East Asian Woman MiniDV Self-Filming in Tide Temple
A highly detailed cinematic prompt for Grok Imagine Video, featuring a continuous 15-second MiniDV-style self-shot of a woman exploring an ancient white jade temple above the clouds, complete with realistic camera artifacts and binaural sound descriptions.
プロンプト
The same 24-year-old East Asian female protagonist @0ba07db1-974c-467d-80dc-d9dffddac0ba wearing @27d48282-8e11-4b4e-94aa-f77a7eb8fbc1, with consistent facial features, age, and temperament throughout. Dark moist pupils, a delicate nose bridge, natural pale pink lips; skin retains pores and fine lines under the eyes, no airbrushing or 'influencer' makeup.
The protagonist always holds a silver-grey MiniDV camera in her right hand to film herself—no cameraman. Selfie distance is about 45 cm; when showing the environment, she must first rotate her wrist and body, passing the lens over her shoulder, sleeve, or a railing before facing the scenery; returning to the selfie must also involve a complete physical rotation process.
It is forbidden to show her from a third-person back view, full-body tracking, aerial shot, or external camera perspective while she is filming herself. When the camera turns to the environment, the protagonist can only continue to exist in the frame through her extended left hand, white sleeve, skirt edge, shadow, or live sound.
16:9 MiniDV widescreen mode, natural handheld with slight walking jitter, imperfect composition, brief loss of focus, hesitant autofocus, white balance drift, exposure breathing, motion blur, subtle interlacing artifacts, DV grain, soft highlight bloom, and authentic tape colors.
Each segment is a continuous 15-second selfie shot, no cuts. Between the six segments are travelogue-style time jumps, allowing for changes in weather and light, but the character, clothing, hair accessories, MiniDV, and sound must remain consistent.
The female lead's voice is a natural Mandarin Chinese spoken by an East Asian woman in her 20s, soft, warm, and curious, with occasional slight panting from walking or climbing. Not a costume drama recitation, AI narration, broadcaster, or high-energy influencer-style pitch. 15-second MiniDV selfie video | Oriental Siren Style @b061c722-4fae-42c2-aa5d-48e9dd7dc6df
This is no ordinary palace, but an ancient Tide Temple built above a sea of clouds. Inside stands an unimaginably huge white jade dragon platform: tiered lotus petal bases, spiraling dragon bodies, waves, shells, fish scales, and tide patterns are all carved from aged white jade. Tall dragon-coiled stone pillars support a dark wooden palace roof, with cold white water vapor constantly rushing in between the pillars, leaving moist water marks on the white jade surfaces.
Siren style is expressed through the real environment: cold moist vapor, pearl and mother-of-pearl reflections, low-frequency distant tides, occasionally dripping seawater, and faint female chanting. Do not directly show fish tails or exaggerated monsters.
The protagonist remains the same person, the same face, and the same white-to-pale-pink gradient hanfu. The cold moist vapor makes stray hairs by her ears stick slightly to her cheeks, and her skin shows moist reflections; the white gauze appears pale mother-of-pearl under the blue-grey water light, not a sudden outfit change. The silver hairpin, milky white bead ornaments, and dark red tassel on her wrist remain unchanged.
She always holds the MiniDV herself with her right hand, no cameraman.
0–4 seconds
The recording begins as she walks slowly along the bottom of the white jade dragon platform.
She holds the MiniDV in front of her, her face in the lower right of the frame, with the massive white jade carvings extending off-screen from above her head. It's darker here than outside, the MiniDV's auto-gain is noticeably high, and slight color noise appears in the shadows; the bright clouds behind her produce soft overexposure.
Cold vapor brushes her face, and she instinctively shrugs her shoulders, her breath forming a faint white mist in front of the lens. She touches her damp sleeve with her left hand and says in a low voice:
'Why is it... suddenly so cold here?'
She doesn't intentionally create a sense of mystery while speaking; it's just a physical reaction to the temperature.
4–8 seconds
She first looks up at the dragon platform, then slowly turns the camera outward from herself via her right wrist.
The lens passes her damp hair, silver hairpin, and white sleeve, then captures a close-up low-angle shot of the massive lotus base, the dragon statue, and the dragon stone pillars behind it. This is a realistic angle she could capture while standing below the platform, not an aerial or external panoramic view.
The autofocus first lands on mottled water marks nearby, then shifts to the high dragon head. She says softly off-screen:
'This dragon platform... looks like it rose from the sea.'
Her voice is off-axis from the microphone, slightly obscured by the low echoes and water sounds inside the palace.
8–11 seconds
Just as she finishes speaking, a short snippet of female chanting comes from the shadows behind the dragon platform.
It's not background music, but a real sound located far off in the hall: very low volume, just a soft, ethereal long note, reflecting off the pillars and the massive dome, making its direction hard to judge. The sound is mixed with low-frequency tide sounds, as if coming from a hollow structure beneath the dragon platform.
The protagonist's wrist stops immediately, the frame holding on the slightly tilted white jade carving. She doesn't turn around right away but first holds her breath and tilts her head to confirm.
Then she turns the camera back to herself, her eyes looking past the lens toward the source of the sound, and asks in a hushed tone:
'Wait... did you guys hear that?'
11–15 seconds
The chanting stops briefly. She blinks naturally once, and the curious smile on her face gradually fades.
A clear echo of a water drop falling into deep water comes from the base of the dragon platform. Immediately after, a second, closer female long note sounds from her back left. Her shoulders tighten slightly, her breathing becomes shallow, and she slowly looks at her flip screen as if confirming if the camera recorded it too.
She looks back at the lens, her voice almost a whisper:
'The one singing just now... wasn't me.'
After speaking, she doesn't scream or run but slowly turns the camera toward the dark passage behind the dragon platform. The frame passes her shoulder and damp sleeve, finally stopping on a patch of slightly vibrating shallow water beneath the white jade carving.
A ripple appears on the water surface with no visible source. The recording ends naturally with a third, extremely soft and distant chant.
Live Sound: Cold wind in the hall, slight friction of damp fabric, stone pillar echoes, dripping water, low-frequency distant tides, female chanting from behind the dragon platform. No background music, no narration.
Siren Style Performance Requirements: The protagonist does not perform seductive poses. The sequence of real reactions must be: feeling cold → observing the dragon platform → hearing the sound → holding breath to confirm → realizing the sound was not her. Use subtle eye movements, natural blinking, swallowing, tightening of shoulders, and shallow breathing to show unease.
Supplementary Negative Constraints: No cameraman, no third-person full-body shots, no external orbiting camera movement; no sudden outfit changes, no fish tails, no blue skin, no fangs, no exaggerated monster transformations; no sexy dancing, no exaggerated seductive performance; the protagonist does not open her mouth to sing, the mysterious chanting must come from the space behind the dragon platform; no background soundtrack, no horror sound effect jumpscares, no underwater filters, no palace liquefaction, no statues suddenly moving, no subtitles or watermarks.
このプロンプトの使い方
- 1
上の完全なプロンプトをコピーします。
- 2
Grok Imagine に対応したプラットフォーム（YouMind など）を開き、プロンプトを貼り付けます。
- 3
アイデアに合わせて被写体・スタイル・細部を入れ替え、生成します。
これは YouMind のプロンプトライブラリにある無料の AI プロンプトです。ほかにも数千点の 動画 プロンプトがあり、すべて自由にコピーして使えます。
ほかの 動画 プロンプトを見る
その他のプロンプト機能
ビジョンツール
画像からプロンプト
どんな写真も詳細な AI 画像プロンプトに変換。無料の Image to Prompt 変換ツールが構図・スタイル・ライティングを解析し、数秒で同じ表現を再現できます。
クリエイターのために。ずっと無料。
YouMind は世界中のクリエイターに信頼される AI 制作パートナーです。ここにあるプロンプトは、より速く、より良い制作を助けるために厳選されています。