentation.
Input Images:
![]() Image 1 |
![]() Image 2 |
Prompt:
Create a character promo for a male lead in an otome game. Use Image 2 as a strict identity reference. Preserve the same face, hairstyle, body proportions, costume design, material detail, and polished otome-CG aesthetic throughout.
video-012-otome-male-lead-promo.mp4
Source: MiniMax — Official H3 guide
A first-person camera advances, checks angles, fires, and keeps moving through a military base.
Input Images:
![]() Image 1 |
Prompt:
Camera: first-person, eye level, handheld gameplay. Simulate a player operating a modern-warfare FPS, holding an assault rifle and advancing slowly around the perimeter of a military base. Move forward along a road beside cover, sweep the reticle across the passage ahead, pause to fire several rounds at a distant target, then continue pushing forward like authentic player-controlled footage.
Lighting: cool natural light across a modern military base, mixed with smoke and firelight. Keep the image photoreal and crisp, with AAA-quality weapons, materials, dust, and battlefield haze.
Camera movement: subtle player-driven sway while moving; begin with a slow advance, make small checks left and right, add light recoil when firing, then continue forward steadily.
video-013-modern-warfare-fps.mp4
Source: MiniMax — Official H3 guide
Cross-modal control using images, video, music, voice, and camera motion.
Six images supply the assets while one reference video supplies rhythm, transitions, and music.
Input Images:
![]() Image 1 |
![]() Image 2 |
![]() Image 3 |
![]() Image 4 |
![]() Image 5 |
![]() Image 6 |
Reference Media:
Video 1
video-014-reference-01.mp4
Prompt:
Use Images 1–6 as assets. Match Reference Video 1 closely for shot rhythm, transition language, and music.
video-014-six-asset-rhythm-reference.mp4
Source: MiniMax — Official H3 guide
A macro push into coffee foam transforms seamlessly into wind-carved desert dunes.
Input Images:
![]() Image 1 |
![]() Image 2 |
Prompt:
@Image 1: Push in rapidly toward the milk foam, cocoa particles, and dark liquid texture on the coffee until particles, bubbles, and ripples fill the frame. Keep the macro photography realistic, with extremely shallow depth of field and fine powder drifting through backlight. Let the surface feel suspended between granular sand and fluid.
At the exact moment when the cocoa particles, foam contours, and coffee swirl closely resemble the dune ridges, wind-carved textures, and airborne sand in @Image 2, transition seamlessly into the desert landscape. Continue pushing forward until the full dunes from @Image 2 are revealed.
No tearing, black frames, hard cuts, obvious VFX, or compositing seams. Keep it photoreal, quiet, and restrained—as though one granular material naturally expands from the microscopic coffee surface into a vast desert. One continuous shot with no visible edit.
video-015-coffee-to-desert-transition.mp4
Source: MiniMax — Official H3 guide
Camera motion, character appearance, and vocals are drawn from three different modalities.
Input Images:
![]() Image 2 |
Reference Media:
Video 1
video-016-reference-01.mp4
Audio 3
video-016-audio-03.mp4
Prompt:
Reference the Hitchcock camera movement from Video 1, have the character in Image 2 sing, with the vocals matching Audio 3.
video-016-hitchcock-camera-voice-reference.mp4
Source: MiniMax — Official X article
Targeted replacements, compositing, and hand-drawn effect edits.
A single direct instruction replaces the subject while preserving the source video.
Reference Media:
Video 1
video-017-reference-01.mp4
Prompt:
Replace the cat in the video with a dog.
video-017-replace-cat-with-dog.mp4
Source: MiniMax — Official H3 guide
A keyed subject is integrated into a responsive fairy-tale scene with matched relighting.
Reference Media:
Video 1
video-018-reference-01.mp4
Video 2
video-018-reference-02.mp4
Prompt:
Remove the green-screen background from Video 1 and replace it with a fairy-tale environment similar to Video 2. Make every background element respond correctly to the subject’s movement, and relight the subject so they blend naturally into the new scene.
video-018-green-screen-fairy-tale.mp4
Source: MiniMax — Official H3 guide
One request coordinates several object, wardrobe, face, effect, and background edits.
Reference Media:
Video 1
video-019-reference-01.mp4
Prompt:
In the reference video: replace the newspaper with a green hardcover book; replace the chair with a red sofa; remove the subject’s sunglasses and reveal a clear face; remove the burning-car effect and restore the vehicle to normal; replace the photograph taken from the coat with a small black notebook; and add a tree on the left side of frame.
video-019-multi-element-precision-replacement.mp4
Source: MiniMax — Official H3 guide
Orange sparks and pink brushstrokes build around a couple in response to their movement.
Input Images:
![]() Image 1 |
Reference Media:
Video 1
video-020-reference-01.mp4
Prompt:
Add orange-yellow hand-drawn marks like Image 1 around the two people in Video 1. As they move closer, the marks multiply and build from tiny sparks into bright radiance. When they kiss, introduce pink brushstrokes.
video-020-hand-drawn-graphic-effects.mp4
Source: MiniMax — Official H3 guide
Read CONTRIBUTING.md before proposing a prompt. Submissions must include a direct source, the complete prompt, the matching output, and confirmed sharing rights.
The repository's editorial text is licensed under CC BY 4.0. MiniMax media, trademarks, and third-party materials remain the property of their respective owners and are not automatically covered by this license.


































