由 Alibaba 出品

Wan 3.0 提示詞

Alibaba's Wan 3.0 — up to 30-second clips from multimodal inputs, turning even documents into video.

video
Approximately 16 seconds, vertical 9:16, polished cinematic 3D animation. Match the reference video's complete duration and original pacing. Preserve its beginning and ending without adding an introduction or extending the final pose. REFERENCE ROLES Video reference: the source for the complete performance, action sequence, timing, emotional progression, camera behavior, framing and audio. Image 1: the new father. Preserve his exact face, green-hazel eyes, wavy auburn hair, fuller reddish-brown beard, body design, sage green knitted sweater, navy trousers and cream sneakers. Image 2: the new toddler daughter. Preserve her exact face, green-hazel eyes, curly auburn pigtails, mustard bows, toddler proportions, mustard corduroy pinafore, ivory blouse, cream tights and brown ankle boots. The images define character appearance, clothing and 3D rendering style only. Do not copy their standing poses, studio backgrounds, portrait composition or studio lighting into the scene. Replace both original characters and their entire outfits with these two referenced characters from the first frame onward. No gradual transformation, blended identities or remnants of the original outfits. ACTION AND PERFORMANCE Follow the video reference throughout, preserving every action in its original order and at its original time. Do not create a new choreography or rearrange the emotional beats. Begin with the new father already holding the new daughter in the equivalent position shown at the start of the video. Keep the father on screen left and the daughter on screen right, matching the reference's orientation and framing. Preserve the original head movements, hand movements, touches, kisses, eye contact, facial reactions, smiles, laughter and final embrace. Preserve the natural pauses and transitions between these actions. Add no extra gestures or repeated kisses. Transfer the reference performance onto the new character designs. Preserve the direction, rhythm, intention and timing of each movement while making only the small spatial adjustments needed for their different facial shapes, hair and beard. For every touch or kiss, preserve the intended contact target from the video. Hands must reach the new character's actual cheek or beard surface. Faces approach, make gentle contact and separate naturally. Do not copy coordinates that cause hands or faces to intersect. The father's fuller beard remains consistent with Image 1. It compresses slightly under the daughter's fingers or against her face and returns naturally after contact. Preserve the daughter's small toddler scale relative to her father. Her individual reference image fills its frame for presentation only; it does not mean she is adult-sized. The father supports the daughter's weight continuously. Keep his supporting arms and hands anatomically connected and consistent with the reference action, including when they are partially outside the frame. EMOTIONS Match the original emotional progression rather than displaying one fixed expression. Reproduce the father's affectionate gaze, smiles, eye closures, emotional reactions and visible tears at the corresponding moments in the reference. Do not introduce tears earlier or exaggerate them into sobbing. Reproduce the daughter's changing expressions, playful attention, affectionate reactions and laughter at their original moments. Preserve who looks at whom and when. Match the final cuddle and the characters' closing expressions to the video reference. Do not replace the ending with a pose toward the camera. LOCATION AND LIGHTING Change the background subtly to a slightly different cozy family living room: warm beige walls, a softly blurred pale oak shelf and a small muted green houseplant. Keep these elements in the background and outside the characters' movement paths. No additional people or background activity. Preserve the video's warm light direction, soft shadows, intimate atmosphere and shallow depth of field. Adapt that lighting to the new characters and clothing. The background remains visually secondary to their faces and interaction. CAMERA AND TIMING Follow the reference video's shot structure, camera height, perspective, framing and camera movements. Preserve any cuts only where they exist in the reference. Keep the intimate framing. Do not widen the shot to display the complete outfits or shoes. Clothing appears only where naturally visible within the original composition. Do not add camera angles, cutaways, transitions, dramatic zooms, slow motion, speed ramps or extra pauses. Preserve the original action rhythm and all contact moments. AUDIO AND LIP SYNC Use the video reference's audio as the exact target for music, words, vocal delivery, pronunciation, pauses and all audible nonverbal sounds. Preserve the original language and exact wording. Do not translate, paraphrase, add dialogue or infer lines from the filename. Preserve the original speaker assignments. Synchronize the new characters' mouth movements and expressions to the corresponding speech, laughter and other vocal sounds at their original timestamps. Preserve the reference music, timing and balance with the voices. Retain sounds only where they are present in the source. Add no new music, narration or sound effects. VISUAL QUALITY AND CONTINUITY Maintain the polished stylized 3D animated-feature appearance of the character images, with expressive eyes, soft skin shading, detailed hair, knitted fabric and corduroy. Keep both identities and outfits stable throughout. Preserve the father's beard shape and the daughter's hairstyle, bows and toddler proportions across all movement. Hair and clothing respond naturally to motion and contact.
Create a 30-second ultra-realistic cinematic cyberpunk action sequence featuring a fierce young female warrior with short electric-blue hair, wearing futuristic red, silver, and black tactical armor. She is running across a wet rooftop in a futuristic neon-lit city at sunset, while several dark, zombie-like enemies chase her. She performs an incredible slow-motion jump across rooftop obstacles, lands gracefully on the wet ground, and immediately engages enemies in an intense martial arts battle using a metal sword. Show powerful kicks, fast sword strikes, realistic combat movements, dynamic dodges, and dramatic enemy takedowns. During the fight, a female enemy wearing futuristic red armor joins the battle. The main heroine jumps into the air, swings her weapon, and defeats multiple attackers. A nearby wooden structure explodes dramatically, sending sparks, smoke, and debris into the air. End with the blue-haired warrior standing confidently on the rooftop, holding her sword while looking toward the glowing futuristic skyline. Visual Style: Photorealistic AAA video game graphics, cinematic cyberpunk atmosphere, neon city lights, wet reflective rooftop, realistic physics, dramatic explosions, volumetric smoke, dynamic camera tracking, slow-motion action shots, detailed character faces, consistent character appearance, 4K, high detail, 9:16 vertical format. Negative Prompt: Cartoon style, blurry frames, distorted faces, extra limbs, unrealistic movements, character inconsistency, floating objects, bad anatomy, watermark, text.
Main Concept: A girl is enjoying her favorite ice cream with her adorable white Persian cat when a terrifying ghost suddenly crawls out of the television. But the ghost doesn't want to haunt her… it wants her ice cream! 👻🍦 Main Characters 1\. Girl – UGC Model A beautiful young adult woman with naturally glowing skin, expressive eyes, long silky hair, and a cozy, stylish red-and-white outfit. Natural makeup, charming personality, and authentic facial expressions. 2\. Cat – The Adorable Sidekick An exceptionally fluffy, pure-white Persian cat with gorgeous blue eyes, silky fur, and a tiny red bow around its neck. Realistic feline movements and adorable reactions. 3\. Ghost – The Unexpected Villain A terrifying, photorealistic ghost with pale translucent skin, dark hollow eyes, long messy hair, and creepy supernatural movements. A genuinely frightening appearance with realistic physical interaction. Scene 1 – The Irresistible Ice Cream (0–6 Seconds) A beautiful, cozy modern living room at night. Warm golden lighting, a large television playing a movie, and a comfortable sofa. The girl sits on the sofa with her adorable white Persian cat beside her. She holds a delicious, premium-looking ice cream tub with a beautiful branded design. She opens the lid, revealing creamy vanilla and chocolate ice cream with rich chocolate swirls. Extreme macro close-up: * A spoon slowly scoops through the creamy ice cream. * Thick chocolate sauce drips naturally. * A delicious scoop reveals its soft, creamy texture. * She takes a generous bite and closes her eyes with satisfaction. She smiles and says naturally: Girl: "Oh my God! This is SO good!" Her cat curiously watches the spoon. Sound: Satisfying lid opening, spoon scraping, creamy bite, and cozy background music. Scene 2 – Something Is Watching (6–12 Seconds) Suddenly, the television freezes. The movie glitches. The warm lighting slowly fades, replaced by a mysterious deep-red glow. The girl stops eating. Her cat raises its ears and stares directly at the television. A creepy whisper emerges from the screen: Ghost Whisper: "I... want... some..." The girl looks confused. Girl: "What was that?" The camera slowly pushes toward the television. Scene 3 – The Ghost Wants Dessert (12–19 Seconds) Suddenly, two terrifying pale hands emerge from the television screen. The screen transforms into a realistic liquid-like portal. A frightening ghost slowly crawls out of the television and lands on the living room floor. The girl freezes in terror. Her cat jumps backward with its fur slightly raised. The ghost slowly turns its head toward the girl. A terrifying silence. Then its eyes move toward the ice cream tub. The ghost points at the ice cream. Ghost: "GIVE... ME... THAT!" Scene 4 – The Great Ice Cream Heist (19–25 Seconds) Instead of attacking the girl, the ghost suddenly rushes forward and snatches the entire ice cream tub from her hands. The girl screams: Girl: "HEY! THAT'S MINE!" The ghost grabs the spoon, takes an enormous scoop of ice cream, and eats it. Its terrifying expression suddenly changes into pure happiness. Ghost: "Mmmmm... HEAVEN!" The ghost quickly turns around, jumps backward into the television, and disappears with the ice cream. The television flashes. The room returns to its original warm lighting. Scene 5 – The Sweetest Twist Ending (25–30 Seconds) The girl stares at her empty hands in disbelief. Her cat slowly looks at her, then at the television. She takes a deep breath. Girl: "I can't believe I just got robbed by a ghost... for ice cream!" Suddenly, the television turns on again. Inside the movie, the ghost appears sitting comfortably, happily eating the ice cream with a spoon. The ghost looks directly at the camera and gives a satisfied thumbs-up.
Cinematic surreal transformation video, photorealistic with fantasy and digital glitch elements.The video opens with extreme close-ups of black chunky sneakers with thick white soles and silver accents, worn with black cargo pants, stepping on a dark, wet, highly reflective black floor against a pure black void. Water droplets and reflections shimmer. As the foot plants, a small patch of lush green grass and wildflowers (white daisies, purple and pink blooms) instantly blooms and spreads under the shoe with soft particle bursts.The camera slowly pulls back as the person walks forward. More grass and flowers grow with every step, turning the wet darkness into a vibrant meadow. Reveal the full figure from the side: a person in a light gray/silver hooded technical jacket with black backpack-style straps, black cargo pants with multiple pockets, hands in pockets, face mostly obscured by the hood. They walk calmly through the expanding field.The environment fully transforms into a vast, sun-drenched fantasy meadow at golden hour. Warm sunlight rays pierce through mist, illuminating rolling hills covered in dense wildflowers (pink, purple, white, blue, yellow), moss-covered rocks, scattered trees with pink blossoms, distant mountains with fog in the valleys, and soft clouds. Butterflies flutter throughout the scene. The person continues walking deeper into this beautiful landscape, small and centered in the wide shot. Near the end, the scene begins to glitch: green digital wireframe grids, pixelated fragments, floating light particles, and holographic butterflies overlay the meadow. The environment partially dissolves into a black void filled with sparkling particles and digital artifacts. The video closes by returning to extreme close-ups of the same black sneakers stepping on the wet reflective floor, now with floating particles and residual glitch https://t.co/2FKTSvXYLd notes: High-detail cinematic lighting, smooth transformation, dramatic contrast from dark/wet void to warm golden-hour paradise then digital glitch, shallow-to-deep depth of field transitions, elegant slow camera pull-back and tracking. Mood is mysterious, hopeful, and slightly cyber-surreal.
Create a 30-second ultra-realistic cinematic Korean morning self-care routine featuring a beautiful young Asian woman with natural black shoulder-length hair, glowing skin, and a peaceful personality. Scene 1 (0–5s): Close-up cinematic shot of hands carefully cracking a fresh egg into a small dark bowl, warm morning sunlight illuminating the scene. Scene 2 (5–10s): The woman sits in a cozy modern bathroom, gently tying her hair back before beginning her morning skincare routine. Scene 3 (10–15s): Close-up shots of her washing her face with clean water, gently splashing water onto her cheeks. Realistic water droplets and natural skin texture. Scene 4 (15–20s): She gently pats her face dry with a soft white towel, revealing fresh, glowing skin. Scene 5 (20–25s): Beautiful close-up of her peaceful face resting on a soft white pillow, golden sunlight falling naturally across her skin. Scene 6 (25–30s): She gets out of bed, slips her feet into soft cream-colored bedroom slippers, and enjoys a peaceful morning. VISUAL STYLE: Ultra-realistic Korean lifestyle commercial, premium skincare advertisement aesthetic, warm golden-hour sunlight, soft beige and cream color palette, natural skin texture, macro close-ups, cinematic shallow depth of field, smooth camera movements, realistic water physics, elegant composition, 4K UHD. Maintain consistent facial identity, hairstyle, clothing, bathroom and bedroom environment throughout the entire video. No cartoon effects, no distorted hands, no extra fingers, no text, no logos, no watermark.
THE WARNING WAN 3 | 30 seconds | 3:4 | Psychological crime thriller Use the supplied image as the opening frame and permanent reference for Woman 1. Preserve her exact facial identity, slicked-back dark hair, gray cropped jacket layered over white sleeves, oversized gray cargo jeans, black-and-white sneakers, pink shoulder bag, and natural skin texture. Hyperrealistic live-action cinema, believable physics, natural acting, restrained expressions. Oslo, Norway. Hard cuts between shots. No continuous soundtrack, only environmental sound and dialogue. CHARACTER IDENTITIES Woman 1: Protagonist from the supplied image, young woman with distinctive gray streetwear and pink bag. Woman 2: Unfamiliar young blonde woman with shoulder-length hair, dark coat, and anxious demeanor. Appears only in Scenes 1–2. Woman 3: Woman around 40, understated dark clothing, composed and intimidating. Seated inside the apartment. Man 1: Man around 40, understated dark clothing, controlled and quietly threatening. Seated beside Woman 3. Man 2: Solidly built man in his 30s or 40s, ordinary dark clothing, intimidating physical presence. Concealed behind the apartment door. All five characters have distinct facial identities. Never interchange or duplicate characters. SCENE 1 | THE ENCOUNTER | AFTERNOON | 0–5s Grünerløkka, Oslo. Continue naturally from the starting image. Woman 1 walks along the lively sidewalk past outdoor cafés. Woman 2, a complete stranger to Woman 1, steps directly into her path. Woman 2, relieved: "There you are. I've been looking everywhere for you." Woman 1 stops, confused, studying this unfamiliar woman. SCENE 2 | THE WARNING | AFTERNOON | 5–9s Closer two-shot on the sidewalk. Woman 2 leans toward Woman 1, lowering her voice. Woman 2, urgently: "Whatever you do, don't go home tonight." Woman 2 glances over her shoulder, visibly frightened, then quickly disappears into the passing pedestrians. Woman 1 watches her leave, unsettled. Hard cut to nighttime. SCENE 3 | THE BUILDING ENTRANCE | NIGHT | 9–14s A modest urban Oslo apartment building with brick exterior, short entrance steps, and warm entry lighting. Quick hard cuts: Woman 1 approaches along the sidewalk; climbs the entrance steps; tight stationary close-up of the electronic RFID key-fob reader mounted beside the entrance door. The close-up must simultaneously show the reader, its indicator light, the door handle, and Woman 1's hand. Woman 1 raises her key fob to the reader. The red light turns green. A clear electronic beep sounds, followed by the mechanical click of the door unlocking. Without changing camera framing, Woman 1's hand moves from the reader to the handle and pulls the door slightly open. Hard cut. SCENE 4 | THE STAIRWELL | NIGHT | 14–16s Two-second shot of Woman 1 ascending a narrow, modest European apartment stairwell. Warm overhead lighting, worn but clean surfaces. Her footsteps echo naturally. Hard cut. SCENE 5 | THE OPEN APARTMENT | NIGHT | 16–20s Interior corridor. Close-up of Woman 1's apartment door, clearly displaying apartment number "304." The door is slightly ajar, revealing darkness inside. Hard cut to Woman 1's face. She freezes. Her eyes widen subtly, her lips part, and her expression shifts into genuine apprehension. Restrained, believable shock, no exaggerated acting. Woman 1 cautiously pushes the door inward and steps into the dark apartment. SCENE 6 | THE VISITORS | NIGHT | 20–26s Reveal a very small, efficient Scandinavian apartment. A compact kitchenette opens directly into a tiny living area with a modest sofa, inexpensive but tasteful furniture, and a few personal possessions. Realistic young-adult rental, not luxurious. Between the kitchenette and living area sits a simple four-chair dining table. A shallow dish-shaped metal pendant lamp hangs approximately 75 cm above it, casting a concentrated pool of warm light. All other lights are off. The apartment's edges remain dark. Man 1 and Woman 3 sit side by side at the table facing the entrance. Both appear connected to a criminal underworld through their controlled demeanor, understated dark clothing, and quiet authority. No obvious gangster costumes or weapons. Man 1 regards Woman 1 with cool impatience. Man 1: "It's about time you got home." Woman 3 remains seated, expression serious. Woman 3: "We need to talk." Neither Man 1 nor Woman 3 stands. Their calmness makes the intrusion more disturbing. SCENE 7 | THE DOOR | NIGHT | 26–30s Hard cut to a tight medium close-up of Woman 1 facing into the apartment. Warm ambient spill from the pendant lamp softly illuminates her face. Woman 1 is stunned and apprehensive, holding herself still. Behind Woman 1, clearly visible over one shoulder, the apartment's inward-opening front door remains partly open. Man 2 has been concealed behind it. He is intimidating without looking theatrical. Man 2 emerges just enough to be visible, looks toward the door, reaches for it, and forcefully slams it shut behind Woman 1. The door closes completely with a single loud, heavy impact. IMMEDIATE HARD CUT TO BLACK ON IMPACT. The slam echoes briefly over the black screen. End. PRODUCTION RULES Maintain Woman 1's exact identity, wardrobe, and pink bag throughout. Woman 2, Woman 3, Man 1, and Man 2 must remain visually distinct and never exchange appearances or dialogue. Woman 2 appears only during the afternoon encounter. Woman 3 and Man 1 remain seated throughout Scene 6. Man 2 appears only during the final reveal. Natural European urban environments, realistic apartment proportions, convincing lighting and shadows. Precise spatial continuity: the entrance, dining table, seated visitors, and hidden Man 2 must occupy physically consistent positions. No extra characters inside th
HONG KONG, MONG KOK - THEY'RE LATE WAN 3.0 | Leonardo AI | 30 seconds | 3:4 vertical Use the supplied image as the exact opening frame. Preserve Man 1 and Woman 1's faces, hairstyles, proportions, and clothing throughout. Authentic Mong Kok streets, illuminated storefronts, Chinese signage, crowds, and evening traffic. Handheld iPhone 17 Pro realism. Quick hard cuts, varied 1.5–3-second shots, longer for dialogue. Natural environmental audio only. No soundtrack. SCENE 1 (0–3s): OPENING WALK Begin with the supplied image. Man 1 and Woman 1 walk briskly toward the camera through crowded Mong Kok. Camera tracks backward, keeping both faces visible. Opening title: "HONG KONG, MONG KOK" bottom-center, white Poppins Semi-Bold on a dark #17212B rounded rectangle at 60% opacity. Visible for 2 seconds, then disappears permanently. No further subtitles or overlays. SCENE 2 (3–7s): THE MESSAGE Handheld two-shot while walking. Woman 1 checks her phone, smiles, and looks at Man 1. Woman 1 (amused): "They're asking where we are." Man 1 (casual): "Tell them we're almost there." She gives him a knowing look. SCENE 3 (7–12s): ARRIVAL Hard cut inside an upscale contemporary Hong Kong foodie restaurant. Refined contemporary-traditional fusion: low ceilings, large street-facing windows, warm architectural lighting, pale oak, textured stone, brushed bronze, restrained Chinese design accents, clean lines, and elegant table settings. Sophisticated but lively, modern and welcoming rather than formal. Man 1 and Woman 1 enter and approach four friends seated together: Man 2, Man 3, Woman 2, and Woman 3. Friends recognize them and gesture enthusiastically. Man 2 (joking): "Finally! We thought you weren't coming!" Everyone laughs. SCENE 4 (12–18s): THE BLAME GAME Handheld medium group shot. Man 1 playfully gestures toward Woman 1. Man 1: "She took forever getting ready." Woman 1 turns toward him with amused disbelief. Woman 1: "He changed his outfit three times!" Everyone bursts into genuine laughter. Man 1 smiles sheepishly. Natural overlapping reactions and believable comedic timing. SCENE 5 (18–26s): THE MEAL AND NEXT PLAN Quick hard cuts clearly showing time passing throughout dinner. Same restaurant, table, and characters. Cut 1: Drinks arrive, beautifully plated modern Cantonese dishes are served. Friends begin eating, chatting, and smiling. Cut 2: Mid-meal. Everyone eats, shares dishes, and laughs. Plates are partially empty, glasses used, table naturally busy. Cut 3: Dinner finished. Plates empty or cleared, remaining glasses on the table. Everyone leans back comfortably, smiling, relaxed and visibly satisfied after a substantial meal. Final beat: Woman 1 leans back in her chair, looking pleasantly full and playful. Friends beside her share the same relaxed, post-dinner body language. Woman 1 (enthusiastic): "Who's up for another place? I know a great bar right around the corner!" Friends exchange amused, enthusiastic looks and agree. Clearly establish the progression from beginning dinner to finishing the entire meal. SCENE 6 (26–30s): BACK INTO MONG KOK Hard cut to the group emerging onto a vibrant Mong Kok sidewalk. Warm restaurant lighting behind them, neon storefronts, pedestrians, and traffic. Man 1 and Woman 1 walk alongside their friends, smiling and laughing. End with a lively front-facing handheld group shot as they head toward the bar. PRODUCTION RULES Hyper-realistic live-action. Visible pores, natural skin texture, realistic eyes, expressive microexpressions, believable anatomy and movement. No waxy, oily, plastic, or airbrushed skin. Lock all character identities and wardrobes. Accurate hands, fingers, doors, and physical interactions. Natural walking continuity. English dialogue only, expressive and conversational, synchronized lips, correct speakers. No specified accents. Handheld iPhone 17 Pro cinematography, natural exposure and lighting. Hard cuts only, no morphing or impossible transitions. Protagonists visible from front or three-quarter angles, never from behind. Natural independent crowd movement. Authentic Hong Kong environment, no gibberish signage. Opening title only, no additional subtitles or text. Diegetic audio only: traffic, footsteps, restaurant ambience, dishes, conversations, and laughter. No musical score. Prioritize genuine social chemistry, natural humor, clear passage of time during dinner, and a lively finish.
Create a 15-second ultra-realistic 16:9 landscape video featuring the same naturally attractive 24-year-old Korean woman with long loose dark hair, minimal makeup, an oversized maroon hoodie, loose casual pants, and a soft knitted scarf. Preserve her exact facial identity, hairstyle, outfit, scarf, and body proportions across every shot. Shot 1 — 0–3 seconds: On a quiet tree-lined neighborhood sidewalk during a breezy autumn afternoon, she walks slowly beneath chestnut trees. She notices a shiny brown chestnut lying on the pavement near a fallen leaf. She pauses, bends down, and picks it up with a curious expression. The camera follows her casually from a few steps away. Shot 2 — 3–6 seconds: She turns the chestnut between her fingers, examining its smooth, glossy surface. She smiles and holds it up toward the camera as if proudly showing off her little discovery. In the background, another chestnut drops from a tree and lands nearby. Shot 3 — 6–9 seconds: She hears the soft impact and turns her head. Suddenly, several chestnuts begin falling from the tree around her, bouncing lightly across the pavement. She instinctively steps back, startled, then looks upward with wide eyes as another chestnut drops close to her shoe. Shot 4 — 9–12 seconds: She quickly moves out of the falling chestnuts' path, laughing in surprise. One chestnut rolls toward her foot, and she gently stops it with the toe of her shoe. She crouches to pick it up, still smiling at the unexpected little shower. Shot 5 — 12–15 seconds: She holds the two chestnuts in her palm, compares them with an amused expression, and carefully slips them into her hoodie pocket. Before walking away, she glances up at the tree as if wondering whether more are coming. A final chestnut falls in the background, and she gives a playful, surprised look toward the camera. Visual style: Authentic early-2000s Sony MiniDV home-video footage filmed by another person, not a selfie. Slight handheld shake, imperfect framing, spontaneous camera reframing, occasional autofocus hunting, subtle exposure shifts, soft contrast, slightly faded colors, realistic skin texture, and natural autumn afternoon light. The falling chestnuts should look like real chestnuts, with believable size, weight, bouncing, and rolling movement. Motion quality: Smooth, continuous real-time movement. Natural walking, bending, hand gestures, facial reactions, and realistic chestnut physics. Keep the falling chestnuts scattered and occasional rather than creating an impossible continuous rain. Maintain consistent facial identity, hairstyle, outfit, and body proportions across every shot. No stuttering, judder, frame skipping, duplicated frames, slow motion, teleporting objects, or exaggerated cartoon-like reactions. Audio: Natural outdoor ambience only—soft footsteps, a light breeze, rustling leaves, chestnuts tapping and bouncing on the pavement, and her spontaneous quiet laughter. No background music, narration, or artificial sound effects.
Create a cinematic, dark fantasy fashion film in vertical 9:16 format, featuring a mysterious woman in a flowing crimson-red gown. Scene 1: A mysterious hooded woman slowly extends her hand toward the camera, holding glowing red magical dice. Dramatic close-up, mysterious expression, dark atmosphere, glowing particles and cinematic lighting. Scene 2: Transition into a magnificent gothic palace with a grand black-and-white chessboard floor. A powerful queen stands in an elaborate black outfit, surrounded by ornate chandeliers, dramatic architecture and symmetrical compositions. Scene 3: A woman wearing a flowing red silk gown dances across a vast, dark rocky landscape under a stormy sky. Her dress moves dramatically in the wind. Scene 4: Aerial shot of a woman in a red dress surrounded by powerful ocean waves, creating a circular white-water pattern around her. Smooth cinematic drone movement. Scene 5: A mysterious woman in red stands alone among endless rows of dark hooded figures. Slow camera movement, symmetrical composition, surreal atmosphere and dramatic contrast. Scene 6: A surreal fashion sequence featuring the woman spinning inside enormous circular architectural structures, followed by a dramatic red-dress pose against an abstract black-and-white painted backdrop. Final Scene: A woman in a flowing crimson gown walks toward a breathtaking golden sunset through elegant white curtains above the clouds. Ethereal atmosphere, cinematic wide shot and graceful movement. Visual Style: Ultra-realistic 4K, high-fashion editorial photography, dark fantasy aesthetics, rich crimson-red color palette, dramatic lighting, realistic fabric physics, atmospheric depth, smooth transitions, elegant slow motion, sophisticated cinematic camera movements. Consistency: Maintain the same female character, facial features, hairstyle and red gown throughout all scenes.
Create a 15-second ultra-photorealistic cinematic short film set on a beautiful narrow Seoul neighbourhood street during a gentle autumn rain at night. MAIN CHARACTER: The same 24-year-old Korean woman throughout the entire video, with a naturally beautiful face, long loose dark hair, minimal makeup, oversized maroon hoodie, loose dark casual pants and a knitted scarf. Maintain identical facial identity, hairstyle, clothing and body proportions in every shot. She carries a transparent umbrella. ENVIRONMENT: Authentic Seoul residential neighbourhood, small illuminated convenience stores, Korean shop signs softly blurred in the background, wet asphalt reflecting warm amber and subtle neon lights, gentle rainfall, atmospheric evening mist. Realistic live-action cinematography, natural human expressions, physically accurate movement and detailed environmental textures. SHOT 1 — 00:00–00:04: A beautiful cinematic wide shot of the woman walking slowly along the rainy Seoul street. Camera smoothly tracks backwards in front of her at walking speed. She holds her transparent umbrella and looks around peacefully. Rain droplets collect on the umbrella. Colourful shop lights reflect across the wet pavement. A tiny golden-brown puppy is visible sheltering beneath a small shop awning in the background. SHOT 2 — 00:04–00:07: Medium close-up as the woman notices the puppy. She slows down, turns her head and looks towards it. Her expression changes into a gentle, spontaneous smile. Camera subtly pushes closer towards her face. Natural eye movement and realistic facial expressions. SHOT 3 — 00:07–00:11: Low-angle intimate cinematic shot. She gently kneels beside the puppy and moves her transparent umbrella over it, protecting it from the rain. The puppy looks up at her, slowly wags its tail and approaches her hand. She gently strokes its head. Detailed realistic fur, natural animal behaviour and delicate rain droplets. SHOT 4 — 00:11–00:15: The puppy happily follows her as she begins walking again. She looks down at it with a warm smile. Camera smoothly pulls backwards into a beautiful wide cinematic composition. The two walk together beneath the same transparent umbrella, surrounded by warm shop lights and softly falling rain. Finish with a visually beautiful, emotionally satisfying shot. CAMERA AND VISUAL QUALITY: Premium independent-film cinematography, authentic early-2000s Sony MiniDV-inspired texture, subtle organic film grain, realistic skin texture, shallow depth of field, natural motion blur, smooth continuous camera movement, beautiful warm-versus-cool colour contrast. Preserve character identity and environmental continuity across all shots. AUDIO: Realistic gentle rainfall, distant passing traffic, soft footsteps on wet pavement, subtle puppy whimper and paw sounds. Natural environmental audio only. No dialogue, no narration, no artificial music. STRICT CONSTRAINTS: No face changes, no wardrobe changes, no extra limbs, no distorted hands, no duplicated puppy, no unnatural animal movement, no sudden camera jumps, no flickering, no frame skipping, no subtitles, no captions, no watermarks, no logos. 16:9 landscape, 15 seconds, ultra-photorealistic live-action appearance.
Replace the person in Video1 with the character from Image1 (character sheet). Use Video1 as the reference for camera quality, lighting, environment, voice tone, speaking style, and overall atmosphere. Maintain the character's facial features, hairstyle, body proportions, and appearance consistently throughout the video. Preserve the natural behavior and general movements from Video1, but introduce subtle variations in facial expressions, head movements, posture, eye contact, and hand gestures so the result is not an exact copy. Keep realistic skin textures, natural blinking, breathing, and spontaneous micro-expressions. The performance should feel authentic, relaxed, and naturally recorded. Replace the original speech with the following EXACT script: {script} Speak every word clearly with natural conversational pacing and accurate lip synchronization. Preserve the intended emotion and delivery. Do not skip, change, rush, or cut off any words. Ensure the entire script is spoken completely. Negative prompt: Subtitles, captions, on-screen text, text overlays, watermarks, logos, timestamps, UI elements, robotic speech, unnatural voice, inaccurate lip sync, missing words, skipped dialogue, cut-off speech, rushed delivery, exaggerated expressions, unnatural facial movements, stiff body movements, repetitive gestures, distorted hands, extra fingers, facial deformation, identity inconsistency, flickering, face morphing, blurry facial features, plastic skin, excessive skin smoothing, artificial lighting, cinematic color grading, overprocessed footage, CGI appearance, uncanny valley, unrealistic physics, frame glitches, visual artifacts.
LEIPZIG, GERMANY — PLAGWITZ One More Stop | WAN 3.0 | 30 Seconds | 2:3 Style & Characters Use uploaded starting frame. Lock both faces, hairstyles, outfits, and proportions. Hyperrealistic early-2000s European 35mm film aesthetic, muted colors, subtle grain, natural skin pores, authentic daylight. Plagwitz's industrial brick buildings, vintage shops, creative atmosphere. Dialogue: English spoken by native Germans with clearly recognizable, natural German accents in EVERY line. German vowel sounds, consonants, and speech rhythm. No British or American accents. Understated, affectionate chemistry. Scene 1 | 0:00–0:03 — The Distraction Couple walks along Plagwitz sidewalk. Opening title "Leipzig, Germany" appears for first two seconds, white Poppins SemiBold, translucent dark background. She spots a vintage shop, catches his sleeve, smiles. He follows her gaze, amused. Store sign: "Vintage Kleidung". Smooth tracking two-shot. Scene 2 | 0:03–0:07 — Just a Minute She points at a jacket in the shop window. Woman (playful): "Just one minute." Man (dry smile): "Of course." She grabs the actual entrance door handle, opens the door, and walks THROUGH the doorway. He follows directly behind her INTO the shop. Camera follows across threshold. Never walk past the entrance. Scene 3 | 0:07–0:11 — First Jacket Inside, she pulls an oversized jacket from a rack, holds it against him. He raises an eyebrow; she laughs. Quick cut to shop mirror, him wearing it, both visible. He gives an unconvinced smile. Natural handheld framing. Scene 4 | 0:11–0:16 — One Minute, Huh? Still inside, he's back in his original outfit. She finds a patterned shirt, excitedly holds it against his chest. Woman (delighted): "Ooh, you'd look so good in this!" He sighs, subtly rolls his eyes, then smiles. Man (dry, teasing): "One minute, huh?" She laughs and gently nudges him. Affectionate, not irritated. Scene 5 | 0:16–0:20 — His Turn Outside, she's carrying a shopping bag. He spots a bakery, sign reads "Bäckerei". Man (playful): "Okay, my turn." She smiles. He opens the bakery door; both physically enter through the doorway. Side-tracking camera. Scene 6 | 0:20–0:25 — Too Many Choices Inside bakery, both lean close to a glass pastry display, faces clearly visible. They point excitedly at different cakes and pastries. Man (impressed): "Oh, that looks good." Woman (pointing): "Wait, look at this one!" He hesitates between choices. She notices, smiling knowingly. Intimate two-shot, warm lighting. Scene 7 | 0:25–0:30 — The Payoff Outside bakery, both hold pastries in paper sleeves. She carries her shopping bag. He takes a satisfied bite. Woman (teasing): "That took you long enough." He laughs, gently bumps her shoulder. They exchange genuine smiles and walk together. Finish with waist-up two-shot, subtle push-in. Production Rules 30 seconds maximum, 2:3 vertical, seven scenes, hard cuts. English dialogue with authentic German accents throughout. No subtitles. Opening title only, first two seconds. All visible signage correctly spelled in German or English. No gibberish, nonsensical text, or random letters. Unspecified text blank or blurred. Both characters physically enter shops through doors, never walk past entrances. Strict face, hair, outfit, and prop continuity. Natural expressions, subtle flirting, realistic movement, visible skin texture. No CGI or plastic skin. Ambient street/shop sounds only. No soundtrack. Both characters visible, clean compositions, no slow motion or exaggerated acting. Priority: Genuine couple chemistry, playful teasing, and a humorous reversal between clothing shopping and pastry shopping.
Create a 15-second ultra-realistic 16:9 landscape video featuring the same naturally attractive 24-year-old Korean woman with long loose dark hair, minimal makeup, an oversized maroon hoodie, loose casual pants, and a soft knitted scarf. Preserve her exact facial identity, hairstyle, outfit, scarf, and body proportions across every shot. Shot 1 — 0–3 seconds: On a quiet neighborhood street during a chilly autumn afternoon, she walks past a small house with a large glass window. She casually glances toward the window and suddenly notices her reflection. She slows down, tilts her head slightly, and gives her reflection a curious little smile. The camera follows her from a few steps behind and to the side. Shot 2 — 3–6 seconds: She stops in front of the window and raises one hand. Her reflection appears to raise its hand at exactly the same time. Amused, she moves her head slightly from side to side, watching the reflected movement with growing curiosity. Shot 3 — 6–9 seconds: She playfully tests the reflection by lifting one shoulder, making a funny face, and briefly puffing out her cheeks. The reflection mirrors every movement perfectly. She suppresses a laugh, then leans a little closer to the glass to inspect her reflection. Shot 4 — 9–12 seconds: She gently places her palm against the window, and her reflection's palm meets it from the other side. She holds the pose for a moment, smiling softly. A passing car's headlights briefly sweep across the glass, mixing with her reflection and the faint view of the room inside. Shot 5 — 12–15 seconds: She pulls her hand away, gives her reflection a tiny farewell wave, and starts walking again. After taking two steps, she glances back at the window with one last amused smile before continuing down the sidewalk. Visual style: Authentic early-2000s Sony MiniDV home-video footage filmed by another person, not a selfie. Slight handheld shake, imperfect framing, spontaneous camera reframing, occasional autofocus hunting, subtle exposure shifts, soft contrast, slightly faded colors, realistic skin texture, and natural autumn afternoon light. The glass should show a believable reflection while still allowing a faint view through the window. Keep the scene intimate, spontaneous, and charming rather than cinematic. Motion quality: Smooth, continuous real-time movement with natural walking, head tilts, hand gestures, and facial expressions. The reflection must accurately mirror her movements with correct timing and matching body proportions. Maintain consistent facial identity, hairstyle, outfit, and appearance in both the real subject and her reflection. No independent reflection movement, delayed mirroring, distorted faces, duplicated people, stuttering, judder, frame skipping, or slow motion. Audio: Natural outdoor ambience only—soft footsteps, faint wind, distant traffic, and subtle clothing movement. No background music, narration, or artificial sound effects.
Create a photorealistic cinematic video using the supplied reference video as the master for movement, actions, camera work, editing, and timing. Match its approximately 14.5-second duration and original portrait framing. REFERENCE MAPPING AND PRIORITY Photo 1: the replacement MAN at the far end of the bridge. Photo 2: the replacement WOMAN in the foreground. Use each photo as the authoritative reference for the character’s COMPLETE appearance: face, hairstyle, hair color, body proportions, clothing, footwear, jewelry, and visible accessories. Reproduce the exact outfit from each photo, including its colors, materials, silhouette, layers, and details. Replace BOTH the original actors AND their original clothing. Do not retain the original woman’s white shirt and white trousers or the original man’s white shirt and dark trousers unless those garments are actually present in the corresponding photo. Do not blend the original wardrobe with the reference outfits. The photos control character identity and wardrobe. The video controls the location, story, choreography, props, expressions, camera angles, and timing. Ignore the backgrounds and poses in the photos. Keep both characters and their complete outfits consistent throughout every shot. Clothing and accessories must move naturally with their bodies, with realistic weight, folds, and inertia. LOCATION Preserve the exact original environment: a narrow, weathered wooden suspension bridge over a deep, mist-filled rocky ravine. Dark suspension cables, vertical suspension ties, aged wooden planks, rocky ground at the near end, dense gray-blue fog, and soft overcast daylight. The man remains at the opposite end of the bridge. Preserve the original bridge geometry, distances, background, and perspective. Cold muted colors gradually acquire warm orange firelight as the bridge burns. Realistic skin, hair, clothing, shadows, smoke, and cinematic fire effects. ACTION AND SHOT SEQUENCE The reference video takes priority over the approximate timestamps below. 0.0–3.0 seconds: Match the original frontal shot of the woman walking toward the camera along the bridge. She wears the complete outfit from Photo 2. She carries the dark green bottle in her left hand and the olive-green rectangular canister in her right hand. Match her walking pace, foot placement, shoulder movement, gaze, and composed expression. She lifts the bottle to her lips and tilts it to drink while continuing to walk. Her reference clothing moves naturally with each step. The distant man wears the complete outfit from Photo 1 and repeats the original gestures, posture changes, and reactions at the same moments. 3.0–6.0 seconds: Reproduce the original low rear shot following the woman’s lower body as she walks toward the near end of the bridge. Show the actual lower garments and footwear from Photo 2. Do not recreate the original white trousers or bare feet if they differ from the photo. Match the canister’s position and tilt, the visible liquid falling onto the wooden planks, and the wet trail left behind. Preserve the exact coordination between her steps and the canister swing. Match the original camera height and movement. 6.0–8.8 seconds: Match the frontal shot of the woman reaching the rocky landing, with the bridge extending behind her. She lowers and releases the canister out of the foreground exactly as in the reference. The bottle stays in her left hand. Her right hand follows the original reaching movement toward her right hip and retrieves the small lighter. If the reference outfit has a suitable pocket, use that pocket. If it has no pocket, retrieve the lighter discreetly from behind an existing waistband or belt at the same position. Do not add a visible pocket or alter the reference outfit. Preserve the original gesture and timing. Reproduce the brief glance toward the bridge, head turn, and backward throwing gesture. The lighter leaves her hand at the same point in the movement. The first small flame appears on the bridge only after the throw. Preserve the original pause and her calm reaction. 8.8–10.8 seconds: Match the original cut to the bridge as flames spread across the planks and rise between the suspension lines. Keep the man at the far end in his Photo 1 outfit, preserving his original screen position, gestures, and reaction. Match the reference fire progression, smoke, brightness, and orange illumination as cinematic visual effects. Do not add explosions, injuries, falls, or additional events. 10.8–14.5 seconds: Match the final frontal shot of the woman on the rocky landing with the burning bridge behind her. She calmly raises the bottle to her lips again, tilts the bottle and her head back, and drinks. Match her posture, expression, hand positions, the length of the sip, and the final frame. Her face, hair, outfit, footwear, and accessories remain exactly consistent with Photo 2. Firelight illuminates the actual materials of her reference outfit naturally. Keep the man visible in the background wherever he appears in the original shot. CAMERA AND MOVEMENT Reproduce the original shot order, cuts, framing, camera height, perspective, and camera motion. Preserve the separate shots and their original transitions. Do not add new angles, close-ups, slow motion, or dramatic zooms. Transfer every gesture, step, glance, pause, prop interaction, and reaction to the replacement characters. Do not mirror the scene or swap hands. Preserve the timing and physical cause-and-effect of