A detailed multi-shot video prompt for Seedance 2.0 featuring two female characters in a surreal mountain setting. It utilizes camera rotation to create a Buster Keaton-style visual illusion where a cliff face appears as level ground, ending with a fourth-wall-breaking comedic reveal.
Consigne
[Generation Mode]
Seedance 2.0 Fast
[Video Specifications]
Strictly generate a 15-second video, 16:9 widescreen, with three distinct shots.
[Overall Style]
Poetic Xianxia visual illusion comedy, realistic 4K cinematic texture, using classical Chinese white-space composition, restrained deadpan performance, soft morning light, low-saturation jade green and ivory white tones, fine film grain, and borrowing from Buster Keaton-style spatial illusions to reveal the truth through controlled camera rotation rather than relying on failed magic for laughs; the entire film is a purely ancient Chinese world with no modern elements.
[Character Locking]
Use @Image 1 and @Image 2 to strictly lock character identities, faces, hairstyles, body proportions, clothing, shoes, and accessories.
Character ID A | Senior Sword Immortal Sister
East Asian female, 25–30 years old, oval face, fair natural skin tone, dark almond eyes, long black hair partially tied up with a white jade hairpin, tall and slender, wearing a white embroidered silk hanfu with semi-transparent layered wide sleeves, a silver waist seal, jade pendant, and white cloth boots.
Character ID B | Junior Martial Sister
East Asian female, 20–25 years old, round and lively face, black hair in braids, petite build, wearing a teal linen hanfu, dark belt, wooden hairpin, and black cloth shoes.
[Shot 1 | 0-5s | Wide or Long Shot]
The frame is intentionally rotated 90 degrees clockwise, making a steep cliff wall appear horizontally as the ground.
Character ID A: Senior Sister, seen from head to toe, appears to be walking calmly and upright along the vertical cliff with hands behind her back. Her hair and sleeves naturally hang toward the abyss in the frame.
Character ID B: Junior Sister appears to be clinging to an ancient pine tree below.
[Shot 2 | 5-10s | Medium or Cowboy Shot]
The Junior Sister in teal hanfu looks up and asks: "Senior Sister, is this walking on walls to reach the sky?"
The Senior Sister in white hanfu continues walking calmly and replies: "When the heart is upright, the world balances itself."
The background maintains the same cliff, pine tree, floating mist, stone platform, and distant pavilion; the false vertical orientation must be maintained without altering character anatomy.
[Shot 3 | 10-15s | Close-up or Extreme Close-up]
The camera smoothly rotates 90 degrees counter-clockwise to restore the true horizontal line, clearly revealing that the Senior Sister is actually just walking normally on a flat stone platform next to a low wall, while the Junior Sister is casually leaning against the pine tree.
The Junior Sister says expressionlessly: "Senior Sister, the world is balanced now, but the camera is crooked."
Extreme Close-up: The Senior Sister's forced dignified smile freezes, one eyebrow twitches slightly, and she replies nonchalantly: "This is to test your eyesight."
Ends with a dry guqin pluck and the sound of a pine cone hitting a stone slab.
[Technical Requirements]
Strictly 15 seconds total, 16:9 widescreen, three clear shots, native Mandarin dialogue, stable character faces and clothing, continuous scene geometry, realistic mist, silk fabric, hair, pine trees, and gravity direction, no subtitles, only two visible characters throughout.
[Negative Prompts]
blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props
Comment utiliser ce prompt
1
Copiez le prompt complet ci-dessus.
2
Ouvrez une plateforme compatible avec Seedance 2.0, comme YouMind, et collez le prompt.
3
Modifiez le sujet, le style ou les détails selon votre idée, puis générez.
Voici un prompt IA gratuit de la bibliothèque de prompts de YouMind. Découvrez des milliers d'autres prompts vidéo, tous libres de copie et d'adaptation.
Laissez l'IA chercher parmi des dizaines de milliers de prompts. Filtrez par modèle, plage de dates et mots-clés, puis triez par engagement : vues, favoris, partages et plus.
Transformez toute photo en prompt d'image IA détaillé. Le convertisseur image vers prompt gratuit analyse la composition, le style et la lumière pour recréer n'importe quel rendu en quelques secondes.
