学会写 MiniMax H3 提示词

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 video.

non_diegetic_music:
N/A

The camera pushes in with small amplitude at slow speed toward the folded letter in her hands.

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

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 N) aligns with the S.SS-second mark of the target video.

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

[Shot 1] Live-action, a medium-wide shot frames a nearly empty provincial train platform in late-afternoon light. A woman in her early thirties with a dark ponytail and a beige trench coat stands in the right foreground holding a suitcase, facing an elderly man in a grey jacket who waits beside a bench ten paces away, a cloth cap held in both hands. Neither moves for a moment. The camera pushes in with small amplitude at slow speed as she sets the suitcase down, walks the ten paces, and stops in front of him; he raises the cap halfway, then lowers it, and she takes his hands.

The camera pushes in with small amplitude at slow speed toward the folded letter in her hands.
The camera pans right with large amplitude at fast speed, revealing the open doorway.
The camera holds a static shot as the runner exits the frame.

A red neon sign reading "营业中" glows above the doorway.

overall_soundscape: Steady rain taps against the café windows while low room ambience continues underneath. The entrance bell rings once, followed by wet footsteps and the soft scrape of a chair.

non_diegetic_music: Sparse piano notes at a slow tempo, joined by sustained low strings that gradually increase in volume before fading out.

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.

[Shot 2] At 00:03.500, the camera cuts to...

integrated_multimodal_description: [Shot 1] Live-action, a medium-wide shot frames an elderly postman in a faded green uniform walking a narrow village lane at dawn, a worn leather mailbag on his shoulder. The camera tracks alongside him with small amplitude at slow speed as he stops before a wooden gate, takes a single envelope from the bag, and looks at it for a moment. [Shot 2] At 00:05.500, the camera cuts to a close-up of his weathered hand sliding the envelope into the gate's mail slot. He rests his palm on the gate briefly, then steps back and smiles.

overall_soundscape: Birds chirp in the quiet lane while the mailbag's leather strap creaks softly with each step. The envelope slides against wood, followed by the light metallic click of the mail slot.

non_diegetic_music: A solo harmonica melody at a slow tempo, joined by soft acoustic-guitar chords that fade out in the final seconds.

integrated_multimodal_description: [Shot 1] Live-action, a medium shot frames a small kitchen at night under a warm ceiling lamp. An old-fashioned radio on the counter plays a soft old song that both women can hear. The young woman (S2) pushes the door open and steps in with a suitcase. Her mother, an older woman with a gentle, slightly hoarse voice (S1), looks up from the table and says: <d>[Chinese] 回来啦，锅里给你留了粥。</d> The daughter (S2) says in an off-screen voiceover: <d>[Chinese] 那一刻我突然不想走了。</d> while her lips remain completely closed. [Shot 2] At 00:04.500, the camera cuts to a close-up of the mother rising to ladle porridge from the pot, still smiling.

overall_soundscape: The door latch clicks and the suitcase wheels roll briefly over the tiles. A pot lid rattles softly as porridge simmers on the stove.

non_diegetic_music: N/A

subject_definitions:
<Subject 1> is the boy in <Picture 1>, with short black hair, a round face, and a yellow apron over a white T-shirt.
<Video 1> is a seaside clip referenced only for its slow lateral camera movement and pacing.

summary:
[reference generation] The target video shows <Subject 1> learning to fry an egg in a home kitchen, using the slow lateral tracking movement and unhurried pacing referenced from <Video 1>.

retention_analysis:
<Subject 1> (appears in [Shot 1], [Shot 2]): fully_preserved - the boy's short black hair, round face, yellow apron, and white T-shirt are retained.
<Video 1> (camera movement and pacing): weak_reference - only the slow lateral movement and pacing are followed.

detailed_description:
The target video is in a bright, realistic home-video style with natural window light.
[Shot 1] A medium shot frames <Subject 1>, the boy with short black hair and a yellow apron, standing at a stove with a frying pan. Following the slow lateral movement referenced from <Video 1>, the camera trucks right with small amplitude at slow speed as he cracks an egg against the pan's rim and tips it in. [Shot 2] At 00:03.500, the shot cuts to a close-up of the egg white spreading and setting around the yolk while <Subject 1> watches from the edge of the frame, holding the shell halves.

overall_soundscape:
The egg sizzles steadily in the pan under a faint kitchen fan hum. The shell taps lightly against the pan's rim.

non_diegetic_music:
N/A

[I2VA] For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
[FL2VA] 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 N) aligns with the S.SS-second mark of the target video.
[L2VA] How the reference pictures align with the target video — <Picture 1> (from [Shot N]) aligns with the S.SS-second mark of the target video.

integrated_multimodal_description: [Shot 1] <Style>, <shot size> frames <subject + initial composition + scene>. The camera <motion type + amplitude + speed> as <action develops>. <Speaker description> (S1) says: <d>[Language] <original dialogue></d> [Shot 2] At 00:0X.XXX, the camera cuts to <new information>.

overall_soundscape: <1–4 sentences: ambience + physical sounds + non-verbal human sounds>

non_diegetic_music: <1–3 sentences: instrumentation + tempo + rhythm + dynamics, or N/A>

subject_definitions:
<Subject 1> is <definition + source asset + key features>.
<Picture 1> is <only if it is a real frame / storyboard anchor>.
<Video 1> is <only for whole-video relationships>.
<Audio 1> is <audio role; add (Sx) if bound to a target speaker>.

summary:
[task type + task type] <One short paragraph using only defined labels.>

retention_analysis:
<Subject 1> (appears in [Shot 1]): fully_preserved / partially_preserved / attribute_transfer / weak_reference - <what is retained>.
<Audio 1>: fully_copy / partially_copy / reference / weak_reference - <how the audio is used>.

detailed_description:
<One or two sentences establishing style.>
[Shot 1] <Composition, subject appearance and position, environment and lighting, actions, camera, current sound, labels where they take effect.>
[Shot 2] At 00:0X.XXX, the shot cuts to <...>.

overall_soundscape:
<Ambience and physical sounds; audio-copy relationship for this layer if any.>

non_diegetic_music:
<Audience-only score, or its reuse relationship, or N/A.>