Prompt Video cho Documentary

A young traveler hikes through a lush mountain forest, crosses a wooden bridge over a flowing stream, and reaches a stunning waterfall hidden among moss-covered rocks. Ultra-realistic travel documentary, authentic hiking movement, realistic environmental physics, natural English lip-sync, bright daytime lighting, immersive forest ambience, and seamless story continuity throughout.

**Main Subject:** Young Korean woman, from reference image, 24, naturally attractive, realistic skin, minimal makeup, long dark hair loosely tied back. Wearing a faded oversized mustard-yellow T-shirt, loose dark-gray sweatpants, white socks, and worn house slippers. Thin silver necklace. Preserve her exact identity, facial features, hairstyle, and appearance throughout. **Location:** Old Seoul apartment on a warm weekend afternoon during moving day. Narrow hallway, worn wooden doors, stacked cardboard boxes, plastic bags, old furniture, partially empty rooms, open windows, tangled cables, dusty corners, neighboring apartment buildings visible outside. Warm natural sunlight mixed with slightly dim interior shadows.\n\n**Style:** Ultra-realistic early-2000s Sony MiniDV home video. Candid family recording, imperfect and unstaged. Heavy handheld movement, awkward framing, autofocus hunting, exposure pumping between bright windows and dark rooms, faded colors, soft contrast, DV compression, slight motion blur and microphone noise. No stabilization or modern cinematic camera movement.\n\n**00:00–00:03:** She struggles through the apartment hallway carrying a large cardboard box that blocks most of her view. She nearly bumps into a doorframe, laughs, and sets it down.\n\n**00:03–00:06:** She opens the box and realizes several smaller items have fallen over inside. She kneels down and starts reorganizing them while someone off-camera tells her where the box should go.\n\n**00:06–00:09:** Two people attempt to carry an old wooden chair through the narrow doorway. They get stuck for a moment, laugh, rotate it awkwardly, and finally squeeze it through.\n\n**00:09–00:12:** She sits briefly on an unopened box, exhausted, drinking from a plastic bottle while looking around the half-empty room. Sunlight pours through the window behind her.\n\n**00:12–00:15:** Someone off-camera calls her name. She immediately gets up and grabs another box. As she walks past the camera, she notices it, gives a tired little smile, and keeps working. The camera follows her into the empty room before accidentally pointing toward the bright window and blowing out the exposure.\n\n**Audio:** Natural sound only—cardboard scraping, footsteps, furniture dragging, tape ripping, plastic bags rustling, distant traffic, muffled conversations, elevator sounds, doors closing and occasional laughter. No music, narration, or added sound effects.

A young snowboarder drops into an alpine terrain park, carves smoothly down the slope, performs a controlled 180° jump and freestyle butter, then finishes with a clean stop. Ultra-realistic winter sports documentary, physically accurate snowboard physics, authentic human movement, natural English lip-sync, bright winter daylight, immersive mountain ambience, and seamless story continuity throughout.

Ultra-photorealistic full 3D cinematic wildlife sequence, 15 seconds, single continuous take with natural camera moves, absolute real-looking African animals, hyper-detailed fur, muscle, dust and light physics, zero CGI look, documentary quality. [0-4s]: Wide establishing shot of the African savanna at golden hour. A fully adult African lioness stands alert in the center foreground, dense golden-tan coat with every individual hair, subtle breathing and ear twitches visible. In the distance a massive horde of over 40 real black-backed and side-striped jackals begins charging toward her across cracked red earth, kicking up thick volumetric red dust clouds. Slow cinematic push-in begins. [4-9s]: Medium tracking shot following the charging jackal horde. The pack surges forward in chaotic realistic running gaits, lean bodies, open jaws with saliva flecks, pointed ears, frantic snarls. Dust particles catch the low sunlight. The lioness remains steady, watching them approach. Camera continues smooth push-in while slightly orbiting right for depth. [9-13s]: The lioness’s massive partner, a dominant African lion with thick dark wind-ruffled mane, emerges powerfully from directly behind her. He strides into the foreground, plants his huge paws in the dust, lowers his head and delivers a deep chest-vibrating roar that freezes the entire jackal pack mid-charge. Extreme detail on mane strands, wet nose, amber eye reflections, muscle ripples under skin. [13-15s]: Close-up reaction shot of the jackals skidding to a halt, some scattering slightly in fear while the lion holds his protective stance in front of the lioness. Camera settles on a powerful heroic medium shot of the lion and lioness together against the dusty savanna. Camera language: smooth cinematic push-in + subtle orbit, shallow depth of field, natural handheld micro-shake, anamorphic lens feel, volumetric god-rays and heat haze. Style: ultra-realistic 3D photorealism, ARRI Alexa 65 look, real animal fur physics, authentic African savanna lighting and atmosphere, 8K detail, original quality. Audio (native full stereo sound): (soft distant wind and savanna ambient bed) <jackal pack running feet on dry earth, growing louder snarls and yips, heavy dust whooshes> <deep powerful African lion roar that echoes across the plains, low chest rumble> <jackals skidding and whimpering in fear, sudden silence after the roar>

Reference Character: Use the first image as the protagonist — a field journalist/survivor. Maintain identical face, hairstyle, clothing (soot-streaked jacket), and identity throughout all shots. Reference Location: Use the second image as the collapsing mountain town. Maintain identical architecture, ash-covered streets, and volcanic backdrop throughout every scene. Style: Ultra realistic cinematic disaster thriller, handheld chaotic camera work, photorealistic, ash-orange and grey color palette, volumetric smoke and falling debris, shallow depth of field, 35mm, harsh directional light through smoke, physically accurate motion blur, HDR, desaturated cinematic grade. Audio: No music. Only distant rumbling, falling ash/debris, panicked breathing, cracking structures, wind, muffled crowd sounds, heartbeat under stress. 0–3s Extreme wide shot. A volcano erupts in the distance, ash plume rising into a blood-orange sky. Protagonist stands frozen for a beat, then turns to run. 3–6s Handheld sprint shot, camera matching pace. Protagonist runs through a narrow street as ash rains down, covering everything in grey. Others flee in the background, blurred. 6–9s Close-up, ground-level. A crack splits the pavement just behind the protagonist's heel as they leap over it without breaking stride. 9–12s Wide tracking shot. A building facade collapses in slow motion beside the running path, dust and debris exploding outward, catching the edge of frame. 12–15s Close-up, protagonist's face — eyes wide, breathing ragged, ash coating skin and hair. Camera shakes violently with each footfall. 15–18s Medium shot. Protagonist grabs a stumbling child/stranger by the arm, pulling them upright without stopping, continuing the run together. 18–21s Low-angle shot. They burst through a doorway into a stone archway just as a wave of ash and debris rushes past outside, momentarily blacking out the frame. 21–24s Interior held shot. Both catch their breath in the dim archway, coughing, ash settling around them like snow. Distant rumbling continues. 24–27s Slow push-in through a gap in the archway. Outside, the ash cloud begins to settle, revealing the ruined street bathed in eerie orange light. 27–30s Final wide shot. Protagonist steps out into the haze, silhouette stark against the smoldering skyline, breathing steadying as the rumbling fades to silence. Quality Tags: ultra realistic, cinematic disaster masterpiece, physically based rendering, volumetric ash and smoke simulation, HDR, 8K, realistic debris physics, consistent character identity, epic scale, no music, no text, no logo, no watermark.

Duration: 20 seconds Format: 9:16 vertical Style: Couple POV handheld selfie feel (Boyfriend POV), summer outdoor natural light, one-shot no editing, real mobile phone quality Character: Main character @Image1 [Camera & Framing Principles] The boyfriend holds the phone to shoot in first-person perspective, maintaining a normal social distance of about 1.5–2 meters. The whole film is dominated by full-body and upper-body shots; absolutely no extreme close-ups filling the face. Perspective changes are generated by the two characters moving naturally: - Start: Full body medium shot - Middle: Upper body (waist up) - Closest: Half-body close-up above the chest, with head and shoulders remaining completely in the frame with margins. The lens shakes slightly, with real breathing fluctuations, naturally swaying with her movements, slightly out of focus and then re-focusing, no stabilizer. [Environment] A shaded path in a summer afternoon, she stands in mottled tree shadows, behind her a row of green trees and a sun-drenched road, shallow depth of field turns the background into flowing green light spots. All-natural lighting, no subtitles, no filters, no BGM. [Script Breakdown] [00:00-00:04] Full Body Medium Shot · Called out, unable to smile: She is standing in the shade looking down at something, relaxed. Boyfriend says: "Hey, look here—smile." She reacts late, looking at the lens with a "why are you filming me?" expression. She tries to smile but it's a failed smile—lips only slightly raised, eyes not matching, looking a bit awkward. [00:04-00:07] Upper Body · Hit in the weak spot: Boyfriend steps forward. He says: "Just like the day you first met my mom." Her reaction is in two layers: first, disbelief/confusion, then a playful explosion: "That's different! I was nervous!" [00:07-00:10] Upper Body · Can't hold it back: She tries to hold back her laughter but fails. She starts with a sniffle, then squints her eyes, and finally lets out a broken laugh, turning her head away to hide from the camera. [00:10-00:12] Upper Body · Stopped: Boyfriend says: "Wait, don't move, you have something on your mouth." Her laughter stops like a car braking, turning into a look of concern and tension. [00:12-00:15] Close-up · Self-check: She walks closer to the lens to use it as a mirror, wiping her lip and checking her finger, looking anxious. [00:15-00:17] Frozen: Boyfriend says: "...it was just a bit of cuteness." She freezes for a whole second, staring at the lens with no expression except a small eye movement. [00:17-00:20] Shy Closing: She realizes she's been teased. She makes a fake angry face for half a second before it melts into a shy smile. She hides half her face with her hand and says sweetly: "Oh you're so mean—people get shy." The shot ends on her peeking through her fingers.

Create a product video ad from [image1],[image2], script "9:16, 24fps, 15 seconds. 0-3s: Close-up shot. In a dim room lit by warm ambient lamps, a stylish girl with bangs and freckles calmly puts on her over-ear headphones. 3-5s: Close-up of a finger tapping the "Play" button on a smartphone. As the music starts, the girl closes her eyes and begins swaying rhythmically to a heavy beat, fully immersed. 5-12s: Sophisticated Documentary Montage. The girl remains the absolute visual center within real-world settings: 1. Sitting on a couch at a dim party, she sways in her own world while crowds flow through the foreground and background. 2. At a livehouse venue, she sways in the center with people in the background rendered in artistic motion blur. The camera vibrates slightly with the beat, capturing her internal focus amidst external chaos. 12-15s: The camera snaps back to the girl in her room mid-sway. The background swiftly dissolves and transitions into a solid brand-red color, with a white brand logo “Apple Music”fading into the center. Negative Prompt: Any text, subtitles, watermarks, light effects, black background."

Main Subject: \n\nYoung Korean woman, 23, natural everyday appearance, shoulder-length black hair loosely tied with a simple fabric scrunchie, wispy bangs, realistic skin texture, minimal makeup, calm and slightly playful personality. Wearing a faded red zip-up hoodie over a white T-shirt, loose dark-blue jeans, white sneakers, and a small navy canvas shoulder bag. Maintain consistent identity, clothing, hairstyle, and appearance throughout.\n\nLocation: Small neighborhood laundromat on a rainy afternoon. Old front-loading washing machines, plastic laundry baskets, fluorescent ceiling lights, fogged windows covered with rain droplets, vending machine, folding table, faded Korean instruction stickers, and a quiet residential street visible outside.\n\nVisual Style: Ultra-realistic documentary realism. Ordinary, candid behavior with authentic early-2000s Korean neighborhood details.\n\nCamera Style: Early-2000s Sony MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting between spinning washing machines and her face, fluorescent flicker, exposure pumping near the bright window, faded colors, soft contrast, slight motion blur, DV compression artifacts, mild digital noise, no stabilization.\n\n00:00–00:03\nShe enters carrying a blue laundry basket, shaking a few raindrops from her hoodie. The camera briefly focuses on the wet floor before finding her.\n\n00:03–00:06\nShe loads clothes into an old washing machine and pours detergent from a small plastic bottle. The machine door closes with a heavy click.\n\n00:06–00:09\nShe sits on a plastic chair watching the clothes spin through the round glass door. She rests her chin on one hand, looking slightly bored.\n\n00:09–00:12\nRain becomes heavier outside. She notices the camera and makes a small amused expression before pointing toward the spinning laundry.\n\n00:12–00:15\nThe washing machine suddenly finishes its cycle with a loud beep. She stands and opens the door as the camera moves closer, loses focus, and abruptly cuts to black.\n\nAudio: Natural ambience only—washing machines humming, water spinning, fluorescent buzzing, rain against windows, footsteps, plastic basket sounds, machine beeps, distant traffic. No music. No narration.\n\nGoal: A forgotten MiniDV home video from 2004, capturing a completely ordinary rainy afternoon at a small Seoul laundromat–mundane, intimate, imperfect, nostalgic, and convincingly real.

Restrained Documentary footage, single continuous take, no cuts. Real, natural steady footage, intimate close-up framing.nuanced understated, An Italian woman, twenty-eight years old, dark hair loosely framing her face, sharp blue suit, open collar, close-up dead center, matches the confirmed opening frame exactly: soft window light from one side, muted neutral grade, shallow depth of field, She speaks in a near-whisper with a noticeable Italian-English accent, voice flat, controlled, unhurried, every word calculated and released with total economy, nothing given away. She holds the frame from the opening image, composed and still, the smallest flicker of restraint beneath an otherwise unreadable calm. Soft room tone, quiet breath, distant ambient hum. No music or soundtrack, diegetic sound only. The camera holds the opening frame's exact composition for the first four seconds (0–4s), an all but invisible push-in beneath complete stillness. She holds, unmoving but for a single natural blink (4–6.5s), then speaks, barely audible, flat and even, accent faint in the vowels: "Who told you my name is Jill?" (6.5–8s), a long still pause, breath suspended, before "Tell me. Please." (8–9.5s), the words dissolving to near silence. Final beat: she remains motionless, eyes steady, lips closed, expression unreadable, stillness unbroken (9.5–10s). Face identity stable throughout, one natural blink only, performance held to the barest minimum of visible effort.

[Video Specifications] 16:9, 1920×1080, 24fps, ultra-realistic wildlife macro cinematography. Bright tropical morning, natural sunlight passing through plants from the upper left, forming clear but soft golden sunrays. Small amount of real suspended dust and pollen particles in the air, visible only in sunlight. ARRI Alexa 35 film texture, professional ultra-macro probe lens, real shallow depth of field, natural bokeh, delicate motion blur, and slight film grain. The entire film is one continuous shot, no cuts, no resets, no morphing. No background music. [Reference Image and Consistency] The uploaded butterfly close-up must serve as the perfectly consistent first frame and the only reference for character and environment throughout the film. Do not add a second ending image. Maintain the same Blue Morpho throughout: identical head, compound eyes, black body fuzz, cobalt and cyan iridescent wings, dark wing edges, and subtle pink-purple textures. Always maintain four correctly connected wings, six long black legs, two antennae, and one curled proboscis. Do not change species, head size, wing patterns, or body proportions. The camera focus must consciously shift in sequence rather than the entire frame being clear throughout: Compound eyes → Stamens and pollen → Wing scales → Complete butterfly. Each focus transition is completed through a real lens rack focus, lasting approximately 0.4–0.7 seconds. Prohibit sudden blurring, random defocusing, or AI-style focus pumping. [0–4s | Compound Eyes and Natural Vitality] Start directly from the ultra-close-up compound eye in the reference image. The compound eye maintains sharpest focus, showing fine compound eye structures and tiny reflections of the tropical garden and sunlight. The camera is not static but moves in a very slow arc around the head by about 25 degrees, while sliding slightly forward. The butterfly maintains real micro-movements: one antenna slowly sweeps the foreground, the other oscillates slightly independently; head makes tiny adjustments; proboscis contracts slightly; the thorax and abdomen show very subtle fluctuations with breathing. Nearby petals are gently pushed by a breeze. Prohibit the butterfly from remaining completely motionless like a static model. Focus remains locked on the compound eye, foreground stamens naturally blurred. Finally, the camera slides slowly along the butterfly's line of sight toward the magenta stamens ahead, the compound eye beginning to softly defocus. [4–8s | Focus Shift to Flower and Pollen] Complete the first natural rack focus: compound eyes gradually blur, magenta stamens, dewdrops, and golden-yellow pollen enter sharp focus. The camera slides laterally close to the stamens, passing over the wet petal surface and transparent dewdrops. Dewdrops must realistically reflect the blue wings and surrounding greenery. One of the butterfly's forelegs moves forward and gently touches a stamen. Real contact must occur first, with the stamen bending and rebounding, then releasing a small amount of fine pollen. Pollen is not an explosion but dozens of different-sized particles slowly entering the sunlight, some close to the lens, creating natural foreground/background parallax. The curled proboscis slowly extends toward the flower center, motion continuous, soft, and physiologically accurate. The camera continues moving along the stamen toward the butterfly's body, focus briefly locking on a few golden pollen grains attached to the fine hairs of the foreleg. The butterfly in the background remains recognizable but softly blurred. [8–12s | Focus Shift to Wing Micro-texture] The camera slides up the foreleg to the thorax and wing base, completing the second rack focus: stamens gradually blur, wing base and tiny scales enter sharp focus. The butterfly begins to slowly open its wings. The camera moves in a parallel track a few centimeters from the wing surface, clearly showing millions of overlapping real micro-scales, fine wing veins, and dark wing edges. As the camera angle changes, structural color naturally shifts from deep blue to cobalt, cyan, and blue-violet; color changes come from light angles, not glowing or magic effects. Wings complete only one full and natural opening motion, not mechanical repetitive flapping. The weak airflow generated by the expansion pushes petals, dewdrops, and previously released pollen. A small amount of pollen spirals upward through the sunlight, forming a delicate airborne micro-pollen effect. Some tiny dewdrops are lifted by the airflow, but movement must follow weight, inertia, and gravity. The camera always stays on the outside of the wings, never passing through wings, body, or flowers. Wings can pass near the lens but must never completely cover the frame or cause shape distortion. [12–15s | Full Display and Short Takeoff] The camera pulls back quickly but smoothly and rises slightly, completing the third focus transition, transitioning from wing micro-texture to the whole butterfly. The butterfly's full body enters sharp focus, four wings correctly structured, six legs still naturally gripping the petals. The butterfly's body first dips slightly, wings powering upward; then leaves the flower with one strong downward wing beat. Causality must be clear: legs release petals first, petals bend downward due to reaction force, body gains upward and forward acceleration, then petals rebound. Prohibit direct floating, teleporting, or powerless shrinking. The butterfly performs only one short-distance natural takeoff, flying forward and upward in the direction of sunlight. Wings maintain fast but slightly irregular real flapping. Camera tracks and pulls back synchronously with a slight lateral tracking, keeping the butterfly clear in the air while allowing magenta flowers, floating pollen, and golden sunrays to form clear spatial layers. In the final second, the butterfly flies from the foreground to the midground, maintaining the same appearance and wing pattern. The camera stays in a dynamic tracking state, not landing on a second flower, not suddenly freezing, and not switching scenes. [Camera and Focus Principles] The camera continuously performs subtle arc movements, lateral slides, tracking along object surfaces, and a final steady pull-back throughout the entire sequence, never using stiff fixed shots. Movement must be delicate, stable, and have the spatial parallax of real macro photography. Focus changes must be clear and serve narrative purposes: Compound eyes sharpest, flowers blurred. Stamens, dewdrops, and pollen sharpest, butterfly softly blurred. Wing scales sharpest, flower blurred. Complete butterfly enters sharp focus upon final pull-back. Prohibit the entire sequence from being all sharp, and prohibit the subject from suddenly blurring without reason. Shallow depth of field must come from real optical distance, focus plane moving smoothly. [Physical and Environmental Details] Pollen and dust can only move due to foreleg contact, stamen rebound, or wing airflow; prohibit random appearance without cause.

Nostalgic vintage European countryside footage, warm sunlight, faded tones, soft grain, imperfect handheld camera, natural movement, intimate documentary realism. 0–3s: A young French woman walks beside a quiet village canal carrying a wicker basket. A small paper boat suddenly drifts toward her. She picks it up and discovers a tiny handwritten drawing inside. 3–7s: She follows the canal through the village, passing a bakery, old bicycles, flower-filled windows, and a sleepy dog resting in the sun. A bicycle bell rings behind her and she instinctively turns. 7–11s: She reaches a stone bridge where a little boy is searching for his paper boat. She holds it up. His face lights up, and he runs toward her. His mother smiles from a nearby doorway. 11–15s: The woman places the boat back into the water. The boy gently pushes it forward. Suddenly, several paper boats appear around the corner, floating together down the canal. She watches them disappear into the golden sunlight, smiles softly, and walks away. Natural human reactions, subtle camera shake, realistic wind and reflections, organic focus changes, authentic village details, nostalgic atmosphere, completely unstaged, no modern cinematic effects, no text, no watermark

Gritty Cinéma Vérité, handheld tracking cinematography, 35mm natural film grain, soft tropical daylight, authentic documentary energy, subtle camera shake and natural operator breathing. Maldives luxury island resort, turquoise lagoon, white sand, lush palms, wooden villas and busy resort paths. SHOT PRIORITY: The camera must NEVER follow her from directly behind. Keep her face and front/side profile visible throughout. Primary perspective is a FRONT 3/4 TRACKING SHOT, with the camera moving backward ahead of her bicycle at matching speed. Secondary angles are FRONT-SIDE and PURE SIDE TRACKING. Camera remains physically close enough to capture facial expression, hair movement and natural body motion. No rear-view hero shots. CHARACTER: A beautiful young adult woman with sun-kissed skin, long flowing dark hair, wearing a minimal black high-cut swimsuit and light sandals, riding a simple white beach bicycle at a casual natural pace. Relaxed posture, soft smile, effortless expression. Hair and swimsuit fabric react naturally to the ocean breeze and bicycle movement. Stable facial identity and consistent wardrobe across every shot. TIMELINE: 0-2s: [FRONT 3/4 TRACKING] Camera moves backward smoothly in front of her as she rides out from a wooden villa path. Her face is clearly visible. A staff member in white uniform passes in the background carrying a drinks tray and waves. Two tourists in colourful wraps walk past laughing. 2-4s: [FRONT-SIDE TRACKING] Camera shifts slightly toward her left/front side while maintaining eye contact and visible facial profile. The path opens toward a lagoon boardwalk. A giant tortoise slowly crosses ahead of her bicycle. She naturally slows and steers around it. A parrot flies low across the frame. 4-6s: [DYNAMIC FRONT TRACKING] Camera continues moving backward ahead of her as she gently accelerates past a small open restaurant. Waiters carry plates, guests turn and smile. In the lagoon behind her, a manta ray leaps from the water with a large realistic splash. 6-8s: [SIDE-FRONT TRACKING] Camera moves parallel to her front half, keeping her face visible while the sandy palm-lined path passes behind. Two giant tortoises cross in the deeper background. A whale breaches far across the lagoon, creating a tall spray. 8-10s: [FRONT 3/4 TRACKING] She rides toward camera at a relaxed pace. A group of tourists taking selfies appears behind her; one points toward the lagoon. Another manta ray jumps almost parallel to her. A resort golf cart slows behind and gives her space. 10-12s: [CLOSE SIDE TRACKING] Camera travels beside her at shoulder height, capturing her natural smile, wind moving through her hair and detailed fabric motion. The path curves along the water. A large whale surfaces in the background and rolls, its fin cutting through the lagoon. Bright parrots land on a railing and take off.

Main Subject: Young Korean woman, 24, natural everyday appearance, long dark-brown hair tied into a low messy ponytail with loose strands around her face, realistic skin texture, minimal makeup, relaxed and curious personality. Wearing a faded sage-green windbreaker over a white T-shirt, loose beige cargo pants, worn navy canvas sneakers, a dark baseball cap, and a small canvas backpack. Maintain consistent identity, clothing, hairstyle, and appearance throughout.\n\nLocation: Small working fishing harbor in Busan just after sunrise. Weathered fishing boats, tangled ropes, blue plastic crates, fishing nets, concrete docks, old warehouses, seagulls, calm seawater, distant hills, and a few local fishermen preparing their boats. No tourists or commercial attractions.\n\nVisual Style: Ultra-realistic documentary realism. Genuine candid behavior, natural body language, imperfect everyday moments, authentic coastal atmosphere.\n\nCamera Style: Early-2000s Sony MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting between fishing equipment and her face, exposure pumping between bright sky and shaded docks, faded colors, soft contrast, slight motion blur, DV compression artifacts, mild sensor noise, no stabilization.\n\n00:00–00:03\nShe walks carefully along the concrete dock carrying a small fishing rod, stepping around coiled ropes. The camera briefly focuses on the ropes before finding her.\n\n00:03–00:06\nShe sits on the edge of the dock and prepares the fishing line, concentrating as a gentle sea breeze moves her ponytail.\n\n00:06–00:09\nShe casts the line into the calm water and waits quietly. A seagull lands nearby, making her turn and smile.\n\n00:09–00:12\nThe fishing rod suddenly moves slightly. She looks surprised and quickly grabs it with both hands, laughing when she realizes it was only the current.\n\n00:12–00:15\nShe looks toward the camera with an embarrassed smile, shrugs playfully, and returns her attention to the water. The operator pans toward the boats as the recording abruptly cuts to black.\n\nAudio: Natural ambience only—seagulls, gentle waves against concrete, ropes creaking, distant boat engines, fishermen talking, wind, footsteps, and water movement. No music. No narration.\n\nGoal: A forgotten MiniDV home video from 2004, capturing a quiet morning at an ordinary Busan fishing harbor—raw, peaceful, imperfect, nostalgic, and completely believable.

FORMAT 15 seconds | 16:9 | live-action fashion dress shoot footage Real outdoor fashion shoot in Taj Mahal, Agra. Raw professional camera footage, observational realism. No commercial-style fantasy treatment. REFERENCE CONTROL @Image1 = exact dress reference. The model wears the exact dress shown in the reference. Preserve the dress construction precisely: dusty rose-pink traditional outfit, intricate lace and embroidery, detailed floral embellishment, matching embroidered lower garment, sheer matching dupatta with detailed embroidered border, rich traditional textile detailing. Do not simplify or redesign the dress. Maintain the exact dress throughout every shot. SETTING Beautiful open-air fashion shoot at the Taj Mahal during sunset. Historic Mughal architecture, white marble façades, gardens, trees and symmetrical pathways surrounding the model. Soft warm sunset daylight. Real Taj Mahal atmosphere. MODEL Adult high-fashion model. Tall, slender proportions. Minimal makeup, understated hair. Natural relaxed expression. Controlled graceful movements. 00–02.5s — ENTRANCE Wide shot from the Taj Mahal. The camera holds on the Taj Mahal and surrounding garden. The model suddenly enters the frame from the left side wearing the exact referenced dress and smiling naturally. The dress begins moving naturally with her steps. The dupatta responds gently to the light breeze. 02.5–05s — WALK Medium rear three-quarter tracking shot. Camera moves behind her as she walks into the garden. Show the back of her body while revealing the details of the dress. The dress sways with realistic weight and delayed momentum. The embroidery catches subtle sunset daylight. 05–07s — DETAIL Extreme close-up of the dress. Show the dimensional lace, embroidery and layered construction. Camera moves naturally across the fabric. The intricate details catch subtle sunset daylight. 07–09s — FACE Close-up shot of her face. Show her eyes, lips and natural facial expression. She looks naturally toward camera before shifting her gaze toward the sunset. Natural skin texture and realistic facial detail. 09–12s — SUNSET Medium-wide shot. She sits gracefully in the garden and adjusts her clothes naturally. The fabric gathers and settles realistically around her. She looks toward the setting sun. Warm sunset light falls naturally across her face and dress. 12–15s — DRONE Distant drone shot. The camera rises and pulls backward away from her. Reveal the model seated in the garden with the Taj Mahal behind her. The frame expands to reveal the scale of the Taj Mahal and surrounding gardens. CAMERA Real professional fashion-shoot camera coverage. Wide, tracking, close-up and drone professional camera footage. Natural operator micro-movement. Minor reframing. Real autofocus adjustments. Natural motion blur and depth of field. No floating camera.

Create a 15-second ultra-photorealistic live-action medieval war sequence set during the 12th-century Crusades, depicting a fictionalized battlefield confrontation between Crusader forces and the army of Salahuddin (Saladin). The entire scene must feel grounded, documentary-like, raw, and physically realistic, as if authentic historical footage had somehow been captured with a primitive period camera. Environment: A medieval settlement and battlefield in the Levant during the Crusades, with weathered stone buildings, fortified walls, dirt roads, wooden structures, tents, farmland, horses, carts, siege equipment, scattered shields and weapons, drifting smoke, dust in the air, damaged structures, and a tense wartime atmosphere. Harsh overcast afternoon light mixed with dusty sunlight, natural atmospheric haze, and realistic environmental wear. Characters: Crusader soldiers wearing historically inspired 12th-century mail armor, surcoats, helmets, shields, boots, and period-accurate equipment. Salahuddin’s soldiers wear historically inspired Ayyubid-era Middle Eastern military clothing, chainmail, helmets, shields, and period-accurate equipment. Natural faces, realistic skin texture, sweat, dirt, fatigue, fear, and believable body movements. Horses and animals must move according to realistic biomechanics. 0–3s — Establishing Shot: Wide handheld shot of a dusty medieval settlement suddenly filled with smoke and confusion. Crusader soldiers and Salahuddin’s forces move rapidly between stone buildings and defensive positions. Horses pull wooden carts while civilians rush toward safer areas. Dust and smoke drift naturally through the battlefield. 3–6s — Tension: Camera moves through the battlefield at shoulder height, following several Crusader soldiers as distant battle cries, horns, arrows, and metal impacts are heard. They immediately react and take cover behind a stone wall and overturned wooden cart. Across the battlefield, Salahuddin’s soldiers advance cautiously through the dust. 6–10s — Combat: Fast handheld tracking shot as Crusader and Ayyubid soldiers clash between cover. Shields absorb impacts, swords collide with realistic weight and momentum, arrows strike wooden structures and shields, and small pieces of stone, wood, dust, and debris fall naturally from nearby impacts. Weapon movement, armor weight, recoil from physical impacts, momentum, balance, and body weight must be physically accurate. Keep the violence realistic and restrained. 10–13s — Human Moment: Camera briefly focuses on a wounded soldier being helped behind cover by another soldier. Their breathing, facial expressions, fear, exhaustion, body language, armor weight, and movement should feel natural and unscripted. In the background, the battle continues through smoke and dust. 13–15s — Final Shot: Camera pulls back into a wide shot of the medieval battlefield as smoke slowly moves through the settlement. Crusader forces

15-second ultra-photorealistic cinematic video set in a completely untouched ancient forest inspired by the year 1200 AD or earlier. A beautiful young woman is the main character, wearing a simple historically inspired medieval linen dress in earthy natural tones, with long slightly messy hair and no modern accessories or makeup. She is peacefully playing with a large realistic giant panda deep inside the ancient forest. The forest feels completely natural and untouched: enormous centuries-old trees, thick moss, wild ferns, hanging vines, small streams, soft mist, fallen leaves, natural rocks and subtle morning sunlight filtering through the dense canopy. No buildings, roads, modern objects or artificial elements. 0–4 sec: Wide cinematic shot as the woman walks slowly through the misty forest and notices the panda sitting near an old moss-covered tree. The panda looks at her naturally and curiously. 4–8 sec: Medium handheld shot as she gently approaches and sits beside the panda. She smiles naturally and carefully strokes its thick fur. The panda responds playfully, moving closer to her. 8–12 sec: Close-up of the woman's genuine expression and the panda's highly detailed face and fur. Natural breathing, blinking, subtle facial movements, realistic hair movement from the forest breeze. 12–15 sec: Cinematic wide shot as the woman and panda playfully walk deeper into the ancient forest together while sunlight breaks through the trees and mist floats around them. Extremely realistic human anatomy, realistic skin texture, individual hair strands, physically accurate panda fur, natural animal behavior, realistic cloth physics, subtle environmental movement, authentic atmospheric perspective, natural daylight, soft volumetric light, realistic shadows, cinematic depth of field, slight handheld camera movement, documentary-style realism, shot on a high-end cinema camera, 4K detail, natural color grading, no fantasy look, no CGI appearance, no artificial beauty filter, no modern elements, no text, no watermark.

Duration: 15 seconds Aspect Ratio: 16:9 landscape Style: Cinematic Chase Oner, New York Manhattan street, cloudy diffused natural light, cold tone low-saturation documentary film quality. Character: Protagonist I. Narrative Goals The entire video is a continuous horizontal side-tracking long shot. The camera remains parallel to the street, moving left in a shoulder-mounted stabilizer posture, without cutting or changing position. 1. Front: Tracking the running female lead to build speed and tension. 2. Middle: Briefly losing the subject due to foreground obstruction, with hesitant camera movement before locating pursuers. 3. Back: Focus shifts from pursuers to the distant female lead; camera recaptures and accelerates. II. Spatial Layers Foreground: Parked cars, passing yellow taxis, newsstands, construction scaffolding. Subject Layer: Running female lead -> Pursuers -> Female lead. Mid-ground: Outdoor restaurant seating, startled passersby, men in navy suits rushing out of revolving doors. Background: Manhattan main street vanishing point, traffic lights, white steam from vents. III. Executable Camera Timeline - 00:00-00:01.8: Establish Stillness. Slow left pan focusing on an old man at an outdoor table. - 00:01.8-00:02.3: Triggered. Female lead rushes past; camera snaps into a leftward acceleration with realistic shake. - 00:02.3-00:06: Tracking Speed. Medium-close side shot of the lead at full sprint. Background is blurred. Focus on her tense expression and heavy travel bag. - 00:06-00:07.2: Obstruction. A yellow taxi blocks the view; camera loses the subject. - 00:07.2-00:08.3: Hesitation. Camera slows and drifts right to find the subject, eventually locking onto men in suits exiting a building. - 00:08.3-00:11.5: Pursuers. Tracking three men in navy suits running through the crowd. - 00:11.5-00:12.5: Focus Drift. Focus shifts from pursuers to the distant female lead; camera accelerates again. - 00:12.5-00:15: Convergence. Camera tracks the lead entering a dense crowd. She is exhausted. Final shot holds as she disappears into the crowd.

extremely fast-paced, cinematic, bright, photorealistic FPV flight through the ancient Byzantine Empire at its magnificent peak. Begin soaring high above Constantinople at golden sunrise, then dive rapidly toward the colossal Theodosian Walls, skim above bustling streets filled with Byzantine citizens, merchants, soldiers, horses, and colorful market stalls, race between monumental stone buildings and marble columns, sweep through the vast Hippodrome packed with spectators and chariot racers, fly past imperial guards in historically authentic armor, then accelerate toward the magnificent Hagia Sophia with its enormous dome gleaming in sunlight. Continue over grand imperial palaces, churches, courtyards, harbors crowded with wooden Byzantine ships, and the sparkling Bosporus before climbing dramatically above Constantinople to reveal the immense ancient city stretching toward the horizon. Historically authentic Byzantine architecture, clothing, ships, streets, and atmosphere, brilliant natural sunlight, vibrant colors, realistic materials, cinematic lighting, breathtaking scale, dynamic motion blur, extreme speed, immersive FPV perspective, ultra-detailed, photorealistic, visually spectacular, smooth stabilized camera movement. One continuous uninterrupted single-take shot from beginning to end, perfectly fluid movement, no cuts, no transitions, no scene changes, no teleportation, no modern objects, no text, no logos, no fantasy elements

Create a 30-second ultra-realistic selfie video using the reference image for the woman’s identity. Keep her face, skin tone, hair, features, and overall appearance consistent throughout, with zero identity drift or facial distortion. Setting: Luxury mansion living room with marble columns, ornate white ceiling, crystal chandelier, soft grey walls, and an elegant grey sofa behind her. Keep the background and lighting consistent with no scene changes. Camera: Natural smartphone selfie camera, held close to her face with a slight 24–28mm wide-angle look. Subtle handheld micro-sway only. Soft natural indoor daylight, realistic skin texture, shallow depth of field, and documentary-style realism. 0–5s: She looks into the camera, smiles warmly, and says naturally: “Simbaaa... Simba, come here. I’m making a video for Instagram. They wanna see you... good boy.” 5–10s: A large, fully realistic adult male lion slowly walks out from behind the sofa and approaches her right shoulder. He moves calmly with realistic weight, paw placement, fur movement, breathing, and a gently swaying tail. She notices him, turns slightly, and laughs nervously while keeping the phone steady. 10–17s: The lion gently rubs his massive head against her cheek and neck like an affectionate giant house cat. He gives a soft low growl/snort. The contact between his fur and her skin should look physically realistic. 17–23s: The lion affectionately licks her cheek with a realistic tongue. She laughs genuinely and says: “Aww, good boy...” 23–30s: She continues smiling and laughing while the lion stays close, gently nuzzling her. She looks between him and the camera, enjoying the moment. End naturally on the close interaction. Realism: Photorealistic 4K/8K-quality appearance, detailed skin pores, fine facial hairs, realistic eyes and blinking, natural lip-sync, individual lion fur strands, whiskers, detailed eyes, moist nose, realistic tongue and saliva sheen, accurate body weight and contact physics. No cuts, scene changes, flickering, face morphing, identity drift, warped hands, extra limbs, unnatural movement, or camera movement. Keep the woman, lion, environment, lighting, and appearance consistent for the entire 30 seconds. The final video should feel like an authentic spontaneous Instagram selfie.

Main Subject: Young Korean woman, 20, natural everyday appearance, medium-length dark brown hair in a loose half-up style with wispy bangs, realistic skin texture, minimal makeup, slightly sleepy but cheerful personality. Wearing a soft mustard-yellow cardigan over a white cotton blouse, dark navy pleated midi skirt, white ankle socks, brown loafers, and a small canvas shoulder bag. Maintain consistent identity, clothing, hairstyle, and appearance throughout. Location: Quiet traditional neighborhood in Gyeongju on a cool autumn morning. Low tiled-roof houses, stone walls, narrow lanes, small gardens, bicycles, old utility poles, fallen leaves, and a tiny family-owned bakery with a fogged glass window and handwritten Korean signs. No tourists or busy traffic. Visual Style: Ultra-realistic documentary realism. Genuine candid behavior, subtle expressions, natural movement, authentic Korean small-town atmosphere. Camera Style: Early-2000s consumer MiniDV camcorder. Heavy handheld shake, imperfect framing, autofocus hunting between bakery windows and her face, exposure pumping between indoor and outdoor light, faded colors, soft contrast, slight motion blur, DV compression artifacts, mild sensor noise, no stabilization. 00:00–00:03 She walks down the quiet lane carrying her shoulder bag, stepping through fallen leaves. She notices the small bakery and slows down. 00:03–00:06 Inside, she looks through the glass display and chooses a freshly baked red-bean bun. Warm bakery light reflects on the glass while autofocus struggles to find her face. 00:06–00:09 She steps outside, takes a small bite, and smiles while warm steam escapes from the fresh bread. A bicycle passes behind her. 00:09–00:12 She continues toward a nearby stone wall, checking the time on her small wristwatch as morning sunlight reaches the street. 00:12–00:15 She notices the camera, laughs softly, gives a quick little wave, and walks away toward the old neighborhood. The operator accidentally points at the pavement before the recording cuts to black. Audio: Natural ambience only–morning birds, footsteps on leaves, bicycle bell, distant scooter, bakery door chime, quiet conversation, paper bag rustling, soft wind. No music. No narration. Goal: A forgotten MiniDV recording from 2004, capturing an ordinary autumn morning in historic Gyeongju–quiet, nostalgic, imperfect, intimate, and completely believable.

Duration: 15s. Format: 9:16 vertical. Style: Unprocessed iPhone handheld selfie perspective shot in a high-end cigar room. Automatic settings, first-person boyfriend perspective. No artificial lighting or grading. Slight handheld shaking for realism. Single take, no edits. Character: Mature female based on image reference, wearing glasses, black gloves, and high heels. Interaction principles: social distance (1.5-2m), full and upper body shots only, no extreme face-filling close-ups. Environmental details: Warm yellow lighting, cigar cabinets in background with soft golden bokeh. Scripted beats: 0-3s: Senior presents cigar tray, gives a restrained cold smile. 3-6s: Reaction to boyfriend's comment, turning cold and questioning. 6-9s: Suppressed laughter breaking through. 9-11s: Stop laughing when told there's ash on her lip. 11-13s: Self-check by using the camera as a mirror. 13-14s: Freezing for 1 second upon a soft comment. 14-15s: Dangerous narrowing of eyes transitioning back to cold restraint. No subtitles, filters, or background music.

[0-4s]: Extreme close-up of a vibrant red-eyed tree frog sitting motionless on a lush rainforest leaf. Heavy tropical rainfall in the background, out of focus with deep depth of field. Static camera. [4-7s]: A single large water droplet hits the leaf right beside the frog, causing the leaf to bounce smoothly. The frog blinks slowly once and turns its head toward the camera. Audio: Heavy jungle rain ambience, a resonant liquid thud sound effect at 4s when the drop impacts.

30-second ultra-cinematic immersive first-person battlefield flight through a fictional WWII-era battlefield. The viewer experiences the movement directly through an invisible camera viewpoint. The camera itself is completely unseen and physically nonexistent in the image: only the environment and action are visible. Photorealistic, extreme velocity, realistic inertia, wide-angle perspective, seamless continuous movement. 0–4s: Begin high inside smoke above the battlefield. Instantly plunge into a steep vertical dive, rotating 180° as the ground rapidly approaches. Trenches, armored vehicles and ruined buildings rush toward the viewer. 4–8s: Pull out just above muddy terrain at extreme speed. A WWII-era fighter aircraft tears across the sky overhead. Immediately bank hard around wreckage, perform a complete 360° aerial roll, then dive into a narrow trench. 8–12s: Race through the trench at incredible speed, weaving between wooden supports, sandbags and moving soldiers. Burst upward, skim directly over an armored vehicle, then dive underneath its raised chassis and emerge at full speed. 12–17s: Accelerate across cratered terrain. Hard left around wreckage, hard right around a military truck, then climb rapidly toward ruined buildings as another aircraft crosses overhead. 17–22s: Target a shattered second-floor window. Rapidly climb and pass directly through it at full speed, thread through ruined rooms, rotate 90° through a doorway, descend through a stairwell opening and burst through another window into daylight. 22–26s: Dive toward a massive crater, spiral tightly around its interior wall, recover at the last moment and race between two armored vehicles while dust, smoke and debris rush past. 26–30s: Maximum acceleration toward a ruined church tower. Spiral vertically around the tower, complete a fast 360° roll through dense smoke, then burst above the smoke into a gigantic aerial battlefield reveal and continue toward the horizon. The entire sequence is seen exclusively from an invisible first-person cinematic viewpoint. No physical camera equipment is ever visible. No object occupies the foreground as a filming device. The viewer simply experiences impossible aerial movement. Continuous momentum, realistic motion blur, strong environmental parallax, volumetric smoke, dust turbulence, mud particles, sparks, rapid exposure changes and physically coherent transitions. No conventional cuts.

Create a 15-second ultra-photorealistic cinematic action sequence. A young woman is roller skating alone through an extremely dangerous mountain environment. She wears realistic black technical outdoor clothing, protective gloves, helmet, and professional roller skates. Her face, body proportions, clothing, and skating movement remain perfectly consistent throughout the entire video. 0–3 sec: Wide aerial establishing shot of enormous jagged mountains surrounding a tiny, narrow cliffside road. The road is barely wide enough for one person, with a terrifying vertical drop into a deep fog-covered valley. Dark clouds move rapidly between the peaks while strong wind blows across the cliffs. 3–6 sec: Low-angle tracking shot as the woman skates dangerously close to the edge. Small rocks fall from the cliff beside her and disappear into the abyss. Her wheels realistically react to cracks and uneven pavement. She maintains balance while her hair and clothing move naturally in the powerful wind. 6–9 sec: The path suddenly becomes extremely narrow, with a massive rock wall on one side and a huge drop on the other. She passes beneath a giant overhanging rock while loose stones tumble down behind her. The camera moves alongside her, showing the terrifying scale of the environment. 9–12 sec: A dramatic close tracking shot as she approaches a broken section of the mountain road. A large crack runs across the path. She jumps over it while skating, landing realistically on the other side. Dust and tiny rocks scatter naturally from the impact. 12–15 sec: The camera pulls rapidly backward into a huge cinematic wide shot, revealing the woman skating alone along the impossibly dangerous mountain ridge, surrounded by enormous cliffs, distant waterfalls, heavy clouds, mist, and a seemingly endless valley below. Style: documentary-level realism, physically accurate human movement, realistic roller-skating physics, natural facial expressions, authentic skin texture, individual hair strands, detailed fabric, real rock formations, atmospheric perspective, natural sunlight breaking through clouds, volumetric mountain mist, realistic wind and dust, subtle handheld camera movement, cinematic lens, realistic depth of field, natural motion blur, high dynamic range, 4K photorealism, premium live-action cinematography. Negative: CGI appearance, cartoon look, artificial textures, unrealistic physics, floating objects, distorted anatomy, extra fingers, extra limbs, face changes, identity changes, flickering, warped wheels, duplicated objects, oversaturated colors, excessive slow motion, unnatural camera movement.