MiniMax H3 examples and prompts

Six real MiniMax H3 clips, each paired with the verbatim prompt that produced it. Study how references, camera language, and sound description come together, then reuse the pattern in a prompt of your own.

Try Free More MiniMax H3 use cases

Showcase

How to read these examples

This gallery collects six MiniMax H3 examples, each one a finished clip alongside the exact prompt that generated it, no paraphrasing, no cleanup, just what was actually typed in. Reading a working MiniMax H3 prompt is a faster way to learn the model than reading a spec sheet, because it shows the specific words that produced a specific camera move, a specific line of dialogue, a specific piece of score, rather than an abstract description of a capability. Look at how each prompt names its references, describes the shot in camera terms rather than vague adjectives, and spells out the sound alongside the picture instead of leaving audio as an afterthought. Notice, too, how the aspect ratio and rough duration are usually stated outright, matching the clip to the platform it was made for. Copy any prompt with the button beside it, swap in your own subject or reference files, and use it as a starting template rather than writing a MiniMax H3 prompt from a blank page.

First and Last Frame

Vintage Binocular Brand Film

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. Keep the twin circular lens mask absolutely fixed throughout. Visual language: a voyeuristic, Wes Anderson-inspired 35mm film look with fine grain, soft highlight halation, restrained color, and red typographic accents.

Reference to Video

Fantasy Wuxia Character Film

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.

Video Reference

Live-Action to Voxel Transformation

Preserve the buildings, pedestrians, and overall environment in Video 1 as photoreal live action. Transform only the trees and cars into 3D pixel-art or voxel-block objects in the style of Minecraft, using Image 1 as the visual reference. Keep their motion physically correct, and preserve the real environment's shadows and transmitted light. Use Video 2 as the overall target.

Text to Video

Neon Laundromat Encounter

15 seconds, 16:9 landscape. Combine a live-action late-night laundromat with hand-drawn luminous animation. The small self-service laundromat has gently flickering fluorescent lights, running washers, plastic baskets, a worn bench, and one sock on the floor. Keep the space quiet and faintly nostalgic. Use a one-handed phone-camera feel with visible shake, exposure fluctuation under white fluorescent light, environmental reflections in glass, and delayed autofocus at close range. Avoid polished commercial composition; it should feel like an authentic late-night encounter, filmed while following a strange apparition.

Motion Reference

Capybara Motion Recreation

Match the action in Video 1 from a locked-off wide camera. Replace the three suited men with three highly photoreal capybaras. Preserve the original movement path exactly: all three drop quickly to the floor; the left capybara jumps to center; the center capybara rolls to the far left; the new center capybara rolls to the far right; the right capybara jumps to center; finally, the center capybara jumps onto the other two, forming a pyramid. Keep the camera fixed and integrate fur, lighting, and shadows realistically into the scene.

Video Editing

Green-Screen Fairytale Composite

Remove the green screen background of Video 1 and turn it into a fairy tale-like background similar to Video 2. The background elements need to completely match the actions of the characters in Video 1. Modify the lighting of the characters in Video 1 so that it completely matches the background.

Prompts

Reading a MiniMax H3 prompt

Naming your references

A MiniMax H3 prompt addresses each uploaded file directly, Image 1 for a subject's face, Image 2 for a location, Video 1 for a motion pattern, Audio 1 for a voice. Naming references this way tells the model exactly which file supplies which part of the shot, instead of leaving it to guess from context, and it lets a single prompt combine several references without confusing which one does what.

Camera and lens language

Instead of a nice shot of, working prompts name the move: slow dolly-in, static wide, handheld follow, low-angle push. Naming a lens or framing choice, close-up, medium shot, wide establishing, gives MiniMax H3 something concrete to execute, and tends to produce steadier, more intentional-looking motion than vague direction, especially across the longer end of the 5 to 15 second range.

Describing the soundscape

Because MiniMax H3 generates audio with the picture, a good prompt describes sound as deliberately as it describes the frame: a quiet room tone under dialogue, a specific instrument in the score, a foley detail like gravel underfoot. Leaving sound undescribed still produces audio, since native stereo is generated on every clip, but naming it steers the result toward what you actually intended.

Aspect ratio and duration cues

Prompts often state the target ratio and rough length directly, a 9:16 clip for a mobile feed, a 21:9 frame for a cinematic wide, an 8-second beat versus a full 15-second scene. Stating both up front keeps the generated shot's pacing and composition matched to where it will actually be viewed, and leaves the adaptive ratio option for when the composition itself should decide.

Try it

Generate your own MiniMax H3 opening frame

This step renders your shot's opening frame as a still image so you can check framing and lighting first, the full 2K MiniMax H3 clip with native audio generates as a separate, later step.

Free and anonymous. Protected by Cloudflare Turnstile — no account, no card.

Explore

Ready to generate your own?

These MiniMax H3 examples are prompts, not magic, the same techniques of naming references, directing the camera, and describing sound work on any subject you bring. Use the tool above to render an opening frame for free and check your composition, then take the prompt patterns from this gallery and adapt them to your own shot.