Generate a 2350 Mecha-Girl POV Sci-Fi Short with Muse Six-Clip Prompts

Paste three segmented prompts into Muse → generate 3:4 vertical clips → assemble into a ~59-second short

Who

Content creators with Muse access who want to make narrative AI videos

You get

A 6-shot, ~59-second first-person POV sci-fi comedy short with character setups and Mandarin dialogue

You need

Muse

Steps

1. Generate Clip 1: Global setup and the peeping discovery

   Open Muse and start a new video generation task. Paste the following prompt in full to generate CLIP 1 (~0:00–0:09.8). This segment also contains the global format lock, character identities, and world setup used across all clips.

   Execution prompt · Source text。Muse video generation input field

   Copy prompt

   Muse Video Prompt
   Format lock: Aspect ratio 3:4 (source 1080x1450, 30 fps; generate at 1080x1440, 30 fps) — the output MUST use exactly this ratio; no cropping, no reframing, no letterbox change.
   Total runtime: about 59 seconds in 6 clips.
   
   A first-person POV sci-fi comedy in photorealistic doll-like CG: a modern young man wakes in the year 2350, in one of humanity's last cities — a place run by beautiful android girls and giant mechs, where men are extinct. THE CAMERA IS THE MAN. He is never seen; only his voice is heard. Every girl speaks to the lens, points at the lens, studies the lens. The whole joke and the whole charm live in that direct address.
   Identity — THE GUARD: A girl of about nineteen with long black hair, twin side locks and small black horn-like hair accessories; glossy doll features, sly bright eyes, pink-gloss lips. A silver chrome cropped tech jacket over a black outfit with a short skirt and a slim choker. Cheeky and menacing in turns, always performing for the lens.
   Identity — THE LITTLE GUARD: A shorter, younger girl with pink-purple gradient hair in a matching chrome outfit; mostly soft-focus or mid-frame; she exists to be scolded.
   Identity — THE ELDER SISTER: A tall woman with very long straight white-blue hair to her hips, pale porcelain skin, calm appraising eyes. A white top under a transparent clear-vinyl long coat, a black tech collar with metal fittings at her throat. She never hurries and never raises her voice; she evaluates the camera like a specimen she might keep.
   Identity — THE TRIO: Three resident girls of the forest city — one silver-blonde bob, one brown-haired, one green-haired — in metallic silver dresses, curious as children at a zoo.
   Identity — THE MAN (voice only): a young man's Mandarin voice, bewildered, increasingly panicked; he is the camera, never visible, no hands, no body.
   World & scenes: (A) a dark mech hangar — a row of giant white bipedal mechs with glowing blue ring cores in their chests, a control console with holographic screens; (B) a neon corridor washed in pink and purple light strips; (C) a red-lit security doorway; (D) an indoor forest city — wet stone paths, wooden houses, drifting mist, floating holographic billboards, lush green canopy overhead.
   Music and sound: a light, curious sci-fi score — soft synth pads and plucked notes, comedic timing, never horror; servo hums and hangar ambience under scene A; the girls' voices are clear Mandarin, spoken straight into the lens.
   Camera: POV handheld feel throughout — the small sway of a person standing, breathing, following; girls repeatedly break the fourth wall by design; hard cuts between beats.
   
   CLIP 1 of 6 — source 0:00-0:09.8. Scene A: the peeping and the discovery.
   Sound (this clip): hangar hum, soft mech servo idle; the Guard's two lines, very close to the microphone of the scene.
   THE RHYTHM & FORCE (this clip): stealth, then a face arriving too close — the comedy is the invasion of the lens. If she keeps a polite distance, it is wrong.
   EMOTION ARC (this clip): she plays cat-and-mouse for one second, then owns him completely.
   Dialogue — The Guard (~0:06-0:09, into the lens): "你是谁，为什么偷窥我"
   Dialogue — The Guard (~0:09, pointing): "差点就被你发现了"
   [0.0-5.5s] Shot 1 — POV wide, slow creeping drift, scene A: from behind a console, the row of giant white mechs with blue ring cores, holographic screens glowing; the camera peeks and settles like someone hiding. Avoid: any person in frame; fast movement; the mechs moving.
   [5.5-9.8s] Shot 2 — face macro series, hard little push-ins, scene A: the Guard's face suddenly fills the screen — a sly smile straight into the lens, closer still until her eyes and nose are a macro landscape, then she pulls back a fraction and points directly at the camera as she delivers the two lines. Avoid: her looking anywhere but the lens; a frightened expression; subtitles appearing.

2. Generate Clips 2–4: Scolding, appraisal, and the corridor

   Continue in the same Muse session. Paste the following prompt in full to generate CLIP 2 (scolding and report), CLIP 3 (Elder Sister arrives), and CLIP 4 (corridor of 2350), covering ~0:09.8–0:39.2.

   Execution prompt · Source text。Muse video generation input field

   Copy prompt

   Whole-clip Avoid: no subtitles or on-screen text, no watermark, no visible cameraman, no hands of the POV man, no horror tone.
   
   CLIP 2 of 6 — source 0:09.8-0:19.6. Scene A: the scolding and the report.
   Sound (this clip): the Guard's scolding, brisk and bossy; the Little Guard silent; hangar ambience.
   THE RHYTHM & FORCE (this clip): a tiny commander dressing down her subordinate in front of a wall of war machines — the scale gap is the joke.
   EMOTION ARC (this clip): the Guard, furious-cute; then, switching to tattletale delight as she reports upward.
   Dialogue — The Guard (~0:10-0:13, to the Little Guard): "我不是叫你看好这个地方吗，来人都不知道，今天别想喝汽油了"
   Dialogue — The Guard (~0:14-0:18, calling off-screen): "姐姐，有个不知道从哪冒出来的人，发现了我们的秘密基地，你赶快过来一下呀"
   [9.8-14.5s] Shot 3 — medium wide, POV still, scene A: the Guard stands small before the towering mech row, hands on hips, scolding the Little Guard, who shrinks beside her; the blue mech cores glow behind them like a jury. Avoid: the mechs moving; the Little Guard answering back; the camera approaching.
   [14.5-19.6s] Shot 3 continues: the Guard turns half toward the hangar doors and calls out the report, one hand cupped beside her mouth, glancing back at the lens with a got-you grin between phrases. Avoid: her sister entering yet; shouting distortion; subtitles.
   Whole-clip Avoid: no subtitles or on-screen text, no watermark, no extra characters, no gasoline cans or props appearing.
   
   CLIP 3 of 6 — source 0:19.6-0:29.4. The Elder Sister arrives and appraises the specimen.
   Sound (this clip): her lines arrive slowly, evenly, straight into the lens; the score thins to almost nothing under her.
   THE RHYTHM & FORCE (this clip): stillness with authority — she barely moves and the scene rearranges itself around her.
   EMOTION ARC (this clip): cool inspection warming by one degree into approval: the specimen passes.
   Dialogue — The Guard (~0:19, presenting): "就是他"
   Dialogue — The Elder Sister (~0:21-0:26, into the lens): "长得还不赖。我们这里已经很久没有出现过男人了"
   Dialogue — The Elder Sister (~0:26-0:28, turning away): "先带回去吧，跟我来"
   [19.6-26.5s] Shot 4 — close-up, very slow push-in, scene A: the Elder Sister fills the frame, white-blue hair falling past her shoulders, the clear coat catching the hangar light; she studies the lens in silence for a beat, then delivers her verdict lines without blinking, the Guard small and smug at the frame edge. Avoid: her smiling broadly; the Guard interrupting; camera shake.
   [26.5-29.4s] Shot 5 — following shot, POV, scene A into B: she turns and walks; the camera falls in behind the two girls as they lead the way out of the hangar toward the neon corridor glow. Avoid: seeing the man's body or hands; the girls looking back in this shot.
   Whole-clip Avoid: no subtitles or on-screen text, no watermark, no touching of the camera, no crowd.
   
   CLIP 4 of 6 — source 0:29.4-0:39.2. Scene B: the corridor of the year 2350.
   Sound (this clip): corridor hum and soft synth; his two bewildered lines as voice-over; her answers over her shoulder.
   THE RHYTHM & FORCE (this clip): a walk-and-talk where every answer makes it worse for him.
   EMOTION ARC (this clip): his wonder curdling into dread; her patience, almost gentle.
   Dialogue — The Man (voice only, ~0:31): "这里是哪儿"
   Dialogue — The Man (voice only, ~0:32-0:35): "感觉科技很发达，又给我一种破败的感觉"
   Dialogue — The Elder Sister (~0:35-0:39): "现在是2350年。看样子，你不是这个世界的人"
   [29.4-34.5s] Shot 6 — following shot, POV, scene B: down the pink-purple neon corridor behind the two girls, their hair and the clear coat lit by the strips; the Guard glances back once, grinning; his two lines play over the walk. Avoid: the girls stopping; other people in the corridor; the camera overtaking them.

3. Generate Clips 5–6: The last city and the canopy ending

   Paste the final prompt into Muse to generate CLIP 5 (last city and welcoming committee) and CLIP 6 (punchline and canopy), covering ~0:39.2–0:58.8.

   Execution prompt · Source text。Muse video generation input field

   Copy prompt

   [34.5-39.2s] Shot 6 continues: the Elder Sister half-turns her head and answers over her shoulder without breaking stride — the year, and the fact that he does not belong to it — and keeps walking. Avoid: a full stop for the exposition; a shocked reaction shot of the man; subtitles.
   Whole-clip Avoid: no subtitles or on-screen text, no watermark, no vehicles, no signage with readable words.
   
   CLIP 5 of 6 — source 0:39.2-0:49. Scene C into D: the last city, and the welcoming committee.
   Sound (this clip): the security door's red alarm glow and chime; then birdsong and water in the green city; her final corridor line at the start.
   THE RHYTHM & FORCE (this clip): the world opens — concrete and neon give way to a forest under a roof of light, and the camera should feel small in it.
   EMOTION ARC (this clip): revelation, then the first touch of being an exhibit.
   Dialogue — The Elder Sister (~0:39-0:41): "这里是人类最后的城市之一"
   Dialogue — A Trio girl (~0:47-0:49, staring): "这是什么生物"
   [39.2-44.5s] Shot 7 — following into wide, POV, scenes C and D: through the red-lit security doorway the corridor ends and the indoor forest city opens — wet stone paths, wooden houses, mist, screens floating between trees; the two guides walk ahead into the green. Avoid: a sunny outdoor look; crowds; the camera flying.
   [44.5-49.0s] Shot 8 — medium shot, slow POV approach, scene D: ahead on the path, three girls in metallic silver dresses stand waiting and turn to stare at the camera as it nears; the first of them asks her question like a child at a fence. Avoid: the trio smiling warmly; the guides leaving frame; subtitles.
   Whole-clip Avoid: no subtitles or on-screen text, no watermark, no animals, no rain.
   
   CLIP 6 of 6 — source 0:49-0:58.8. Scene D: the punchline and the canopy.
   Sound (this clip): the trio's lines in quick succession; his two panicked lines rising; the score resolving into wonder for the final wide.
   THE RHYTHM & FORCE (this clip): the joke lands in faces, then the film exhales into one big quiet landscape. If the ending stays on faces, it is wrong.
   EMOTION ARC (this clip): the girls' innocent scientific curiosity versus his total meltdown — then nobody cares, and the city is beautiful anyway.
   Dialogue — A Trio girl (~0:49-0:52): "我看过资料，这个叫男人"
   Dialogue — Another Trio girl (~0:52-0:53): "男人不是已经灭绝了吗"
   Dialogue — The Man (voice only, ~0:53-0:56, panicking): "这到底是哪儿啊？男人灭绝又是什么东西啊，我靠"
   [49.0-55.5s] Shot 9 — close series, POV locked, scene D: the three girls lean in toward the lens one after another, delivering the identification and the extinction line with bright, blameless curiosity, the Elder Sister and the Guard watching at the edges like staff at an exhibit. Avoid: anyone laughing at him; pushing or touching the camera; his hands entering frame.
   [55.5-58.8s] Shot 10 — extreme wide, slow rise, scene D. Hard cut: the whole party walks away small along the wet path, and the camera lifts to the misty green canopy of the indoor city, holographic billboards drifting between the treetops. THE VIDEO ENDS on the canopy, quiet and vast. Avoid: faces in the final shot; text overlays; a fade to black before the canopy registers.
   Whole-clip Avoid: no subtitles or on-screen text, no watermark, no extra men anywhere, no modern clothing.
   
   This is a reverse-engineered prompt; the generated result cannot fully match the original video and needs further optimization.

Muse Video Prompt
Format lock: Aspect ratio 3:4 (source 1080x1450, 30 fps; generate at 1080x1440, 30 fps) — the output MUST use exactly this ratio; no cropping, no reframing, no letterbox change.
Total runtime: about 59 seconds in 6 clips.

A first-person POV sci-fi comedy in photorealistic doll-like CG: a modern young man wakes in the year 2350, in one of humanity's last cities — a place run by beautiful android girls and giant mechs, where men are extinct. THE CAMERA IS THE MAN. He is never seen; only his voice is heard. Every girl speaks to the lens, points at the lens, studies the lens. The whole joke and the whole charm live in that direct address.
Identity — THE GUARD: A girl of about nineteen with long black hair, twin side locks and small black horn-like hair accessories; glossy doll features, sly bright eyes, pink-gloss lips. A silver chrome cropped tech jacket over a black outfit with a short skirt and a slim choker. Cheeky and menacing in turns, always performing for the lens.
Identity — THE LITTLE GUARD: A shorter, younger girl with pink-purple gradient hair in a matching chrome outfit; mostly soft-focus or mid-frame; she exists to be scolded.
Identity — THE ELDER SISTER: A tall woman with very long straight white-blue hair to her hips, pale porcelain skin, calm appraising eyes. A white top under a transparent clear-vinyl long coat, a black tech collar with metal fittings at her throat. She never hurries and never raises her voice; she evaluates the camera like a specimen she might keep.
Identity — THE TRIO: Three resident girls of the forest city — one silver-blonde bob, one brown-haired, one green-haired — in metallic silver dresses, curious as children at a zoo.
Identity — THE MAN (voice only): a young man's Mandarin voice, bewildered, increasingly panicked; he is the camera, never visible, no hands, no body.
World & scenes: (A) a dark mech hangar — a row of giant white bipedal mechs with glowing blue ring cores in their chests, a control console with holographic screens; (B) a neon corridor washed in pink and purple light strips; (C) a red-lit security doorway; (D) an indoor forest city — wet stone paths, wooden houses, drifting mist, floating holographic billboards, lush green canopy overhead.
Music and sound: a light, curious sci-fi score — soft synth pads and plucked notes, comedic timing, never horror; servo hums and hangar ambience under scene A; the girls' voices are clear Mandarin, spoken straight into the lens.
Camera: POV handheld feel throughout — the small sway of a person standing, breathing, following; girls repeatedly break the fourth wall by design; hard cuts between beats.

CLIP 1 of 6 — source 0:00-0:09.8. Scene A: the peeping and the discovery.
Sound (this clip): hangar hum, soft mech servo idle; the Guard's two lines, very close to the microphone of the scene.
THE RHYTHM & FORCE (this clip): stealth, then a face arriving too close — the comedy is the invasion of the lens. If she keeps a polite distance, it is wrong.
EMOTION ARC (this clip): she plays cat-and-mouse for one second, then owns him completely.
Dialogue — The Guard (~0:06-0:09, into the lens): "你是谁，为什么偷窥我"
Dialogue — The Guard (~0:09, pointing): "差点就被你发现了"
[0.0-5.5s] Shot 1 — POV wide, slow creeping drift, scene A: from behind a console, the row of giant white mechs with blue ring cores, holographic screens glowing; the camera peeks and settles like someone hiding. Avoid: any person in frame; fast movement; the mechs moving.
[5.5-9.8s] Shot 2 — face macro series, hard little push-ins, scene A: the Guard's face suddenly fills the screen — a sly smile straight into the lens, closer still until her eyes and nose are a macro landscape, then she pulls back a fraction and points directly at the camera as she delivers the two lines. Avoid: her looking anywhere but the lens; a frightened expression; subtitles appearing.