AI Video Prompts for Close-Up Video

Macro reveals, extreme close-ups that turn a face into a landscape, product textures that demand to be touched, and the technique of making a single detail carry the weight of an entire scene — these Seedance 2.0 close-up prompts direct the camera at the scale where everything changes.

Close-up video is not about proximity — it is about revelation. The wide shot establishes; the close-up proves. A cityscape says "this is where we are"; a close-up on a specific cracked tile in the sidewalk says "this is what it costs to live here." The scale shift is the meaning, and every genre of video has a version of it. What separates a functional close-up from a great one is not how small the subject is or how close the lens is — it is whether the close-up reveals something that the wider context made invisible, and whether it does so in a frame that has its own internal compositional logic. The structural principle of close-up direction is simple and almost universally ignored in AI video prompts: name what is being revealed, not just what is being shown. "A close-up of a hand" is a framing instruction. "An extreme close-up on the back of a hand, veins raised by cold, the skin at the knuckle creased into a map, a slow pull of focus from the sharpest crease to the soft edge of the frame" is a revelation — the camera is finding something in the hand that the hand does not announce about itself. That difference — the difference between a frame and a discovery — is what close-up direction is for. There are five scales of close-up, each with a distinct spatial grammar and a distinct relationship between subject and frame. The medium close-up (MCU) frames the face from the chest to the crown, keeping the subject in full social context. The MCU is the interview and dialogue register — the camera is as close as a respectful conversation, and the subject occupies the frame's center of gravity without filling it. The close-up (CU) frames from the base of the chin to above the eyebrows, removing the social context and making expression the subject. This is the shot that carries emotional weight in cinema: the single tear, the jaw that tightens, the small involuntary smile. At this scale, the eyes are the compositional axis and every micro-expression is legible. The big close-up or tight close-up fills the frame with the face from chin to forehead, reducing the background to texture and making the face itself a landscape. At this scale, pores are visible, light behaves differently on the micro-geometry of skin, and the subject's relationship to the camera becomes intimate to the point of pressure. The extreme close-up (ECU) isolates a single element — the eye, the mouth, a fingerprint, a reflection in a lens — and makes the scale reversal complete. The ECU tells the viewer: this specific part of this specific thing, right now, is the entire world. The macro close-up moves beyond human subjects into the world of objects and surfaces: the pore of a fabric, the individual crystal in a salt grain, the surface tension of a liquid before it breaks. At macro scale, the camera reveals a world that exists at a scale the eye cannot normally perceive, and the strangeness of the ordinary at that scale is the subject. Lens and depth of field are the two technical choices that determine whether a close-up works. At close-up to ECU distances, depth of field collapses dramatically — an f/1.4 aperture at a face-filling close-up distance produces a focus plane measured in millimeters, which means that sharp focus on the eyes produces soft focus on the ears in the same frame. This selective focus is not a limitation — it is the compositional tool. At the ECU of a face, the eyes should be sharp and the nose tip should fall to soft focus; that hierarchy tells the viewer exactly where to look and confirms that this is a deliberate close-up rather than an awkward crop of a wider shot. At macro distances, a small aperture (f/11 or higher) is often needed just to get a single plane of a small object in focus — but even then, the subject's near and far edges blur to near-abstraction. Naming the focus plane explicitly in the prompt — "sharp focus on the iris, the nose and ear falling to soft bokeh" — gives Seedance the compositional hierarchy to execute rather than leaving focus distribution to default. The lighting grammar of close-up video differs from every other scale because the subjects are small enough that the light source's direction relative to the surface determines the entire topography. At MCU distance, standard three-point lighting works normally. At CU and ECU distance, a single off-axis key light creates shadow structures across the face that reveal the micro-geometry of the skin: the hollow under the cheekbone, the slight asymmetry of the orbital ridge, the way light catches the upper lip differently from the lower. Naming the key light direction and its softness at close-up distance gives the model the tools to produce a face as a topographical record rather than a lit surface. For product and material close-ups, the light direction determines whether the surface reads as texture or as flat color: a raking light at 20 degrees to a rough surface grazes across every imperfection and makes the texture three-dimensional; a front fill at 0 degrees fills all the shadows and makes the same surface read as flat. The difference is a camera-to-light-angle specification, and making that specification explicit is what separates product close-up video that makes the material irresistible from video that merely shows it. Motion at close-up scale operates differently from motion at wide scale because even small camera movements produce large compositional shifts. A 2cm rack focus across a face at ECU distance completely changes the compositional axis. A 1mm dolly at macro distance changes the entire depth structure of the frame. This means that close-up motion has to be named at a finer resolution than wide-shot motion: not "a slow push-in" but "a 3cm push-in over 4 seconds, maintaining sharp focus on the left eye as the right eye moves slightly past the critical focus plane." The motion that works at close-up scale is the motion of discovery: a slow rack of focus revealing successive layers of a subject, a micro-pan that finds the specific texture detail at the edge of frame and centers it, a pull-back that starts inside an unidentifiable texture and widens until context reveals what it was. These are not just camera moves — they are the structural arc of what the viewer is shown: ignorance of context → recognition → understanding. Across all five scales and all subject types, close-up video has one governing principle: the frame has to earn its proximity. A close-up that is merely a cropped wide shot earns nothing. A close-up that reveals something the wider view could not — the tension in a jaw that the dialogue does not express, the surface texture of a material that explains its cost, the specific light reflection in an eye at the moment of a decision — that close-up carries meaning that no other framing could have produced. Every prompt in this gallery is built on that principle: the subject, the scale, the focus plane, and what the close-up is specifically revealing. Copy a prompt, name what your close-up is for, and keep the focus hierarchy and light direction intact.

A fast-paced cinematic sequence in a glowing volcanic terrain. A warrior protagonist @image1 stands high above a volcanic ridge before dropping from a visible height into the battlefield below. The protagonist extends one arm, summoning a returning glowing hammer from a distant point. The hammer travels visibly through the air in a fast glowing arc, wrapped in blue electricity, before snapping firmly into the protagonist's hand. The protagonist channels lightning, moving swiftly and hurling the hammer to push back the figures. The camera follows the protagonist's motion continuously in a fluid handheld style, maintaining clear spatial continuity with controlled whip-pans and no abrupt resets. Treat the entire sequence as one continuous evolving camera language with uninterrupted spatial logic. Cinematic motion blur, no music. Shot 1 (0.0–2.0s) — Fast tilt-down: the protagonist drops from a high rocky ledge, falling through the air before landing heavily on volcanic rock; a strong kinetic shockwave pushes ash and debris outward. Shot 2 (2.0–4.0s) — Controlled whip-pan continuation: the protagonist extends one arm; from far distance, the glowing hammer streaks toward the protagonist in a fast clearly visible arc, blue electricity trailing behind, before locking precisely into the protagonist's grip. Shot 3 (4.0–6.5s) — Continuous tracking: the protagonist moves forward aggressively, weaving through towering figures; the protagonist throws the hammer with force, the hammer visibly traveling outward through the battlefield, striking enemies, ricocheting, then flying back cleanly into the protagonist's hand. Shot 4 (6.5–8.5s) — Lateral motion continuation: the protagonist accelerates and leaps into the air, body fully extended, lightning wrapping around the protagonist mid-air as the protagonist prepares a downward strike. Shot 5 (8.5–10.0s) — Mid-air descent to impact: the protagonist descends rapidly from the jump and drives the glowing hammer downward into the volcanic ground with full force; the moment of impact creates a concentrated energy burst. Shot 6 (10.0–12.0s) — Extreme wide continuation: the impact expands into a massive radial wave of blue electrical energy, visibly spreading across the ground and lifting all surrounding enemies violently into the air. Shot 7 (12.0–15.0s) — Aftermath close-up: the energy wave dissipates and debris slowly falls. The camera gradually settles from the wide destruction into a stable close-up of @image1. The protagonist stands firmly, breathing controlled, faint blue electricity fading away. The protagonist slightly tilts their head, looking forward with a calm but intimidating expression. The camera holds steady on the protagonist's face. Clear visible lip sync as the protagonist delivers the line on-camera: "Who's next?"

Seedance 2.0 AI video prompt: 3D animated film style, ultra high quality, cinematic lighting, global illuminat

3D animated film style, ultra high quality, cinematic lighting, global illumination, soft shadows, depth of field, ultra detailed fur, cute characters, smooth animation, natural lighting, handheld camera feel, found-footage comedy style, realistic camera movement, playful atmosphere Scene: A group of fluffy forest rabbits stand in a bright forest clearing. The rabbits look directly into the viewer as if they are recording themselves. The camera is never visible at any time. The video feels like discovered footage recorded by the rabbits themselves. Characters: 4–5 cute fluffy forest rabbits, different sizes, expressive faces, soft fur, playful personalities Action Timeline Scene 1 Rabbits appear close to frame, looking directly at the viewer. Bunny 1 (curious): "Is this thing recording?!" Scene 2 Another rabbit gently pushes forward. Bunny 2 (excited): "Move! I'm the main character!" Scene 3 Another rabbit leans in. Bunny 3 (very excited): "Hello internet!!!" Scene 4 Another rabbit tries to squeeze into frame. Bunny 4: "Wait… I want to be famous too!" Scene 5 Rabbits gently push each other, trying to move to the front. They all look directly at the viewer. Cute, playful chaos. Bunny 2 (laughing): "Hey! Give me space!" Bunny 3: "No, me first!" All rabbits softly giggle and continue gently pushing. Scene 6 (Ending) One calm rabbit steps slightly forward. Bunny 5 (calm, smart bunny): "No… they'll probably Follow to Oogie' on X." All rabbits suddenly pause. They slowly turn and look directly at the viewer together. Short silence. Then all rabbits smile at the same time. Camera: POV camera, direct-to-camera talking, handheld feel, gentle natural movement, close-ups, cute framing, camera never visible, no camera falling, stable handheld Audio: Cute bunny voices, soft wind, forest ambience, light giggles, gentle movement sounds Mood: Cute, funny, wholesome, viral-style social media content Ultra detailed, cinematic lighting, 4K, smooth animation, soft fur, expressive animation, high quality rendering

Seedance 2.0 AI video prompt: 【Style】Viral CEO Drama, Portrait Mode, High-Saturation Filter, Extreme Close-up

【Style】Viral CEO Drama, Portrait Mode, High-Saturation Filter, Extreme Close-up of Facial Expressions, Intense Emotions. 【Duration】15 seconds 【Characters】Humiliated Groom (wearing cheap suit, suppressing emotions) VS Harsh Mother-in-Law (covered in jewelry, looking disgusted). [00:00-00:05] Shot 1: Extreme Humiliation. Luxurious wedding venue. Mother-in-law throws a "divorce certificate" hard onto the groom's chest in front of everyone, with guests bursting into laughter. 【Action】Mother-in-law points her finger at the groom's forehead. 【Dialogue Lip-Sync Guide】"No car, no house, and you want to marry my daughter? Take these hundred bucks and get out!" [00:05-00:10] Shot 2: Sudden Turn. Groom suddenly lets out a cold laugh, tearing up the divorce certificate. At this moment, a massive propeller sound (sound effect) covers the entire scene, with wind messing up the mother-in-law's hair. 【Action】Groom adjusts his collar, instantly exuding an domineering aura. 【Dialogue Lip-Sync Guide】"This wedding, it's you who wants to call off." [00:10-00:15] Shot 3: Tycoon Arrives. Doors burst open, two rows of black-suited bodyguards rush in, kneeling and laying out a red carpet. An old butler trembles, holding a yellow robe (or supreme black card), running to the groom and bowing deeply. Mother-in-law sits paralyzed on the ground, pupils dilating in shock. 【Dialogue Lip-Sync Guide】Old butler shouts: "Welcome Dragon King (Young Master) home! Family assets have been unfrozen!"

Seedance 2.0 AI video prompt: A hyper-realistic sequence showing a photorealistic Formula 1 car emerging from

A hyper-realistic sequence showing a photorealistic Formula 1 car emerging from a detailed pencil sketch on a cluttered architect's desk.", "camera": { "type": "Slow Arc Shot", "lens": "100mm Macro Prime", "aperture": "f/2.8", "position": "Starts as an extreme close-up on the pencil drawing, then slowly pulls back and arcs around the car as it transitions to a 3D object.", "environment": { "location": "A designer's or engineer's drafting table.", "details": "The surface is a sheet of high-quality, slightly textured white paper covered in technical blueprints and schematics of the car. Several graphite and colored pencils, an eraser, and a compass are scattered around the main drawing. The background is a dark, out-of-focus workshop." }, "lighting": { "primary_source": { "type": "Architect's Desk Lamp", "position": "Just out of frame, to the top left.", "fill_light": { "type": "Soft Ambient Light", "source": "From the out-of-focus workshop background.", "color": "Cool, bluish tint.", "intensity": "Low, to gently lift the darkest shadows and add depth to the scene." } }, "main_subject": { "name": "The Formula 1 Car", "initial_state": "A masterful, hyper-realistic pencil drawing. The lines are precise, the shading is smooth, and there's a sense of depth even in 2D.", "final_state": "A fully realized, photorealistic 3D model of the Red Bull F1 car. The materials are perfect: glossy carbon fiber, metallic paint with livery, and soft-sheen rubber tires.", "animation": { "0.0s - 2.0s": "The camera is focused on the drawing. A photorealistic hand enters the frame with an eraser and gently removes a few faint construction lines from the sketch.", "2.0s - 7.0s": "A magical 'wave' of transformation begins at the front wing of the car and sweeps backward. As it passes, the 2D pencil lines and shading seamlessly transform into 3D, textured materials. The drawn debris on the track lifts up and becomes real, floating for a moment before settling.", "7.0s - 8.0-10s": "The transformation is complete. The car is now fully 3D, sitting on the paper as if it's a real, miniature vehicle. The engine subtly whirs to life, and the exhaust vents emit a tiny, realistic heat haze." } }, "audio_design": { "style": "Transformative, from quiet and organic to powerful and cinematic.", "timeline": [ { "time": "0.0s - 2.0s", "sound": "The soft, realistic sound of a pencil's graphite scratching on paper, and the gentle 'shhh' of an eraser." }, { "time": "2.0s - 7.0s", "sound": "A low, magical humming and shimmering sound that grows in intensity and pitch as the transformation wave moves across the car. This is layered with an epic, swelling orchestral score." }, { "time": "7.0s - 10s", "sound": "

Seedance 2.0 AI video prompt: 0–3s (VIRAL HOOK):
Extreme macro close-up of a gourmet cheeseburger being lifted

0–3s (VIRAL HOOK): Extreme macro close-up of a gourmet cheeseburger being lifted slowly. Melted cheese stretches dramatically between bun and patty—thick, glossy, elastic strands. Juices glisten on the patty, steam rises naturally. Slow-motion effect for maximum satisfaction. First frame is slightly grainy/low-quality, then subtly sharpens (to support your before/after idea). 3–6s: Cut to the influencer holding the burger, shot in natural handheld UGC style (phone camera feel). She reacts with excitement: slight smile, raised eyebrows. Soft dialogue or lip-sync: “Okay… this looks insane.” 6–10s: Handheld vlog-style shot. She takes a big bite—cheese stretches again, sauce slightly drips. Real, unfiltered reaction: eyes widen, she nods, subtle laugh. Natural motion shake for authenticity. 10–13s: Extreme close-up ASMR shots: Crispy toasted bun texture Juicy patty fibers Melted cheese pull + sauce drip Background fully blurred, premium food focus. 13–15s (VIRAL END FRAME): She looks into the camera, smiles confidently, gives a subtle thumbs-up. Freeze frame on the burger with a glowing highlight + slight zoom-in punch. Final frame is ultra-sharp 4K HDR (clear “after” quality moment). 🎥 Visual Style (Enhanced) Hyper-realistic burger textures (juicy patty, molten cheese, glossy bun) UGC handheld authenticity + cinematic polish First 5 sec slightly soft/low quality → transitions into crisp 4K clarity Warm cozy lighting + neon reflections Shallow depth of field, subject isolation Natural motion blur + micro camera shake 🔊 Audio Style Trending TikTok food vlog sound / chill lo-fi beat Strong ASMR layer: bite crunch, sauce drip, cheese stretch Subtle bass hit exactly at first cheese pull (hook moment) Audio clarity improves after 5 seconds (matches video quality jump)

FORMAT: 15s / single continuous impossible camera move / no dialogue STYLE: Dense Southeast Asian night market, wet stone, steam and fire, orange lantern light, photorealistic ground-to-aerial cinematic 8K Shot 01 (0:00–2:00): Camera starts at ankle level. Forest of feet — sandals, bare feet, flip flops on glistening wet stone. Market sounds overwhelming. Camera weaves between legs like water. Audio: Wet footsteps, distant vendor calls, sizzling. Shot 02 (2:00–3:30): Camera rises slowly past steaming woks. A gas flame bursts at exact eye level — camera briefly engulfed in orange fire then emerges through it, uncut. Audio: Gas flame WHOMP. Wok sizzle. Shot 03 (3:30–5:00): Camera weaves through hanging lanterns at mid-height, skimming past them like a moth navigating. Red and orange light strobing across the lens. Audio: Lantern chains clinking. Crowd murmur. Shot 04 (5:00–6:30): Camera dips suddenly under a low table. A child has fallen asleep on a bag under here. Quiet pocket of stillness inside the chaos. Camera lingers one beat. Audio: Noise muffled. Child's quiet breathing. Shot 05 (6:30–8:00): Camera rises back up through the smoke of a charcoal grill — lens briefly obscured by smoke, then emerges above the stall canopy level. Audio: Charcoal crackle. Smoke hiss. Shot 06 (8:00–10:00): Camera continues rising — now above rooftop level. The market reveals itself as an endless orange lantern sea stretching to the horizon. Camera tilts slowly, taking in the full scale. Audio: Market sounds fading to a low ambient hum. Shot 07 (10:00–12:00): Camera begins descending back down — targeting a single stall at the market edge. A lone vendor counting coins. Everything closing around them. Audio: Distant vendor calls dying out one by one. Shot 08 (12:00–13:30): Camera settles at the vendor's hands. Close on coins being stacked methodically. One lantern swaying above them. Audio: Coin clinks. Wind in the lantern. Shot 09 (13:30–15:00): Camera tilts up slowly to the vendor's face. They look up — directly into the camera. Hold. Fade to black. Audio: Last coin placed. Silence. STYLE NOTES: Ground level feels claustrophobic and overwhelming. The aerial shot is the emotional exhale. Warm orange and red throughout — deepening to amber at the end. Wet stone reflections throughout. Real fire and real smoke, no CG substitutes. 8K.

Seedance 2.0 AI video prompt: A young woman matching the exact facial features, hairstyle, and identity of the

A young woman matching the exact facial features, hairstyle, and identity of the reference image (consistent character throughout all shots) is filming a “Get Ready With Me” style video in a softly lit, modern bedroom with a vanity mirror and warm ambient lighting. Opening scene (casual look): She is wearing comfortable knee-length fitted shorts (extending just over the knees) and a simple sleeveless crop top. Natural look, no makeup. She smiles at the camera and casually greets, creating a relaxed, vlog-style tone. Sequence of shots (fast-paced, smooth cuts, ~10–15 shots total): Close-up of her tying her hair into a loose bun Applying face wash at the sink, soft water splashes, natural lighting Gently patting her face dry with a towel Skincare routine (serum, moisturizer) in front of mirror Sitting at vanity applying makeup step-by-step (foundation, eyeliner, lipstick) She occasionally looks into the camera and subtly explains each step (natural lip movement, expressive gestures) Insert aesthetic close-ups: makeup brushes, mirror reflections, soft bokeh lighting Tone & style: Cinematic but vlog-inspired, smooth camera motion, shallow depth of field, soft highlights, natural skin texture, realistic lighting. Maintain facial consistency across all shots. Transition: Quick montage with rhythmic cuts as she completes her look. Final reveal scene: She steps back into frame fully dressed in an attractive yet modest red outfit (elegant, tasteful, non-revealing, flattering silhouette). Hair styled neatly, confident posture. She does a subtle twirl or pose, smiles warmly at the camera, and gives a final confident look. Ending shot: Soft close-up with warm lighting, slight camera push-in, she looks directly into the lens with a satisfied expression. Technical tags: 1080p, cinematic lighting, consistent character identity, smooth transitions, natural motion, realistic skin tones, high detail, depth of field, vlog + cinematic hybrid style

Seedance 2.0 AI video prompt: 15-second cinematic romance, slow-burn emotional tone, one man and one woman onl

15-second cinematic romance, slow-burn emotional tone, one man and one woman only, both adults in their mid-20s, western-style leads, casual luxury wardrobe, dark quiet apartment living room at night, refined romantic tension, natural lip sync, no subtitles, no text on screen. Character continuity: Female lead: adult western woman, mid-20s, elegant natural beauty, long brunette hair with soft loose waves, minimal makeup, emotionally guarded but faintly amused, seated on the sofa. Outfit: soft ivory off-shoulder knit sweater, dark straight-leg jeans, barefoot, understated jewelry. Male lead: adult western man, mid-20s, handsome refined features, slightly messy dark hair, thin metal-frame glasses, calm warm expression. Outfit: charcoal knit sweater over a white T-shirt, dark trousers, sleeves pushed once, relaxed but polished. Environment: Upscale apartment living room, soft sofa, low coffee table, one warm lamp, deep evening shadows, muted neutral palette, intimate silence, shallow depth of field, premium film texture, modern romantic realism. 0-3s: Wide-to-medium slow push-in. She sits in one corner of the sofa with arms folded, looking away. He crosses the room and sits on the edge of the coffee table facing her, leaving a small respectful distance. Hold the silence and tension. 3-6s: Medium close-up on the man. He studies her face, voice low, calm, almost smiling: “I tried very hard to have an ordinary evening.” 6-9s: Close-up on the woman. She turns her eyes to him at last, cool but intrigued, with the faintest teasing edge: “And how did that go?” 9-12s: Close-up on the man. He lets out a quiet breath, gaze steady. He reaches toward a loose strand near her cheek, stopping just before touching: “Poorly. You were in all of it.” 12-15s: Side two-shot. She lightly catches his wrist before he pulls away, not rejecting him, only holding him there. A small unwilling smile appears: “That is not helping me stay angry.” Hold on the shared gaze, the restrained smile, and the unresolved tenderness. Motion and style rules: Slow elegant camera movement, meaningful pauses, micro-expressions, lingering eye contact, almost-touch tension, realistic hand motion, restrained acting, no kneeling, no raised voices, no crying, no extra characters, no exaggerated gestures, no waxy skin, no stiff posing, premium romantic realism, emotionally charged final frame.

FORMAT: 15s / slow cinematic reveal / one continuous emotional escalation / no dialogue STYLE: gothic dark romance, photorealistic cinematic lighting, deep red velvet curtains, black satin fabric, premium editorial horror aesthetic, high detail, soft film grain, shallow depth of field SUBJECTS: A striking dark-haired woman in an elegant black outfit, poised, predatory, and calm. A well-dressed man lies back on a black satin-covered platform beneath her. Her posture is intimate but controlling, one hand near his throat, her face close to his neck. She is not frantic or monstrous — she is composed, sensual, and subtly inhuman. ENVIRONMENT: Minimal theatrical stage framed by rich red velvet curtains. Black satin draped beneath the subjects with glossy folds catching the light. Background kept simple and dark so the figures dominate the frame. MOOD: Seductive, ominous, luxurious, vampiric, emotionally tense. COLOR LOGIC: Deep crimson, black, pale skin tones, soft specular highlights, shadows swallowing the edges of the frame. TIMELINE: 0:00–0:03 Medium-wide shot. A man lies on black satin before deep red curtains. A dark-haired woman in black leans slowly over him. The composition feels elegant and staged, almost like a theater tableau. Camera begins a very slow push-in. Audio: soft fabric movement, distant room tone, faint breath. 0:03–0:06 Closer angle. Her hand settles lightly at his throat and collarbone. He stays still, half hypnotized, half uncertain. She lowers her face near his neck with total control. Hair falls slightly forward. Audio: satin whisper, slow inhale, subtle heartbeat-like bass pulse. 0:06–0:09 Tighter close-up. Her expression remains calm and unreadable. The man’s breathing changes. The camera drifts slightly around them, revealing the shine of the satin and the depth of the red curtain folds. The moment feels intimate but wrong. Audio: breath, fabric creak, low ambient hum. 0:09–0:12 Extreme close framing. She pauses at his neck, then lifts her face just enough for the audience to sense something unnatural — a faint glimpse of sharpened teeth, a slight smear of crimson at the mouth, or an almost imperceptible inhuman stillness. The man’s hand tenses weakly against the satin. Audio: heartbeat rising, near silence. 0:12–0:15 Final hold. She turns her gaze toward the camera while remaining over him, one hand still at his throat. The man lies motionless beneath her. The image locks into a dark romantic horror tableau. End on stillness. Audio: heartbeat stops, silence, faint curtain rustle. STYLE NOTES: Keep the performance controlled and elegant, never exaggerated. Focus on dominance, intimacy, and theatrical horror rather than gore. The scene should feel like luxury gothic cinema, not camp. Prioritize red velvet texture, black satin highlights, slow camera drift, and a final chilling reveal.

Seedance 2.0 AI video prompt: Scene 1 prompt: 
Use the attached storyboard sheet as the primary source of trut

Scene 1 prompt: Use the attached storyboard sheet as the primary source of truth. @ Image1 Create a 15-second cinematic scene exactly following the timing, shots, and dialogue from the sheet. Characters: Indian man and Indian woman Location: modern apartment at night (living room + kitchen continuity) Style: cinematic realism, natural acting, subtle emotions Lighting: warm practical lighting with city lights outside Rules: Follow the exact shot timing and dialogue cadence from the sheet When a character speaks, keep them isolated in frame (close-up) Maintain realistic pacing, pauses, and micro-expressions Do not exaggerate acting or add extra dialogue Audio: soft ambient room tone + subtle background music, natural dialogue delivery. Scene 2 prompt: Use @ video1 as the base continuity reference (same characters, positions, lighting, camera style, and emotional tone). Use @ image1 as the storyboard guide for the next 15 seconds (follow its timing, shot sequence, and dialogue exactly). Extend the scene naturally from where @ video1 ends. Rules: Maintain perfect visual continuity (same apartment layout, wardrobe, lighting, framing) Match character appearance and expressions exactly from @ video1 Follow @ image1 strictly for shot timing and dialogue cadence When a character speaks, keep them isolated in frame (close-up) Keep movements subtle, realistic, and emotionally grounded Preserve pauses and natural pacing Style: cinematic realism, warm indoor lighting, soft shadows, shallow depth of field Audio: natural dialogue delivery, soft ambient room tone, very subtle background score Do not add extra dialogue, actions, or cuts beyond @ image1. Scene 3 prompt: Use @ video1 as the base continuity reference (same characters, positions, lighting, camera style, and emotional tone). Use @ image1 as the storyboard guide for the next 15 seconds (follow its timing, shot sequence, and dialogue exactly). Extend the scene naturally from where @ video1 ends. Rules: Maintain perfect visual continuity (same apartment layout, kitchen + living room positioning, wardrobe, lighting) Match facial features, expressions, and camera framing exactly from @ video1 Follow @ image1 strictly for shot timing and dialogue cadence When a character speaks, isolate them in frame (close-up) Keep movements minimal, realistic, and emotionally grounded Preserve pauses, eye contact beats, and subtle performance shifts Style: cinematic realism, warm indoor lighting, soft shadows, shallow depth of field Audio: natural dialogue delivery, soft ambient room tone, very subtle emotional background score Do not add extra dialogue, actions, or cuts beyond @ image1. Ensure smooth continuation with no visible jump cut—this should feel like a single continuous scene.

Seedance 2.0 AI video prompt: style:
  genre: "premium Korean romance melodrama with K-pop visual polish"
  re

style: genre: "premium Korean romance melodrama with K-pop visual polish" realism: "photorealistic live action" cinematography: "shallow depth of field, elegant close-ups, subtle handheld tension, glossy emotional realism" lighting: "early night kitchen, warm tungsten practical light, faint cool blue city spill from the window, soft reflections on dark stone countertops" scene_anchor: location: "modern apartment kitchen at early night" fixed_details: - "white cabinets" - "dark stone counter" - "sink under the window" - "two ceramic mugs on the island" - "soft refrigerator glow in the background" characters: male_lead: name: "Joon-seo" age: "adult, late 20s" appearance: "tall, black dress shirt, sleeves rolled, loosened tie, tired eyes, restrained posture" female_lead: name: "Ha-yoon" age: "adult, late 20s" appearance: "long dark hair, cream blouse, wounded pride, bright eyes holding back tears" audio: dialogue_language: "English" sound_design: "natural room tone, faint refrigerator hum, distant city traffic, breath and fabric movement, restrained dramatic underscore" continuity_rules: - "Only two adult characters in frame." - "Keep wardrobe, hairstyles, kitchen layout, and prop positions consistent across all clips." - "Maintain intimate actor spacing and precise eye-line matching." prompt: | Premium Korean romance melodrama. Early night in the same modern apartment kitchen. Keep the acting intimate and volatile, with micro-expressions, trembling breath, and emotionally precise lip sync. The emotional tone is hurt, accusation, and unresolved longing. [00:00-00:04] Tight two-shot across the kitchen island, slight handheld sway. Ha-yoon steps into Joon-seo's space and forces eye contact. HA-YOON: "You don't ignore my words, Joon-seo. You ignore my feelings." [00:04-00:08] Reverse close-up on Joon-seo. He swallows hard, jaw tight, guilt flickering behind his eyes. JOON-SEO: "I've been trying to keep everything from falling apart." [00:08-00:15] Slow push-in on Ha-yoon, then settle into a tense two-shot with both faces sharp and the background soft. HA-YOON: "Then why was I always the first thing you let go when you got busy?" He cannot answer. Let the silence hit hard. Hold on the pain in both faces. end_frame_anchor: | Both stand less than a step apart, eyes locked. Ha-yoon's chin is lifted, tears contained but visible. Joon-seo is speechless, breathing shallowly, shoulders tense, unable to look away. style: genre: "premium Korean romance melodrama with K-pop visual polish" realism: "photorealistic live action" cinematography: "close emotional coverage, slow push-in, minimal cutting, performance-first framing" lighting: "exact same early night kitchen lighting as previous clip, warm tungsten practicals with cool window spill" scene_anchor: location: "same modern apartment kitchen, exact same geography and prop placement as clip 1" characters: male_lead: name: "Joon-seo" age: "adult, late 20s" appearance: "same black dress shirt, rolled sleeves, loosened tie, exhausted eyes now wet with regret" female_lead: name: "Ha-yoon" age: "adult, late 20s" appearance: "same cream blouse, long dark hair, anger beginning to crack under heartbreak" audio: dialogue_language: "English" sound_design: "same room tone, breath-forward mix, very light dramatic underscore, clear natural dialogue" continuity_from_previous_clip: | Exact continuation from the final frame of clip 1. No scene reset. No position jump. Same camera height, same kitchen geography, same wardrobe, same eye-lines, same emotional charge. Start with a held half-second of silence before he speaks. continuity_rules: - "Preserve the exact distance between them for the first second." - "Keep the first beat visually stable so the extension feels seamless." - "Performance must feel like a confession breaking through after a long silence." prompt: | Continue from the exact final frame of the previous clip. The emotional tone shifts from confrontation to raw confession. Keep the acting restrained but devastating, like someone finally saying the truth too late. [00:00-00:03] Hold the tension from the last frame. Slight slow push-in. Joon-seo finally speaks, voice low and wrecked. JOON-SEO: "Because I was ashamed." [00:03-00:09] Cut to a close-up that feels intimate and unforgiving. His eyes glisten; he looks like he has not slept. JOON-SEO: "For six months I hid behind work, behind excuses, behind every lie that sounded responsible." [00:09-00:15] Return to a close two-shot. He takes one small step closer, careful, almost afraid of her. JOON-SEO: "I made mistake after mistake, and I kept hurting you because I was too afraid to face what I'd become." Ha-yoon says nothing, but her anger softens just enough to show that she is listening. end_frame_anchor: | Joon-seo stands very close now. His hand rises toward Ha-yoon's cheek but stops a few inches away, trembling. Ha-yoon does not pull back. Both are breathing unevenly. The space between his hand and her face is charged and unresolved.

Seedance 2.0 AI video prompt: SUBJECTS:
The knight continuously holds the sword pointed at the princess’s hear

SUBJECTS: The knight continuously holds the sword pointed at the princess’s heart, arm steady but constantly trembling, forcibly suppressing emotions without crying in the early phase, then fully breaking down later; facial performance progresses through moist eyes, tightened lower eyelids, and increasingly unstable, fragmented breathing (knight appearance @[image1]) The princess remains aligned directly with the sword’s path, completing her forward movement in one continuous motion without pause; emotional progression is “reluctance → hesitation → forced restraint → resolve,” and after being wounded, she enters a gradual blood loss and weakening process (princess appearance @[image2]) ENVIRONMENT: Stone castle courtyard interior, open space, rough ground surface, high window light combined with side lighting, cool gray low-saturation natural light, character highlights with gradually darkening background STYLE: Ultra photorealistic cinematic quality, 85mm, shallow depth of field, slight handheld 0:00-0:02: Medium close-up push-in, the knight holds the sword directly aimed at the princess’s heart (maintaining distance), arm trembling, breathing suppressed, eyes slightly moist but forcibly holding back tears, lower eyelids tightened, lips pressed; the princess’s eyes are reddened with tears welling, breathing becomes shallow, expression shows reluctance and pain but she does not step back SFX: suppressed breathing 0:02-0:05: Medium shot lateral move, the knight’s trembling intensifies, Adam’s apple moves, he whispers brokenly “I can’t…”, the sword remains aimed without lowering; the princess looks at him with tears, breathing quickens, lips tremble as if to speak but she restrains it, expression briefly wavers before tightening into resolve, she inhales, lifts her chest to align with the sword tip and leans forward SFX: trembling voice 0:05-0:08: Medium close-up follow, the princess moves forward in one continuous motion with tears, her chest directly meets the sword tip completing contact and entering the penetration result, instant pain and emotional release appear, breathing is cut off, her body pauses then loses support, the sword hilt presses tightly against the heart position, dark red blood appears at the contact point and rapidly seeps into the clothing spreading outward, accompanied by a low, heavy penetration sound and fabric tearing sound to reinforce the moment SFX: penetration sound + tearing sound 0:08-0:10: Low-angle follow, the knight freezes for a split second with pupils dilated, then rushes forward to catch the princess and drops to his knees, control collapses, tears burst out, he says brokenly “No…”, breathing becomes chaotic, hands stained with blood and remain so SFX: broken breathing 0:10-0:13: Close-up lock, the princess’s breathing gradually weakens, chest movement decreases, her gaze loses focus but remains on the knight’s face, tears slide from the corners of her eyes, she speaks in an extremely faint, fragmented breath “Li…ve… for… me…”, after speaking her breathing pauses, then her fingers slowly fall, only after her gaze fully loses focus do her eyes close, her head naturally lowers SFX: faint breath 0:13-0:15: Medium shot pull back, after a brief pause the knight suddenly lifts his head and screams uncontrollably toward the sky, voice cracking and tearing, face covered in tears, body shaking violently while tightly holding her, the camera pulls back to emphasize isolation and collapse SFX: scream + breakdown sobbing

[CINEMATIC SETUP] Genre & Mood: Gritty Post-Apocalyptic Survival. Tense, visceral, and hyper-realistic. Film Stock & Lens: Shot on 35mm anamorphic lens, f/2.8 for shallow depth of field. Teal-orange desaturated color grade with earthy, dusty undertones. Lighting & Atmosphere: Dramatic volumetric Golden Hour light with heavy dust motes and heat haze. Character Description: An athletic woman in her late 20s, wearing weathered tactical leather armor and dirt-smudged skin. Her hair is wind-blown and messy; her expression is one of intense, lethal focus. Audio Style: Immersive spatial sound design. Detailed SFX of bowstring tension, rhythmic heavy breathing, wind howling through the canyon, and a high-velocity "thwack" on impact. [TIMELINE SECOND BY SECOND] 0-3s: [Extreme Close-up (ECU)] High-angle shot of the woman's face as she aims a mechanical compound bow. The bowstring is pulled taut against her cheek. Movie-level realistic facial features, no deformation, stable throughout. 3-4s: [Macro Cut] Extreme close-up of her iris. The pupil dilates sharply as she locks onto her target. Realistic light reflections in the eye. 4-8s: [Over-the-shoulder (OTS) Shot] The camera sits behind her shoulder on a jagged cliff edge. In the valley below, a herd of mutated, post-apocalyptic Cape Buffalo with thickened grey hide and jagged horns graze peacefully. Smooth camera push-in. 8-10s: [The Release & POV] She releases the arrow. Fast Tracking POV shot following the arrowhead at maximum velocity. Intense motion blur on the passing rocky environment as the arrow slices the air. 10-15s: [Impact & Wide Shot] The arrow strikes the lead beast in the flank with realistic physics. The animal collapses heavily into the dust. The rest of the herd panics and scatters in a chaotic wide shot. Sound fade to the howl of the wind. [STYLE & QUALITY BOOSTERS] Photorealistic 8K, ultra-detailed textures (skin pores, rusted metal, animal fur), cinematic lighting, perfect motion blur, high dynamic range, no artifacts, coherent multi-subject motion.

Seedance 2.0 AI video prompt: Cinematic-quality visuals, a spacious vintage grocery store (neon lights reflect

Cinematic-quality visuals, a spacious vintage grocery store (neon lights reflected on the glass display window, warm and cold lights intertwined). Subject: A beautiful waitress, refer to [Figure 1], very elegant and with a determined look. Action: Two armed robbers confront the waitress, one robber is nervously looking around, pointing a gun at the waitress's head. The camera captures her pretending to be scared while handing over money, then suddenly she flips over the cash register, throws the bills in one robber's face, smashes a bottle of beer at the other robber, and engages in intense close combat. Fighting effects: Every punch lands with impact, movements have force feedback, the waitress kicks one robber down with her foot, knocking over tables and chairs. She then turns around and throws the other robber out of the window, accompanied by flying glass shards. Lighting and shadows: Neon lights flicker, the characters' skin and sweat reflect light prominently, with strong contrast. Sound effects: Accompanied by heavy blows, glass shattering, breathing and gasping sounds, with a tense rhythm. Photography style: Handheld camera style, with rapid shaking and focus switching to capture instant impact; transitioning from tense static shots to chaotic close-up follow shots to showcase real dynamism and tension. Overall atmosphere: Cinematic-level dynamics and lighting, with powerful and dramatic moments frozen in time. Generate creatives using a realistic visual style, use a professional and authoritative digital human image, use a professional and authoritative voice tone, and generate creatives with a tense video mood

Seedance 2.0 AI video prompt: Cinematic lifestyle / entrepreneur routine scene, ultra-realistic, Hollywood blo

Cinematic lifestyle / entrepreneur routine scene, ultra-realistic, Hollywood blockbuster style, 15-second video composed of 30 dynamic fast-paced shots. SCENE OVERVIEW: A fast-paced cinematic montage showing a full productive day in the life of a digital entrepreneur, focusing purely on visual storytelling and routine, from waking up to sleeping. IMPORTANT – CHARACTER CONSISTENCY: Maintain exact facial features, hairstyle, skin tone, and black t-shirt from the reference image @image_1 at all times. Do not alter appearance or clothing. CHARACTERS: 1. Azevi @image_1: - Physical appearance: Young adult man, light skin tone, short dark slightly messy hair, clean-shaven, symmetrical face, expressive eyes. - Clothing: Plain black t-shirt (consistent in all scenes). - Emotional tone: Focused, calm, motivated. - Role in the scene: Digital entrepreneur living a productive daily routine. ENVIRONMENT: Modern apartment, clean minimalist bathroom, stylish kitchen, home office with professional setup, urban streets, luxury car interior, shopping mall, and bedroom at night. Lighting transitions naturally from morning to night. ACTION / SHOT-BY-SHOT SEQUENCE: 1. Close-up eyes opening 2. Turning off alarm 3. Sitting up in bed 4. Walking to bathroom 5. Brushing teeth in mirror 6. Rinsing mouth 7. Splashing water on face 8. Walking into kitchen 9. Preparing coffee 10. Close-up coffee steam 11. Drinking coffee 12. Sitting at desk 13. Turning on camera 14. Recording content 15. Typing on keyboard 16. Checking phone 17. Eating lunch quickly 18. Video call meeting 19. Focused reaction during meeting 20. Walking outside 21. Unlocking luxury car 22. Entering car 23. Driving through city 24. Arriving at mall 25. Walking with shopping bags 26. Returning home 27. Opening laptop dashboard 28. Seeing sales results 29. Eating snack 30. Lying in bed turning off light DIALOGUE: None CINEMATIC STYLE: Ultra-realistic, anamorphic lens, shallow depth of field, cinematic lighting, fast cuts, modern lifestyle aesthetic. CAMERA & TECHNICAL DETAILS: - Resolution: 4K UHD - Aspect Ratio: 16:9 - Frame Rate: 24 fps - Camera movement: handheld + smooth gimbal transitions - Lens: 35mm and 50mm mix AUDIO: Motivational cinematic background music only, no voices, no dialogue, subtle ambient sounds blended with music. MOOD & EMOTION: Productive, focused, inspiring, fast-paced modern routine with a clean and satisfying flow. NEGATIVE PROMPT: cartoon, anime, low resolution, blurry, distorted face, inconsistent face, different clothing, extra limbs, watermark

FORMAT: 15s / MULTI-CUT / 6 BEATS / HIGH-VIRAL COMEDIC PAYOFF SUBJECTS: A small round-faced figure with huge eyes, copper-red pigtails, a yellow polka-dot dress, and exaggerated cartoon proportions. A tall ice cream vendor with a curled mustache, crimson vest, tilted cap, and a long brass paddle carrying elastic white ice cream. Stylized 3D animation with rounded shapes and squash-and-stretch. ENVIRONMENT: A sunlit stone courtyard in an old hillside town with flower-draped archways, a mosaic fountain, ceramic bowls, and a brass ice cream cart with copper bells. Late afternoon light creates warm highlights on cobblestone. MOOD: Fast slapstick mischief with instant hooks, fake wins, and a crowd-pleasing payoff. COLOR LOGIC: Hyperreal Pop Look TIMELINE: 0:00-0:02: The Scroll Stop. Extreme close-up, 50mm. Huge eyes reflect a spinning white scoop, then pull fast to a wide shot, 35mm, revealing the figure frozen mid-skid as the vendor presents the brass paddle like a stage trick. SFX: sharp gasp, bell flutter, fountain splash. 0:02-0:04: Match cut into The First Miss. Close-up, 50mm. Hands clap shut on empty air as the cone snaps upward. The face stays frozen while the pupils tilt up. SFX: quick whoosh, soft clap, tiny squeak, crowd chuckle. 0:04-0:07: Cut on action into The Side Switch. Medium wide shot, 35mm. The vendor slides the paddle behind his back and pops the cone out on the other side. The figure lunges left, scrambles right, and pinwheels in place. A tea glass rattles on a nearby table. SFX: paddle swishes, shoe skids, glass clink, growing laughter. 0:07-0:09: Reaction cut into The Fake Victory. Medium close-up, 50mm. The cone lands in the waiting hand and the face bursts into victory, then the vendor peels the stretchy scoop away in one smooth move, leaving the cone bare for a beat. SFX: victory chime cut short, peel wobble, laughter pop, offended inhale. 0:09-0:11: Insert cut into The Public Humiliation. Insert shot of a ceramic cat staring from a shelf. Smash cut to a medium shot, 35mm, as the figure sags into noodle posture, then puffs both cheeks and folds both arms while onlookers bounce with silent laughter. SFX: tiny huff, crowd laughter swell, cart bell tinkle. 0:11-0:15: Whip pan transition into The Real Win. Medium close-up, 50mm. The vendor kneels and places the cone gently into the waiting hand with no trick this time. One still beat. The figure looks down, eyes sparkle, then the camera pulls back to a wide shot, 35mm, as the figure leans in for the first taste and the courtyard breaks into applause. SFX: soft handoff, held-breath pause, bright chime bloom, applause burst, warm music lift.

Seedance 2.0 AI video prompt: Please convert the reference rough pencil-storyboard into a high-quality, fully

Please convert the reference rough pencil-storyboard into a high-quality, fully animated 15-second Japanese 2D animation cooking video. The star of the video is a guilt-inducing teriyaki chicken donburi, topped with melted, stretchy cheese and a glossy, tempting egg yolk. Use a fast-paced edit with quick cuts. However, do not make the cooking actions feel rushed, and do not use fast-forward, timelapse, or chaotic motion. This is not high-speed cooking, speed-cooking, or timelapse cooking. Animate every action carefully and make it easy to follow. The only "fast" part should be the cuts between shots; the cooking actions themselves must remain clear and readable. Shot Flow: Begin with a close-up of the nearly finished donburi. Show glossy teriyaki chicken, rising steam, soft and stretchy melted cheese, a quivering golden egg yolk, and sauce glistening under warm kitchen lighting. Cut to a close-up of raw chicken thigh skin being scored with shallow cuts from a kitchen knife. Show the elasticity of the meat and the subtle sheen of its fat. Cut to the chicken being placed skin-side down into a hot frying pan. Convey a sharp, sizzling impact sound, tiny droplets of oil splattering, and the air warping from the heat. Cut to soy sauce, mirin, and sugar being poured into a small saucepan, swirling and blending together into a rich amber-colored sauce. Cut to the chicken skin slowly browning in the pan, a spatula pressing down gently, and oil bubbles forming and rising around it. Flip the chicken to reveal crisp, golden-brown skin and shimmering meat juices. Pour the rich teriyaki sauce into the frying pan. Show the sauce bubbling, boiling down, and coating the chicken in a lacquer-like, glossy shine. Cut to the cooked chicken being neatly sliced. Show the crispy skin, tender meat, and juicy cross-section. Arrange the sliced chicken over steaming white rice in a donburi bowl, and drizzle with glossy sauce, letting it soak into the rice. Use the residual heat to melt the cheese, place a bright egg yolk in the center, and have chopped nori and scallions gently fall over the top. Near the end, briefly show a Japanese 2D-anime-style character picking up the perfect bite with chopsticks—a mouthful that includes chicken, rice, yolk, cheese, and sauce. The character takes the bite. No dialogue—just show a warm, deeply satisfied expression. End on a super-close-up of the donburi as the yolk breaks and mingles with the glossy sauce, steam rises, and cheese stretches. Visual Style: High-quality Japanese 2D animation, hand-drawn feel, expressive food animation, warm lighting, crisp lines, rich and natural colors, cinematic macro close-ups, dynamic shot transitions, and strong texture rendering. The cooking is the main character. The human character appears only to reinforce the final moment of satisfaction. Emphasize ASMR-style visual storytelling that conveys sensation even without music. The sounds of knife cutting, oil frying, sauce bubbling, meat juices, crispy skin, sauce-pouring motion, steam, fluffy rice, melting cheese, the yolk breaking, and the chopsticks lifting a bite—all should be felt through the visuals alone. Make this video satisfying with no BGM, no narration, and no dialogue. Strict Prohibitions: No live-action. No photorealistic rendering. No 3D CGI. No game-style rendering. No real-camera-lens aesthetics. No text. No explanatory captions. No subtitles. No title cards. No logos. No watermarks. No signage. No legible text of any kind. No narration. No dialogue. No BGM. Do not let the character stand out too much. In every shot, keep the cooking process clear, appetizing, and easy to understand.

Seedance 2.0 AI video prompt: A young woman sleeps alone in a minimal bedroom.
Pre-dawn light — not quite dark

A young woman sleeps alone in a minimal bedroom. Pre-dawn light — not quite darkness, not quite morning. A single thin band of cold blue-silver light cuts across the bed from a gap in the curtains. Her face is serene, beautiful, completely still. The room holds its breath. SPEED RAMP STRUCTURE — CONSCIOUSNESS AS RHYTHM: 0–3s: [REAL WORLD — SLOW, TACTILE] Extreme close-up: her eyelashes against her cheek. Still. Barely breathing. Camera drifts in ultra-slow — a breath-pace dolly toward her face. The thin blue light shifts imperceptibly across her collarbone. Sound: near-silence. The faint hiss of pre-dawn air. A single eyelid trembles. 3–5s: [THRESHOLD — SPEED RAMP DOWN TO NEAR FREEZE] Her eyes begin to open — time slows to near-stop. Rack focus: eyelashes → iris catching first light. The iris fills the frame — inside it, something moves. A reflection that isn't the room. Sound drops to pure subsonic tone. The world between sleep and waking stretches open. 5–10s: [MEMORY FLOOD — MULTI-CUT ACCELERATION] Rapid fragmented cuts — each 0.3–0.5 seconds: — A hand reaching toward her through white fog. Whose hand. Unknown. — A corridor of stone arches, warm candlelight, someone walking ahead. Face never turns. — Her own hands — younger, smaller — pressed against cold glass. Outside: nothing. — A field of tall silver grass at dusk, wind moving through it like breath. — Two shadows on a sunlit wall. One disappears. — Her face reflected in still water — but the reflection blinks first. — A door. Slightly open. Light beyond. She reaches for it — Each cut slightly faster than the last. Motion blur bleeds between images. Colors shift: warm amber → cold silver → white out. Sound: layered whispers building — no words discernible, only tone and rhythm, doubling in density with each cut. 10–12s: [FLASH PEAK — FREEZE] Single frame: pure white. Then: her eyes — fully open, wide, present. Held for 0.5 seconds. Absolute stillness. The memories are gone. 12–15s: [RETURN — SLOW EXHALE / REAL WORLD] Pull back slowly. She lies in bed, eyes open, staring at the ceiling. The blue-silver dawn light now touches her face fully. She raises one hand slowly — looks at it — as if checking whether it belongs to her. She closes it into a loose fist. Lowers it. Camera cranes up slowly to overhead. She grows small in the frame. The room is ordinary. Whatever she almost remembered: gone. Lighting: pre-dawn cold blue-silver as key light, no warm fill — only the faint ambient glow of the sky beginning. Shadows deep and soft. Color palette: near-monochrome silver-charcoal base, memory cuts in desaturated warm amber, white flash at peak. Style: intimate cinematic, 35mm grain, shallow depth of field throughout, anamorphic horizontal lens flare on light band. Audio: breath-pace silence → subsonic tone → layered whisper swell → white noise peak → pre-dawn ambient return.

Seedance 2.0 AI video prompt: 日本の水彩画風フルカラーアニメ、0.5秒おきの高速なカット割り、作画枚数多め、24fps project: fetish_montage_v1
project:

日本の水彩画風フルカラーアニメ、0.5秒おきの高速なカット割り、作画枚数多め、24fps project: fetish_montage_v1 project: fetish_montage_v3_with_broll format: vertical_9x16 fps: 24 shot_duration: 0.5s total_shots: 28 total_duration: 14s ratio: "fetish 22 : broll 6 (約3.5:1)" broll_philosophy: role: "呼吸・象徴・感情の外部化" placement: "フェチが連続しすぎた直後、または感情の転換点" rule: "直接的にエロを示さず、心拍・温度・湿度を伝える" broll_categories: nature_micro: - "雨粒が窓を伝う、一筋" - "蝋燭の炎が揺れる、息で消えそうな瞬間" - "氷が割れる音と共にひびが走る" - "花弁が一枚、テーブルに落ちる" - "蜘蛛の巣に水滴、揺れる" - "煙草の灰が静かに落ちる" - "湯気が立ち上り消える" - "夜の街灯に虫が一匹" object_symbol: - "壁時計の秒針アップ、止まりそうに見える" - "コーヒーの黒い表面に天井が映る" - "床に脱ぎ捨てられた靴、片方だけ" - "ベッドの皺、誰もいない" - "電話が鳴っている、誰も出ない" - "灰皿の吸い殻が二本、口紅つき一本" - "ドアの隙間から漏れる光" - "鏡に映る空の椅子" texture_landscape: - "夜の濡れた路面、ヘッドライトが滲む" - "ネオンサインがフリッカー" - "シーシャの炭が赤く脈打つ" - "金属表面に映る歪んだ顔" - "革張りソファに沈む手の跡" - "湯船の水面が揺れる" body_abstract: # 体の一部だが象徴化されたもの - "心臓の鼓動で布団が微かに上下" - "影だけが壁を伝う" - "ガラス越しの輪郭、ピントずれ" - "水滴の中に顔が映る" --- sequence: - id: 01 type: fetish action: "髪を持ち上げてうなじを晒す" scale: macro - id: 02 type: fetish action: "下唇を噛んで離す" scale: extreme_macro - id: 03 type: broll category: object_symbol action: "壁時計の秒針、カチッと一秒進む" intent: "時間の伸縮を意識させる" - id: 04 type: fetish action: "袖口のボタンを外し、一回まくる" scale: macro - id: 05 type: fetish action: "鎖骨に影が落ちる、襟がずれる" scale: macro - id: 06 type: fetish action: "グラスの縁を指でなぞる、結露が滴る" scale: extreme_macro - id: 07 type: broll category: nature_micro action: "蝋燭の炎が一度大きく揺れる" intent: "呼吸の比喩、緊張のピーク" - id: 08 type: fetish action: "イヤリングを外す、髪が落ちる" scale: macro - id: 09 type: fetish action: "ヒールから足が抜ける" scale: macro - id: 10 type: fetish action: "喉が動く、嚥下" scale: extreme_macro - id: 11 type: broll category: texture_landscape action: "シーシャの炭が脈打つように赤く光る" intent: "心拍の外部化" - id: 12 type: fetish action: "口から煙をゆっくり吐く" scale: macro_side - id: 13 type: fetish action: "薄手の布越しに肩甲骨が動く" scale: macro_back - id: 14 type: fetish action: "ペンのキャップを歯で咥えて引く" scale: extreme_macro - id: 15 type: broll category: body_abstract action: "布団が呼吸で微かに上下" intent: "緊張の小休止、まだ続くという予告" - id: 16 type: fetish action: "脚を組み替える、ストッキングが擦れる" scale: low_side - id: 17 type: fetish action: "曇った窓に手のひらを押し当てる" scale: macro_through_glass - id: 18 type: fetish action: "髪を一気に結い上げる" scale: back_of_head - id: 19 type: broll category: object_symbol action: "灰皿に吸い殻二本、片方に口紅" intent: "誰かいた・いる気配の暗示" - id: 20 type: fetish action: "舌先が口角を湿らせる" scale: extreme_macro - id: 21 type: fetish action: "背中を反らせて伸びをする" scale: silhouette_side - id: 22 type: fetish action: "前髪の隙間から見上げる" scale: macro_eyes - id: 23 type: broll category: nature_micro action: "雨粒が窓を一筋伝う" intent: "感情の流出、抜きのカット" - id: 24 type: fetish action: "布をぎゅっと握る、関節が白くなる" scale: macro_hand - id: 25 type: fetish action: "自分の首筋に指を当てる、脈を測る" scale: macro_neck - id: 26 type: fetish action: "睫毛が触れ合うスローブリンク" scale: extreme_macro_eye - id: 27 type: broll category: object_symbol action: "床に片方だけ脱げた靴" intent: "去ったのか残ったのかわからない余韻" - id: 28 type: fetish action: "影の中へ歩み去る後ろ姿" scale: wide_silhouette

Seedance 2.0 AI video prompt: FORMAT: 15s, cinematic pacing, continuous camera movement with focus transitions

FORMAT: 15s, cinematic pacing, continuous camera movement with focus transitions, natural transition into inner world through eye reflection, overall smooth and cohesive flow CHARACTER: @[Image 1] FOOD: Salmon rose tower, Michelin-level plating. Thinly sliced salmon layered into a rose form, with a soft oily sheen on the surface. Color transitions from orange to pink, paired with minimalist garnish and refined sauce. SHOT 1 (0–2s): Macro close-up, shallow depth of field, focus on knife edge, slight lateral movement. The camera is close to the surface of the salmon rose tower. The blade slowly cuts into the fish. The layered structure slightly separates, with soft deformation at the edges. Surface oils create delicate reflections under warm lighting. The plate remains blurred, and light moves subtly across the surface. SHOT 2 (2–4s): Focus pull from food to side profile, slight push-in. Focus shifts from the salmon in the foreground to the man’s side profile. He brings a small piece of salmon into his mouth. The foreground gradually blurs. Warm lighting creates soft highlights on his face. The background remains stable. SHOT 3 (4–6s): Extreme close-up from the side, slight push-in. He bites into the salmon. After a brief pause, he begins to chew slowly. Jaw movement gradually slows. Breathing stabilizes. His eyes slightly widen and hold, then soften. His shoulders subtly drop. Facial muscles relax, and the corners of his mouth slowly lift. SHOT 4 (6–7s): Fast but smooth push-in to the eye, transition via reflection. The camera pushes into his eye, filling the frame. The reflection in his eye gradually brightens and expands. Flowing light patterns and wave-like motion appear within the reflection. Restaurant details gradually disappear. The light transforms into underwater lighting and fluid textures, transitioning naturally into the ocean environment. SHOT 5 (7–11s): 24mm wide angle, slow descending high-angle forward move. The scene opens into a clear and colorful underwater world. Sunlight penetrates the water surface, forming visible light beams that move gently and create layered lighting variations. The water is clear, transitioning from light blue to deep blue. The seabed consists of fine sand, rocks, and large areas of soft seaweed, gently swaying with the current. Coral appears in various shapes and colors, creating clear spatial depth. Multiple groups of fish swim at different distances, including schools of salmon, whose scales shimmer subtly in the light. Fish move in unified, smooth directions across the frame. The man is present in the scene from the beginning, his body slightly leaning forward in a horizontal floating posture. His arms extend naturally, legs slightly lowered. His body drifts subtly with the current. His clothing moves softly. His head faces forward, and his gaze follows the movement of the fish. SHOT 6 (11–13s): Low-angle slow orbit, slight upward tilt. The camera moves from behind the man and slightly rises while orbiting. Foreground seaweed continues to sway. Coral forms the mid-ground structure. More fish pass through from different directions, while salmon maintain a consistent swimming direction. Light beams shift slowly, creating dynamic lighting and color layers. The man maintains a stable floating posture, without noticeable displacement. His head turns slightly, following the fish with his gaze. A subtle smile remains, and his face stays relaxed. SHOT 7 (13–15s): Match cut back to restaurant, static shot. The scene cuts back to the restaurant. The man maintains the same head angle and continues chewing. After a brief pause, he swallows, slowly opens his eyes, and his smile becomes more pronounced. He lets out a soft expression of enjoyment. He cuts another small piece of salmon with his utensils. The movement is more natural and continuous, without hesitation. Plate reflections and environment remain consistent. SFX: Soft cutting sound, chewing sound. Ambient sound fades out during transition. Restaurant sound resumes after returning. Underwater environment features gentle water flow sounds.

Seedance 2.0 AI video prompt: [CINEMATIC SETUP] Live PGA Tour TV broadcast style, shot on professional 35mm br

[CINEMATIC SETUP] Live PGA Tour TV broadcast style, shot on professional 35mm broadcast cameras. Natural outdoor daylight, vibrant green turf, and high-contrast professional color grade. Atmosphere is electric with a hushed crowd. Immersive spatial audio featuring a hushed commentator voice-over saying "Techhalla looking for the miracle here..." followed by a massive crowd roar. [IMAGE REFERENCES / LEGEND] [ref] : The golfer. Maintain exact facial features, beard, and black cap from the reference image. He is wearing a professional white golf polo. [TIMELINE SECOND BY SECOND] 0-3s: [Close-up shot] [ref] addresses the ball, focused expression. In the blurred background, a large professional billboard clearly reads "Follow TechHalla" in bold tournament typography. He swings with perfect physics. [Sound: Sharp metallic "clink" of the club hitting the ball]. 3-6s: [Wide-angle cut] Tracking shot following the ball soaring into a clear blue sky. [Sound: Wind whistle]. 6-8s: [Mid-shot cut] [ref] standing on the tee, hand over his eyes, looking up at the sky with anticipation. Cinematic low-angle push-in. 8-12s: [Extreme close-up cut] The golf ball lands softly on the green, rolls with realistic friction, and drops perfectly into the hole. [Sound: The "plop" of the ball hitting the bottom of the cup followed by a sudden, deafening crowd explosion]. 12-15s: [Medium shot cut] [ref] celebrating wildly, pumping his fist and smiling. TV broadcast graphics overlay appears at the bottom: "TECHHALLA - HOLE IN ONE". [Sound: Commentator screaming "UNBELIEVABLE! TECHHALLA WITH THE ACE!"]. [STYLE & QUALITY BOOSTERS] Photorealistic 8K, ultra-detailed textures on the grass and clothing, cinematic broadcast lighting, perfect motion blur on the ball, movie-level realistic facial features, no deformation, stable throughout.

Seedance 2.0 AI video prompt: SCENE: A magical spring garden filled with blooming pink flowers, soft sunlight,

SCENE: A magical spring garden filled with blooming pink flowers, soft sunlight, and floating glowing particles. Atmosphere is dreamy, pastel-toned (white, pink, soft green), with a fantasy aura. SUBJECT / CHARACTER: A beautiful fairy-like girl with long blonde hair, soft elf ears, glowing skin. She wears a flowing silky ribbon dress in pink and green tones, semi-translucent, moving elegantly with the wind. 🎬 SHOT 1 — The Melody (INTRO) Action: The girl stands among flowers.Gentle wind flows through her hair and dress. She slowly opens her lips and begins singing a magical melody (visible lip movement, emotional expression). Camera: Extreme close-up → lips and lower face Slow cinematic push-in Soft depth of field, dreamy bokeh Audio: Clear, enchanting vocal melody (no words, humming-like but intentional) 🎬 SHOT 2 — Magic Awakens Action: As she sings, glowing particles intensify in the air. Light begins to gather behind https://t.co/MMGFY61B86 subtly react (slight movement, magical response). Camera: Side profile shot → slow orbit around her (arc shot) Light flares enter frame 🎬 SHOT 3 — Dragon Emerges Action: A massive crystal dragon forms from light particles. Its body is made of glowing white and pink crystal, semi-transparent, refracting light. It slowly materializes behind her. Camera: Low angle wide shot → dragon rising (epic scale) Slight camera shake for presence Audio: Deep crystal resonance + soft magical chimes🎬 SHOT 4 — Approach Action: The dragon moves gracefully toward the girl. Its movement is slow, elegant, non-threatening. The girl keeps singing softly. Camera: Tracking shot → follows dragon from side Foreground flowers pass softly (depth effect) 🎬 SHOT 5 — First Contact Action: The dragon lowers its massive head gently. The girl lifts her hand and softly strokes the dragon’s face. Her singing becomes softer, more intimate. Camera: Medium close-up → hand touching crystal surfaceMacro detail → light refracting through dragon 🎬 SHOT 6 — Connection (EMOTIONAL CLIMAX) Action: The girl turns her head slowly. She leans forward. The dragon moves closer. Their foreheads touch gently. She stops singing. Both close their eyes peacefully. Camera: Close-up → symmetrical framing Very slow push-in Soft glow increases around them Audio: Melody fades into soft ambient harmony

More use cases

Frequently asked questions

What are the best AI video prompts for close-up video?

The best close-up prompts name three things together: the specific element being isolated (the iris, the fabric pore, the product surface texture, the micro-expression), the focus plane and depth of field instruction (sharp focus on the left eye, the surrounding face falling to soft bokeh), and the light direction relative to the surface (raking side light to reveal texture, soft front fill for skin, hard backlight for product translucency). Without all three, the model defaults to a generic face or object at close range with no compositional logic. Every prompt in this gallery uses that three-layer structure.

How do I write an extreme close-up (ECU) prompt for Seedance 2.0?

Structure the ECU prompt in four elements: (1) the specific subject element — not "a face" but "the left eye, upper eyelid slightly lowered"; (2) the focus plane instruction — "sharp focus on the iris, the lashes at the near edge just slightly soft, the bridge of the nose falling to bokeh"; (3) the light direction and quality — "soft box from camera-left raking slightly across the eye socket to reveal the micro-geometry of the orbital area"; (4) the motion if any — "a 2cm pull-back over 4 seconds, maintaining critical focus on the iris as the surrounding face slowly enters frame at the edges." The focus plane specification is the most commonly missing element and the one that most determines whether an ECU looks deliberate or accidental.

Can Seedance 2.0 generate macro and product texture close-up video?

Yes. Seedance 2.0 handles macro and product close-up video well when the prompt names the specific surface element, the light direction that reveals texture, and the focus plane. For product texture, raking light at a low angle to the surface — "a raking side light at 15 degrees to the material surface, grazing across the weave and creating a shadow structure that makes each thread three-dimensional" — is the most reliable technique for making surfaces feel touchable on screen. For macro work, naming the specific visual phenomenon you want revealed (the surface tension before a liquid breaks, the crystal structure of a material, the micro-scale pore pattern of a fabric) gives Seedance a specific discovery to execute rather than a generic small-scale shot. Browse the close-up prompts here for real examples with preview videos.