🧬 MiniMax H3 Prompt Guide

No reference asset at all — the full timeline is built directly from text.

integrated_multimodal_description: [Shot 1] Live-action, cinematic, a medium-wide shot frames a baker opening the shutters of a small street bakery before sunrise. The camera pushes in with small amplitude at slow speed as the middle-aged baker with a calm, slightly raspy voice (S1) places a fresh loaf on the wooden counter and says: <d>[English] First batch of the morning.</d> [Shot 2] At 00:05.000, the camera cuts to a close-up of steam rising from the sliced bread while the baker's final words carry over from the previous shot.

overall_soundscape: Wooden shutters scrape open over a quiet street as trays clink softly inside the bakery. The doorbell rings once, followed by light footsteps and the crisp sound of bread being sliced.

non_diegetic_music: A soft acoustic-guitar pattern at a moderate tempo, joined by sparse upright-bass notes and a gentle fade at the end.

For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.

integrated_multimodal_description: [Shot 1] Live-action, cinematic, the young woman shown in <Picture 1> remains beside the rain-covered train window, preserving her appearance, clothing, seat position, and the carriage layout. The camera trucks right with small amplitude at slow speed as she lifts her gaze from the folded letter toward the passing city lights. Her reflection moves across the glass while the quiet, breathy young woman (S1) says: <d>[English] I get off at the next station.</d> She folds the letter along its existing crease.

overall_soundscape: The train wheels produce a steady metallic rhythm beneath a low ventilation hum. Rain ticks against the window while paper rustles softly in her hands.

non_diegetic_music: Sustained cello notes at a slow tempo with widely spaced piano tones, gradually decreasing in volume.

How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 1) aligns with the 8.00-second mark of the target video.

integrated_multimodal_description: [Shot 1] Live-action, cinematic, a rain-soaked cyclist begins in the position and framing established by Picture 1, holding a closed black umbrella beside a silver bicycle. The camera pulls out with small amplitude at slow speed as she releases the bicycle handle, raises the umbrella above her shoulder, and presses the runner upward until the canopy opens. Water rolls from the expanding fabric while she steps beneath it, rotates the handle into the final angle, and settles into the pose, spacing, and composition established by Picture 2 at the end of the shot.

overall_soundscape: Rain falls steadily on the pavement, followed by the metallic click of the umbrella runner and the soft snap of the canopy opening. Water drips from the bicycle frame as distant traffic passes.

non_diegetic_music: N/A

How the reference pictures align with the target video — <Picture 1> (from [Shot 1]) aligns with the 6.00-second mark of the target video.

integrated_multimodal_description: [Shot 1] Live-action, cinematic, a close shot begins with an intact drinking glass near the edge of a dark wooden table, while the same hand and sleeve visible in <Picture 1> approach from the right. The camera pushes in with small amplitude at slow speed as the fingertips strike the rim. The glass tips, falls, and hits the floor with a sharp impact; cracks spread through it as fragments slide outward. Toward the end, the moving pieces lose momentum and settle into the exact broken arrangement, hand position, camera angle, lighting, and final composition established by <Picture 1>.

overall_soundscape: Fingertips tap the glass before it scrapes across the tabletop, falls, and breaks with a sharp crash. Small fragments scatter and gradually stop sliding across the floor.

non_diegetic_music: A low electronic pulse at a slow tempo, ending immediately after the glass breaks.

Full six-section rewrite: two picture references define the location and the dog, two video references define the two human subjects, and one audio reference guides a voice timbre without copying the original line.

subject_definitions:
<Subject 1> is the coffee-shop environment in <Picture 1>, featuring an exposed brick wall, an orange tufted sofa with patterned pillows, a neon sign, and a wooden coffee table.
<Subject 2> is the fluffy white Samoyed in <Picture 2>, <Picture 3>, and <Picture 4>, with thick white fur, pointed ears, a dark nose, and a curved tail.
<Subject 3> is the young blonde woman in <Video 1>, with long blonde hair and a light-pink button-down shirt with rolled-up sleeves.
<Subject 4> is the young man in <Video 2>, with short wavy brown hair and a dark-grey hoodie with drawstrings.
<Audio 1> is the voice-timbre reference for <Subject 3> (S1), containing a spoken English vocal layer.

summary:
[reference generation + audio reference] The target video shows <Subject 3> eating a cookie in <Subject 1>. <Subject 4> enters with <Subject 2>, which lunges toward the cookie. The three-shot exchange uses <Audio 1> as the voice-timbre reference for <Subject 3> and ends with a canned audience laugh.

retention_analysis:
<Subject 1> (appears in [Shot 1], [Shot 2], [Shot 3]): fully_preserved - the exposed brick wall, orange tufted sofa, patterned pillows, neon sign, and wooden coffee table are retained.
<Subject 2> (appears in [Shot 1], [Shot 2]): fully_preserved - the Samoyed's thick white fur, pointed ears, dark nose, and curved tail are retained.
<Subject 3> (appears in [Shot 1], [Shot 2], [Shot 3]): fully_preserved - the blonde woman's identity, long hair, and light-pink shirt are retained.
<Subject 4> (appears in [Shot 1], [Shot 2]): fully_preserved - the young man's short wavy brown hair and dark-grey hoodie are retained.
<Audio 1>: reference - its vocal timbre guides the dialogue delivery of <Subject 3> without copying the original signal.

detailed_description:
The target video uses a realistic multi-camera sitcom style with warm indoor lighting.
[Shot 1] A medium shot establishes <Subject 1>, the coffee shop with its exposed brick wall, orange tufted sofa, patterned pillows, neon sign, and wooden coffee table. <Subject 3> (S1), the young woman with long blonde hair and a light-pink button-down shirt with rolled-up sleeves, sits on the sofa holding a chocolate-chip cookie. From the left, <Subject 4>, the young man with short wavy brown hair and a dark-grey hoodie with drawstrings, enters holding the leash of <Subject 2>, the thick-furred white Samoyed with pointed ears, a dark nose, and a curved tail. The dog lunges toward the cookie and pulls the leash taut. <Subject 3> (S1) jerks her hand back and, using the clear youthful voice timbre referenced from <Audio 1>, exclaims with light annoyance, <d>[English] Hey! Watch your dog!</d> She closes her lips and guards the cookie while <Subject 4> pulls the dog back.
[Shot 2] At 00:03.000, the shot cuts to a close-up of <Subject 4> (S2), the young man in the dark-grey hoodie from Shot 1, sitting beside <Subject 3> on the sofa and holding <Subject 2> securely in his arms. <Subject 4> (S2) says in a casual young male voice with a playful tone and an easy conversational pace, <d>[English] He just likes cookies more than me.</d> He closes his mouth into an apologetic smile and strokes the dog's thick white fur.
[Shot 3] At 00:05.000, the shot cuts to a close-up of <Subject 3> (S1), the blonde woman in the light-pink shirt from Shot 1. Her annoyance softens as she looks toward the Samoyed. <Subject 3> (S1) replies in the same clear youthful voice referenced from <Audio 1> with an amused cadence, <d>[English] Well, he has good taste at least.</d> She smiles and raises the cookie in a small toast-like gesture. A classic canned audience laugh begins immediately after the line and continues through the final frame.

overall_soundscape:
Soft indoor coffee-shop room tone continues throughout the scene.

non_diegetic_music:
N/A

Posted as a reusable template: swap in your own @[character reference], keep the rest. Good study piece for how much physical/kinetic detail H3 accepts in one continuous block — dance beats, VFX color language, and camera moves are all interleaved in plain prose rather than split into numbered shots.

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.

Source: x.com/aimikoda/status/2097001707683119410 — "MiniMax H3 Prompt Share," Sep 2026.

Six Midjourney v8.2 images, each locked to one subject or prop by index ("Image #3 defines the young rescuer…"), then a full ten-shot dark-fantasy trailer with two lines of accented dialogue and a title card. Worth studying for the reference-mapping opener and for how tightly each shot is timed (0-1s, 1-2s…) with an explicit cut motivation on every beat. Posted alongside the note: "if you give H3 high-quality references, you get high-quality results."

Image #3 defines the young rescuer and forbidden red fruit; Image #2 defines his captive beloved; Image #1 defines the garden keeper and his potted flowers; Image #4 defines the hooded hunter; Image #6 defines the seer and her raven; Image #5 defines the stone god. Preserve their separate identities, costumes and distinctive props. Use the foliage and roses as connected areas of one nocturnal garden, with new cinematic viewpoints. Preserve the references' illustrated contours, painterly surfaces, deep ultramarine shadows, violet skin tones and coral-red accents.

A kinetic, artistic 15-second dark-fantasy trailer for THE STONE GARDEN. A young man steals forbidden fruit to free his beloved, awakening the garden's stone god. Ten cinematic animated shots followed by one title card. A rapid opening montage expands into readable two-second action and revelation beats. Animate bodies, fabric and foliage with physical depth while retaining the painted style.

0-1s: Close-up through blue leaves, a brief push toward the captive's frightened face. She reaches toward the rescuer offscreen left and whispers, "Please." Her voice is breathy, with a distinct upper-class British English accent. One fragile string note. Cut on her reaching gesture.

1-2s: Extreme close-up of her outstretched wrist. A living blue vine coils tight and jerks her hand back toward the foliage. Its leaves scrape her sleeve. Hard cut on the sudden recoil.

2-3s: Macro side view of the forbidden red fruit cradled in the rescuer's hands, still attached to a low red-leafed branch. He twists and pulls; show the stem snapping and the fruit coming free. The amplified snap kills the music. Cut on the break.

3-4s: Low medium shot tracking beside the rescuer as he clutches that detached fruit to his chest and bursts through hanging red branches toward the captive's clearing, screen right. Branches whip behind him. Cut as he clears the foliage.

4-5s: Overhead insert into the keeper's pot, securely supported by both hands. Its purple flowers abruptly wilt, their stems buckling inward as a magical consequence of the theft. A dry floral crackle. Cut on the collapse.

5-6s: Tight frontal close-up of the keeper's sunglasses and clenched jaw. He snaps his head toward the thief's route; a brief lateral camera slide catches the rose wall reflected in his glasses. A low bass pulse begins. Hard reaction cut.

6-8s: Low wide lateral tracking shot along a narrow passage through the rose field. The hooded hunter launches into a sprint toward screen right, following the rescuer's route. Roses streak past the foreground; his patterned coat trails behind him. Heavy percussion erupts with his first running strides. Cut during the pursuit, before he catches up.

8-10s: Three-quarter medium close-up of the seer. Her raven pushes off her raised hand as she looks toward the disturbance. A quick upward tilt follows its wings; her feathered head ornament stays attached. In a low, ominous voice with a pronounced aristocratic British English accent, precise consonants and non-rhotic delivery, she says, "Save her..." Cut at 10s, carrying her voice across the edit.

10-12s: Tight side-on rescue shot: the young man is left, the captive right, separated by vines. He reaches the same stolen fruit through a gap. She closes her hand over his on the fruit; at contact, the vines loosen and uncoil from her wrist. A short push keeps their joining hands and the releasing vine visible together. He still supports the fruit. The seer's offscreen warning completes, "...and you wake him." Cut on the release.

12-14s: Low-angle wide shot reveals the monumental stone god above the clearing, with the reunited pair small beneath it. A forceful push toward the god accompanies its red eyes flaring and its heavy carved head turning down toward them for the first time. It remains stone. Grinding rock overwhelms the score. Smash cut to black at 14s before it attacks.

14-15s: Hold a static title card for the full final second: THE STONE GARDEN, exact spelling, large centered coral-red uppercase serif lettering on deep ultramarine-black. The complete title appears immediately, with a single resonant impact and a short decaying tail. No other text.

Sharp cuts, urgent natural-speed action, readable hands and reactions. Preserve the rescuer's rightward travel, the hunter's ongoing pursuit and the stolen fruit's identity. The lovers remain together holding the fruit in the final reveal. Keep music beneath the dialogue. Both spoken lines are English with deliberate British accents. No subtitles, additional narration or slow motion. The final film title is the only onscreen text.

Source: x.com/aimikoda/status/2097112285827268887 (video) and the prompt reply — "MiniMax H3 + Midjourney v8.2," Sep 2026.