MiniMax H3 Prompting Guide

Master MiniMax H3 video prompting through prompt structure, reference-asset roles, camera, sound, complete examples, and generated results.

MiniMax H3 can understand text, images, video, and audio at the same time, and generate video with synchronized sound. A prompt needs to make the generation goal, the role of each reference asset, the shot timeline, the subject's action, the camera, and the sound explicit. The more specific your description and the more consistent the pieces are with one another, the more controllable the result.

Core Information in a Prompt

An H3 prompt needs to answer three questions:

Core information	What to spell out	Example
Generation goal	Scene, subject, visual style, and the main event	A cool-toned perfume product short: a water droplet slides down the bottle, ending on the label
Reference-asset role	What each image, video, or audio clip is specifically responsible for	Image 1 provides the product's appearance; Video 1 provides the camera path only
Audio-visual timeline	Opening, action changes, camera, sound, and the ending frame	Droplet slides down → camera pushes in → focus shifts to the label → holds on a product close-up

A complete prompt usually consists of six parts:

Scene sequence: how the video begins, develops, and ends;
Subject action: who does what, and how the action happens and changes;
Reference role: what each image, video, and audio clip provides;
Camera: shot size, angle, movement, and cuts;
Sound: dialogue, ambience, synchronized effects, and music;
Ending frame: where the shot finally rests, and what must stay unchanged.

H3 Prompt Template

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

Complete Prompt Examples

Hands-on exampleAERIS Hydrating Essence Hero Shot

Input: Image 1 · Audio 1 · 8 s · 16:9

Part	Content
Reference	`@1` controls product appearance and packaging identity; `@2` controls musical rhythm, ambience, and the final glass chime
Sequence	Serum macro → product reveal → slow orbit → label close-up → hero lock-up
Camera	Macro pullback, 20-degree orbit, label-tracking pass, and subtle push-in
Sound	Regenerate the restrained rhythm from `@2` and hold on its final glass chime
Keep	Bottle, cap, and label remain rigid; liquid moves only behind the product

Product Ad Prompt

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

Reference inputs · 2

Reference: Image 1 · Product packaging and identity — ReferenceImage 1 · Product packaging and identity

ReferenceAudio 1 · Ambient bed and glass chime

Download MP3

Generated result · 1

Generated resultAERIS Hydrating Essence hero shot

Download MP4

Hands-on exampleCharacter Identity and Motion-Path Transfer

Input: Image 1 · Video 1 · Audio 1 · 8 s · 16:9

Part	Content
Reference	Image 1 controls the character; Video 1 controls only action and camera; Audio 1 controls sound character and rhythm
Sequence	Enters frame → turns around → looks at camera
Camera	Low-angle follow, rising to a medium shot at the end
Sound	Footsteps, fabric rustle, indoor ambience, and low-frequency music
Exclude	Do not copy the character, wardrobe, or background from Video 1

Character Action Prompt

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

Reference inputs · 3

Reference: Image 1 · Standalone character portrait — ReferenceImage 1 · Standalone character portrait

ReferenceVideo 1 · Walk, turn, and camera path

Download MP4

ReferenceAudio 1 · Low-frequency score, room tone, and rhythm

Download MP3

Generated result · 1

Generated resultCharacter identity and motion-path transfer

Download MP4

How to Write Reference Assets

After adding reference assets, describe in the prompt what each one is responsible for, item by item. Do not just write "reference Image 1" or "reference Video 1"; make clear what must be preserved and what should not be copied.

Asset	Information it is suited to provide	Prompt focus
Character image	Face, hairstyle, body type, wardrobe, and demeanor	For a multi-person image, indicate which character to use
Product image	Bottle shape, material, color, label, logo, and text	List separately the packaging details that must be accurately preserved
Action video	Gait, dance, gestures, camera path, or editing rhythm	State which movements to reference only, and exclude the original character and scene
Audio	Timbre, dialogue, beat, music style, or sound effects	State whether to use it as-is or only reference its sound characteristics

Reference-Asset Role Example

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

How to Write the Camera

A camera description includes shot size, angle, camera movement, and the purpose of the movement. Do not just pile up shot terms; explain how the camera moves around the subject and what needs to be visible after it moves.

Shot	Function
Push In	The camera moves toward the subject, emphasizing an expression, product, or key detail
Pull Out	The camera retreats, revealing the full character, scene, or spatial relationship
Tracking	Keeps a speed and distance close to a moving subject
Arc Shot	Moves around the subject, showing its outline, material, and spatial depth
Pan	The camera position stays fixed while the shot turns horizontally to a new subject or piece of information
Pedestal	The entire camera rises or lowers, changing the height of observation
Handheld	Subtle natural shake, suited to documentary, street, and UGC textures
Static	A fixed frame that lets the subject's action become the visual focus
POV	Observes the action and environment from the position of a character's eyes

Complete Camera Description

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

How to Write the Sound

Describe dialogue, ambience, synchronized sound effects, and music separately, and state which action or shot each appears in. The sound content should stay synchronized with the on-screen events.

Dialogue: state who is speaking, their emotion while speaking, and the complete line;
Ambience: describe the persistent spatial sound, such as mall chatter, waves, rain, or a nighttime city floor tone;
Synchronized effects: match sound to a specific action, such as a cap opening, soles landing, fabric rubbing, or liquid poured into a glass;
Background music: state the music's style, instruments, and tempo, and its dynamic changes at key moments.

Sound Description Example

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

Making Prompts More Stable

Match the number of actions to the duration: a short video concentrates on one main action; when several events are needed, split them in chronological order;
Use observable verbs: change "very premium" into "cool side light moves along the glass edge, with clean, restrained reflections";
Avoid camera conflicts: do not require static, a fast push-in, and a large arc at the same time;
State the items to keep: character identity, wardrobe, packaging, logo, color, and key props need to be stated separately;
State the ending frame: write where the shot finally rests and what must be clearly visible in the final frame;
Keep only necessary constraints: focus constraints on problems that genuinely affect delivery, such as typos, distortion, duplicated products, and watermarks.

If the result deviates from the prompt, check in turn whether the subject, action, scene, and camera conflict; whether each reference asset carries only a clear role; whether the number of actions suits the video's duration; and whether the ending frame and items to keep are already spelled out.

Showcase: References and Generated Results

Hands-on exampleText Generation · Hand-Drawn Kitchen Creature

Input Prompt

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

Generated result · 1

Generated resultHand-Drawn Kitchen Creature

Download MP4

Hands-on exampleFirst-Frame Generation · Space Opera Trailer

Input Prompt

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

Reference inputs · 1

Generated result · 1

Reference inputs · 1