AI 影片提示詞

電影感 AI 影片生成提示詞——Seedance、MiniMax H3、可靈、海螺、Runway 等模型全覆蓋。

探索配有真實生成片段的 AI 影片提示詞。每條 Prompt 均經過驗證,按模型與風格標註,複製即可用於你的影片生成工具。

A 24-second cinematic 3D animated short film in polished Pixar-style CGI, shot in 16:9 widescreen (2.39-style cinematic composition inside a 16:9 frame), anamorphic-look lenses, shallow depth of field, soft film grain, warm golden-hour sunlight, rich teal-and-gold color grade, smooth natural motion, detailed fur and feather rendering, expressive character acting. The characters and story are completely original. A tiny green anthropomorphic tree frog named FROG escapes from a bald eagle named ZEKE on a sunny rocky beach. No dialogue, no text, no logos, no music; only natural sound effects (waves, wind, footsteps on sand, wing flaps, squawks, splash, comedic impact sounds). FROG: A small, adorable anthropomorphic tree frog with vibrant emerald-green skin, subtle natural bumps and realistic skin texture, a slightly lighter lime-green belly, a small rounded body, two short front arms, strong little hind legs, two large expressive golden-brown eyes with glossy black pupils and raised eye sockets, tiny nostrils and a wide expressive mouth. He has webbed fingers and toes and wears a tiny blue neckerchief tied in a small knot around his neck, his signature look. Innocent, curious and adventurous expressions. No clothes other than his blue neckerchief. ZEKE: A large, powerful bald eagle with a distinctive pure white feathered head, rich dark chocolate-brown feathers covering his body and massive wings, sharp fierce golden-yellow eyes, a strong hooked bright orange-yellow beak with a darker tip, and powerful orange-yellow talons with long curved black claws. Highly detailed individually layered feathers, broad chest, muscular body, strong shoulders and an intimidating majestic appearance. Horizontal widescreen composition, subjects placed on rule-of-thirds with lead room in the direction of movement. Screen direction is fixed: during the beach chase FROG always runs LEFT to RIGHT in side shots and TOWARD camera in front shots. ZEKE always enters from the RIGHT or from above. Only smooth, motivated camera moves (tracking, dolly, crane, push-in). Motion blur only on fast moves. No Dutch angles, no shaky cam, no random angle jumps. Maintain exact character consistency in every shot: FROG always has emerald-green skin, golden-brown eyes, lime-green belly and blue neckerchief. ZEKE always has a white feathered head, dark brown body and wings, yellow eyes, orange-yellow hooked beak and orange-yellow talons with black claws. SHOT 1 (0.0–2.0s): Low-angle tracking shot, camera 10 cm above the sand, 35mm lens, 3/4 front view. FROG sprints toward camera along the beach, positioned on the left third, looking up worriedly at the sky. His tiny webbed feet kick up sand behind him, blue neckerchief fluttering in the wind. Ocean horizon and blue sky fill the wide frame behind him. Camera dollies backward at FROG's speed. SHOT 2 (2.0–3.5s): ZEKE's point-of-view, high-angle aerial shot, 24mm lens, flying forward over the rocky coastline and turquoise water, looking down at the beach. ZEKE's head and hooked beak sit centered at the bottom of the frame, wings spread wide across the full width, wing flaps rhythmic and powerful. The shot ends as a wing sweeps across the lens as a natural wipe. SHOT 3 (3.5–5.0s): Medium side tracking shot at FROG's eye level, 50mm lens. FROG runs LEFT to RIGHT on the sand while the camera tracks alongside him. The camera smoothly cranes up and pulls back into a wide shot as ZEKE's enormous shadow slides across the sand over FROG. FROG glances up in panic and runs faster. Ocean and rocks fill the background. SHOT 4 (5.0–6.0s): Low-angle wide shot looking slightly up, 28mm lens. ZEKE's powerful orange-yellow talons swoop in from the top right, snatch FROG off the sand in a burst of dust, and ZEKE lifts away steeply into the sky with FROG securely clutched in his claws. FROG's blue neckerchief flutters wildly. SHOT 5 (6.0–8.5s): Tight close-up, 85mm lens, eye-level with FROG held securely in ZEKE's orange-yellow claw, ocean softly blurred behind. FROG trembles, his webbed fingers shaking, huge wet golden-brown eyes darting around, then looks up at ZEKE, then looks down at the claw. His expression turns determined; he opens his wide mouth and bites down hard on ZEKE's toe, cheeks tensed and eyes squeezed shut. The toe visibly twitches and the claw jerks. SHOT 6 (8.5–9.5s): Medium-wide low-angle shot from below looking up, 35mm lens. ZEKE flies against the blue sky, screaming in pain with bulging yellow eyes and a wide-open hooked beak, shaking his foot wildly. His talons spring open and FROG drops out of the frame bottom. SHOT 7 (9.5–12.0s): Camera follows the falling FROG from directly beside him, 24mm lens. FROG falls straight down under real gravity, starting slowly then accelerating, body tumbling, arms and legs flailing, blue neckerchief fluttering above him, mouth open in a scream. Clouds streak upward past the frame. The camera then rotates to a top-down view as the blue ocean rushes toward FROG. No floating, no gliding. SHOT 8 (12.0–13.0s): Side view at the waterline, 50mm lens. FROG hits the water in a big splash; cut to a slow-motion underwater view, sunbeams slanting through the water, bubbles rising, FROG sinking with wide golden-brown eyes, centered in frame. SHOT 9 (13.0–15.0s): Underwater medium shot looking slightly up, 35mm lens. FROG kicks and paddles upward toward the bright surface, then bursts out of the water in a spray, gasping, his blue neckerchief dripping wet. Cut to a wide beach shot at knee height, 28mm lens. FROG scrambles up the wet shoreline from the left and shakes off a spray of water droplets, then looks back over his shoulder toward the sky. SHOT 10 (15.0–16.5s): Wide low-angle shot, 24mm lens. ZEKE, recovered and furious, dives back in from the upper right, low over the beach
FORMAT Create a premium Pixar-style 3D animated bathroom comedy using the supplied video as the direct performance reference. Match Video 1's full duration, approximately 14.5 seconds, vertical 9:16 composition, playback speed and original action sequence. Replace only the two characters and make the minor bathroom decor changes specified below. REFERENCE ROLES Video 1: master reference for the complete performance, action timing, facial expressions, body movements, prop handling, spatial composition, camera behavior and audio. Image 1: appearance reference for the replacement woman. Image 2: appearance reference for the replacement man. Transfer the original woman's performance to the woman from Image 1. Transfer the original man's performance to the man from Image 2. The photos control character appearance and clothing only. Do not copy their neutral standing poses, studio backgrounds or full-body framing into the video. PRIORITY Use Image 1 and Image 2 for character identity, hairstyle, colors and clothing. Use Video 1 for all actions, expressions, timing, framing and interaction. Only the bathroom finishes may change as described below. Do not reinterpret the scene or invent additional actions. WOMAN The same beautiful 25-year-old adult woman from Image 1. Preserve her exact face, green eyes, freckles, skin tone and adult proportions. Preserve her pastel-lavender high wavy ponytail, including its volume, length and loose face-framing strands. Preserve her ivory long-sleeve henley, sage-green lounge trousers and cream slippers wherever visible. Do not replace her ponytail with the original woman's dark bun. Her facial expression must follow the video performance, not remain fixed in the reference photo's smile. MAN The same 25-year-old adult man from Image 2. Preserve his exact face, hazel eyes, tousled dark-brown wavy hair, eyebrows, light stubble and adult proportions. Preserve his navy short-sleeve T-shirt, taupe lounge trousers and dark-gray slippers wherever visible. His expression must follow the video performance, not remain fixed in the reference photo's smile. EXACT PERFORMANCE MATCH Use Video 1 as the continuous motion and expression guide from its first frame to its last. Match each character's: - Head position, tilt, turn and forward lean. - Gaze direction, blinks, eyelid movement and eye widening. - Eyebrow movement, mouth opening, lip pursing, smiles and annoyed reactions. - Shoulder movement, arm trajectory, wrist rotation and finger gesture. - Hand-to-face contact and interaction with grooming tools. - Start and end timing of every gesture. - Original brief pauses and reaction delays. Preserve the original timing difference between the woman's actions and the man's imitations. Do not make them move in perfect synchronization unless they do so in the source. The man imitates only at the moments shown in Video 1. At other moments, reproduce his watching behavior and facial reactions. Do not invent continuous mirroring. Preserve the full movement paths, not merely a few key poses. Keep the action flowing naturally between them. Do not add pauses, accelerate gestures, prolong reactions or repeat completed movements. ACTION ANCHORS These anchors identify the source actions, not a replacement timeline. Their timing, order, duration and detailed execution must come directly from Video 1. Opening: The woman applies mascara near her eye with the original wide-eyed, open-mouth expression. The man stands behind her toward screen-right and imitates her using his empty hand. Reproduce the exact moment when she lowers the wand and reacts. Middle: Match her downward glance and displeased expression, his amused reaction and the original transition from mascara to the blue razor. Reproduce her grooming movements around the chin, cheek and upper-lip area. Match how her free hand stretches her cheek and how her mouth changes shape. Preserve the man's original watching expressions throughout. Ending: Reproduce his finger gesture near his own upper lip, her reaction, their final gaze shifts and her reach toward screen-right. End on the same phase of her movement toward the counter as the source. Do not add a new ending, punchline, embrace or final pose. CAMERA AND SPATIAL COMPOSITION Match Video 1's camera position, perspective, framing and near-static composition. Keep the woman in the foreground and the man behind her, offset toward screen-right, with the same relative screen positions and apparent sizes as the source. Preserve visibility of their faces and hands at the same moments as in Video 1. Do not widen to a full-body view because the character photos show full bodies. Preserve the original screen orientation and hand assignments. Do not horizontally flip the scene. Reproduce only the mirror presentation already visible in Video 1. Do not add a new mirror, a reverse angle, an over-the-shoulder view or a second reflected copy of either character. No visible camera or camera operator. Follow the source camera behavior and any source edits. Do not introduce additional cuts, zooms, pans or camera shake. BATHROOM Keep the original room layout and functional geometry: - Vanity counter in the foreground. - Wooden storage toward screen-left. - Window toward screen-right. - The same available space for grooming gestures. - Essential props in positions consistent with the original hand movements. Make only these subtle decorative changes: Muted sage-green wall tiles, pale oak cabinetry and a warm ivory stone countertop. Keep the original arrangement of grooming bottles, dispensers and the toothbrush cup sufficiently similar that every reach and prop interaction remains logical. Do not add objects that obscure faces or interfere with ha
ROLE Senior motion designer, 3D artist and short-form story writer. Build a fully code-animated vertical video for a faceless "choose your own adventure" disaster series. No AI video or image generators. Every frame is rendered from code. GOAL One 40–45s episode, 1080×1920, 30fps. The viewer IS the main character. It ends on a two-option choice viewers answer in the comments. The next part follows the most-commented option. INPUTS (ask me, never guess) - Disaster: [tsunami / earthquake / volcano…] - City + fictional landmark: [Miami Beach, "Marlin Beach"] - Part number + previous choice - The two ending choices: [BOAT / HELICOPTER] - Companion name: [Jay] + 1–2 side characters TECH - three.js in one HTML file, rendered headless with Playwright. - Expose https://t.co/JQhCZuhsmU(t) that sets everything for time t. Seeded random, no requestAnimationFrame state. - For each frame: seek(frame/30), screenshot, encode with ffmpeg (H.264, CRF 18). - Audio at -14 LUFS. ART - Flat toon-shaded 3D, 3-step toon shading, black outlines on characters and props. No realistic textures. - Palette: sky blue to warm horizon, sand, teal ocean with white foam, accent red #d8343a, safety yellow #f2c230. - Low-poly towers, pastel hotels, palms, lifeguard tower. - Chibi characters: big white eyes, thick brows that carry emotion, simple mouth shapes, mitten hands. Companion in a red tee and navy shorts. - Emotion in whole poses, mouths flap on syllables. CAMERA (MOST IMPORTANT) - True first-person POV. Your two arms are always visible from the bottom corners, reaching, grabbing, pointing. - Wide lens, 100° FOV, slight barrel distortion. - Head bob, panic sway, hard shakes on impact, quick whip pans. - Look up (wave, helicopter) and down (water, ladder) a lot. - Cut every 1.2–2.2s. One action and one line per shot. FX - Toon wave with a moving foam lip and speed streaks on impact. - Flooding room, splashes, water spraying from seams. - Underwater: teal fog, caustics, bubbles, floating cars and umbrellas. - Cartoon helicopter, swinging rope ladder, downwash on the water. STORY (every part) 1. 0–2s: start mid-panic. HUD shows place, time, previous choice. 2. 2–12s: the plan works ("It's holding!"), then fails. 3. 12–22s: trapped or underwater. Audio muffles, 0.5s of silence. 4. 22–34s: you surface, a friend calls your name, a new wave, rescue with "One pass!" 5. 34–40s: cliffhanger, cut to black. 6. 40–45s: choice card, 3s+. Lines of 1–4 words, shouted. Say the friend's name twice. Plant one mystery ("Is that really Jay?"). TEXT - HUD top-left: "[LANDMARK] · [TIME]" + "[City] · Part [N]" in yellow. - Red "YOU CHOSE [CHOICE]" badge for the first 3s. - Captions at 72% height, bold, outlined, one color per speaker. END CARD "WHAT WOULD YOU DO?", a blue and a red button with "OR" between, "Comment below ↓", gentle pulse. AUDIO 2–3 shouted TTS voices, panting, wave roar, impacts, hatch clang, underwater heartbeat, helicopter rotor, sirens. Only a tense drone until the end card swell. COVER Companion's shocked face, 2-line Anton title (white + yellow), choice subtitle, red PART pill. DELIVER episode.html, render.js, part[N].mp4, cover.png, caption, a file with both next parts. DAILY Read the top comment, build the next part, post. 4–6 parts per disaster, then a new city.
Approximately 16 seconds, vertical 9:16, polished cinematic 3D animation. Match the reference video's complete duration and original pacing. Preserve its beginning and ending without adding an introduction or extending the final pose. REFERENCE ROLES Video reference: the source for the complete performance, action sequence, timing, emotional progression, camera behavior, framing and audio. Image 1: the new father. Preserve his exact face, green-hazel eyes, wavy auburn hair, fuller reddish-brown beard, body design, sage green knitted sweater, navy trousers and cream sneakers. Image 2: the new toddler daughter. Preserve her exact face, green-hazel eyes, curly auburn pigtails, mustard bows, toddler proportions, mustard corduroy pinafore, ivory blouse, cream tights and brown ankle boots. The images define character appearance, clothing and 3D rendering style only. Do not copy their standing poses, studio backgrounds, portrait composition or studio lighting into the scene. Replace both original characters and their entire outfits with these two referenced characters from the first frame onward. No gradual transformation, blended identities or remnants of the original outfits. ACTION AND PERFORMANCE Follow the video reference throughout, preserving every action in its original order and at its original time. Do not create a new choreography or rearrange the emotional beats. Begin with the new father already holding the new daughter in the equivalent position shown at the start of the video. Keep the father on screen left and the daughter on screen right, matching the reference's orientation and framing. Preserve the original head movements, hand movements, touches, kisses, eye contact, facial reactions, smiles, laughter and final embrace. Preserve the natural pauses and transitions between these actions. Add no extra gestures or repeated kisses. Transfer the reference performance onto the new character designs. Preserve the direction, rhythm, intention and timing of each movement while making only the small spatial adjustments needed for their different facial shapes, hair and beard. For every touch or kiss, preserve the intended contact target from the video. Hands must reach the new character's actual cheek or beard surface. Faces approach, make gentle contact and separate naturally. Do not copy coordinates that cause hands or faces to intersect. The father's fuller beard remains consistent with Image 1. It compresses slightly under the daughter's fingers or against her face and returns naturally after contact. Preserve the daughter's small toddler scale relative to her father. Her individual reference image fills its frame for presentation only; it does not mean she is adult-sized. The father supports the daughter's weight continuously. Keep his supporting arms and hands anatomically connected and consistent with the reference action, including when they are partially outside the frame. EMOTIONS Match the original emotional progression rather than displaying one fixed expression. Reproduce the father's affectionate gaze, smiles, eye closures, emotional reactions and visible tears at the corresponding moments in the reference. Do not introduce tears earlier or exaggerate them into sobbing. Reproduce the daughter's changing expressions, playful attention, affectionate reactions and laughter at their original moments. Preserve who looks at whom and when. Match the final cuddle and the characters' closing expressions to the video reference. Do not replace the ending with a pose toward the camera. LOCATION AND LIGHTING Change the background subtly to a slightly different cozy family living room: warm beige walls, a softly blurred pale oak shelf and a small muted green houseplant. Keep these elements in the background and outside the characters' movement paths. No additional people or background activity. Preserve the video's warm light direction, soft shadows, intimate atmosphere and shallow depth of field. Adapt that lighting to the new characters and clothing. The background remains visually secondary to their faces and interaction. CAMERA AND TIMING Follow the reference video's shot structure, camera height, perspective, framing and camera movements. Preserve any cuts only where they exist in the reference. Keep the intimate framing. Do not widen the shot to display the complete outfits or shoes. Clothing appears only where naturally visible within the original composition. Do not add camera angles, cutaways, transitions, dramatic zooms, slow motion, speed ramps or extra pauses. Preserve the original action rhythm and all contact moments. AUDIO AND LIP SYNC Use the video reference's audio as the exact target for music, words, vocal delivery, pronunciation, pauses and all audible nonverbal sounds. Preserve the original language and exact wording. Do not translate, paraphrase, add dialogue or infer lines from the filename. Preserve the original speaker assignments. Synchronize the new characters' mouth movements and expressions to the corresponding speech, laughter and other vocal sounds at their original timestamps. Preserve the reference music, timing and balance with the voices. Retain sounds only where they are present in the source. Add no new music, narration or sound effects. VISUAL QUALITY AND CONTINUITY Maintain the polished stylized 3D animated-feature appearance of the character images, with expressive eyes, soft skin shading, detailed hair, knitted fabric and corduroy. Keep both identities and outfits stable throughout. Preserve the father's beard shape and the daughter's hairstyle, bows and toddler proportions across all movement. Hair and clothing respond naturally to motion and contact.
Create a 30-second ultra-realistic cinematic cyberpunk action sequence featuring a fierce young female warrior with short electric-blue hair, wearing futuristic red, silver, and black tactical armor. She is running across a wet rooftop in a futuristic neon-lit city at sunset, while several dark, zombie-like enemies chase her. She performs an incredible slow-motion jump across rooftop obstacles, lands gracefully on the wet ground, and immediately engages enemies in an intense martial arts battle using a metal sword. Show powerful kicks, fast sword strikes, realistic combat movements, dynamic dodges, and dramatic enemy takedowns. During the fight, a female enemy wearing futuristic red armor joins the battle. The main heroine jumps into the air, swings her weapon, and defeats multiple attackers. A nearby wooden structure explodes dramatically, sending sparks, smoke, and debris into the air. End with the blue-haired warrior standing confidently on the rooftop, holding her sword while looking toward the glowing futuristic skyline. Visual Style: Photorealistic AAA video game graphics, cinematic cyberpunk atmosphere, neon city lights, wet reflective rooftop, realistic physics, dramatic explosions, volumetric smoke, dynamic camera tracking, slow-motion action shots, detailed character faces, consistent character appearance, 4K, high detail, 9:16 vertical format. Negative Prompt: Cartoon style, blurry frames, distorted faces, extra limbs, unrealistic movements, character inconsistency, floating objects, bad anatomy, watermark, text.
You are my YouTube Shorts editor and motion designer. You turn a game topic and my clips into a 60-second vertical explainer: script, cut list, voice, on-screen graphics, captions, render. Every graphic is built in code. You never generate AI video and never invent game facts. Ask me for: 1. The game and the topic, as a title (e.g. "How the wanted system works in [game]") 2. My clips: gameplay I recorded, or official trailer footage I'm allowed to use. Tell me which files you need if I haven't attached enough 3. My sources for the facts (official posts, trailer moments, patch notes), or permission to research them 4. Length (default 60 s, 1080x1920, 30 fps) 5. Voice: free (Kokoro) or my ElevenLabs key Build a fact sheet: every claim the video makes, where it comes from, and whether it's confirmed, shown in a trailer, or speculation. Anything unconfirmed gets cut or worded as "looks like" / "from the trailer". Never fill a gap with a guess. Write 140-170 words, fast and friendly, like a guide who's already played it: - Line 1 names the system and makes a promise ("the police system in [game] has been completely redone") - Then 4-6 mechanics, each one line of "what it is" and one of "what it means for you" - One "most people will miss this" detail near the end - Last line loops back to the start or teases the next video Show me the script plus the fact sheet and WAIT for my OK. For every line: which clip, in and out timestamps, crop to 9:16 (keep the subject centred, track it if it moves), speed (100% default, 80% for slow-mo moments), and which graphic plays on top. Never use the same 2 seconds of footage twice. Cut every 1.5-3 s, always on a word. Build everything in one HTML file where https://t.co/6do3SVVxsJ(t) draws frame t as a pure function of time, rendered as a transparent overlay: - TITLE CARD (first 2 s): game logo if I give it, otherwise a bold title, plus the topic in white italic caps - HUD ELEMENTS that match what's being explained: a star/level meter that fills and drains, icons that light up one at a time, a minimap with a pulsing search circle, a phone text bubble, a news ticker. Rounded panels, a neon green glow, a thin dark border - CAPTIONS: 2-5 words at a time, heavy italic caps, white with a black outline, the key word in green or red, sitting in the lower third - MOTION: every element springs in (overshoot, then settle), nothing fades slowly, a light camera push on each clip Voiceover on top, a low hype beat ducked under the voice, a whoosh on every cut, a ding when an icon lights up, a siren hit when the stars go red. - Generate the voice first, get word timestamps, and lock every cut, caption and graphic to its word - Cut and crop the clips with ffmpeg, render the overlay frames with Playwright, composite and mix with ffmpeg (H.264, -preset veryfast, CRF 18) Before the full render, show me a contact sheet of 8 frames and WAIT for my OK. Check that captions never cover a face or the HUD, nothing is cropped badly, and every fact on screen is in the fact sheet. The final mp4, a clean version without captions, the script, the fact sheet with sources, and a title, description and 5 hashtags for YouTube.
Ask me for: the accent colour, a song (mp3), the words for the 3 text moments (search query, card title, toast). If I skip any, use the defaults: lime #C6F432, any 120-130 BPM electronic track, "motion study 07" / "Every frame is code" / "Rendered from one file". One black shape (#0e0e10) on a warm light stage (#f4f4f1 to #e1e1dc radial). It never cuts: every UI state is born out of the one before it. White text, Geist for UI, Geist Mono for numbers and labels. The accent appears only where something turns on. A macOS cursor drives every change with real clicks and one real drag. Every morph uses one curve: cubic-bezier(.45,0,.15,1). Pop-ins use a closed-form spring with a tiny overshoot. Text rises through a mask line, it never fades in. The camera zooms per state so each state fills about 60% of the frame, and creeps slowly through every hold. Banned: crossfades, hard cuts, bouncy easing, particles, glows, gradients on UI chrome, holds over 1 second, anything that looks like a template. 120 BPM grid, 24 beats, then the whole film is time-warped onto the real song's beat. Generate pill → click → shrinks into a spinner circle → grows into a toggle → click, the knob springs right and the track turns accent → stretches into a slider → drag the knob from 15 to 85, the number counts → widens into a ⌘K search bar, the query types itself → unfolds into a chart card, 7 bars spring up one per 1/8 beat, the last one in accent → click the accent bar, it pulses → folds into a toast with a check → back into the Generate pill. Last frame = first frame, cursor included. 1. One HTML file, square 1440x1440. Every style is computed from time inside seek(t): no CSS transitions, no timers, no state between frames. 2. The shape is one div. Width, height, radius and colour are keyframe tracks [[t, value]] eased with the one curve. Each state's content is its own layer with its own in / out window inside the shape. 3. Camera: one scale track around the centre, plus a 1.2% sine creep over the whole loop. 4. Cursor: a track of screen positions for the free moves; during the drag its position is computed from the same function that places the knob, scaled by the camera. 5. Beats: analyse the song with numpy (onset envelope, autocorrelation for BPM, align to the kicks, find the drop). Put the drop on the chart bars springing up. 6. Render with Playwright: 60 fps, 4 subframes averaged per frame for motion blur, piped to ffmpeg x264. Then one real SFX per event (click, select, typing, whoosh), placed by its measured peak, quiet under the music, loudnorm to -14 LUFS. - If the cursor follows its own keyframes during the drag, it slides off the knob. Derive both from one function. - Retiming every key to a 129 BPM song breaks the grid. Author at 120 BPM and warp time once: t * (12 / 11.146). - A 300 px pill at zoom 1.7 looks lost in a 1440 frame. Size the zoom per state, about 60% of the width. - A frame-diff pop scan flags the fast morphs. Check each flag by eye: a moving edge is fine, a jumping layer is not. Ask me for the inputs, then show me the state list on the beat grid before you write any code.
TITLE: GTA VI — LUCIA'S NIGHT RUN STYLE: Ultra-realistic AAA open-world video game gameplay inspired by Grand Theft Auto VI. 16:9 landscape, exactly 15 seconds, photorealistic Rockstar-style game-world atmosphere, modern Vice City at night, Florida-inspired Leonida environment, realistic character animation, detailed environmental textures, dynamic lighting, realistic reflections, premium next-generation console graphics. This must look like actual third-person free-roam gameplay, NOT a cinematic movie trailer. CHARACTER LOCK: Lucia Caminos from GTA VI. Preserve her recognizable official character appearance, facial structure, hairstyle, skin tone and body proportions throughout every shot. She wears a fitted casual top, denim shorts and sneakers. Same outfit in every scene. LOCATION: A busy Vice City neighborhood at night. Small American convenience store with glass entrance doors, brightly lit shelves, refrigerators, checkout counter, colorful neon signs, palm trees, parked cars, wet asphalt and a black sport motorcycle parked directly outside the store. SHOT 1 (0:00–0:03) — THIRD-PERSON GAMEPLAY CAMERA. Camera positioned slightly behind Lucia as she enters the convenience store. Automatic glass doors slide open. She walks naturally toward the refrigerated drinks section. Bright fluorescent store lighting contrasts with the neon-lit street outside. A few customers casually move in the background. SHOT 2 (0:03–0:06) — OVER-THE-SHOULDER GAMEPLAY. Lucia opens the refrigerator, takes a cold bottled drink and grabs a packet of chips from a nearby shelf. Close-up of her hand placing both items on the checkout counter. A cashier scans the products. Natural hand movements, believable object interaction, realistic refrigerator lighting. SHOT 3 (0:06–0:08) — MEDIUM FOLLOW SHOT. Lucia completes payment, picks up her small shopping bag and turns toward the entrance. The automatic doors open. Camera smoothly follows her outside. The warm neon signs and colorful Vice City street become visible. SHOT 4 (0:08–0:11) — THIRD-PERSON EXTERIOR GAMEPLAY. Lucia approaches her black sport motorcycle parked beside the sidewalk. She places the shopping bag securely in the motorcycle's storage compartment, takes the handlebars and swings one leg naturally over the seat. Realistic body weight and motorcycle suspension. SHOT 5 (0:11–0:13) — CLOSE SIDE ANGLE. Lucia starts the engine. Headlight switches on, engine vibrates realistically, rear tire moves slightly. She accelerates smoothly away from the sidewalk and enters the street. SHOT 6 (0:13–0:15) — THIRD-PERSON CHASE CAMERA. Camera follows behind the motorcycle as Lucia rides through a neon-lit Vice City street. Palm trees, colorful storefronts, moving traffic, wet road reflections and distant skyscrapers create a believable open-world gameplay atmosphere. End while she continues riding into the city. GAMEPLAY CAMERA: Authentic GTA-style third-person follow camera, smooth player-controlled movement, slight camera lag during acceleration, realistic steering and turning, consistent camera distance, natural vehicle physics. No random cinematic camera cuts. AUDIO: Automatic store door chime, refrigerator hum, footsteps, product packaging rustle, checkout scanner beep, muffled store ambience, motorcycle ignition, realistic engine revving, tire movement and distant city traffic. Subtle Vice City-inspired original background radio music. VISUAL QUALITY: High-detail next-generation open-world graphics, realistic character animation, detailed store interiors, natural facial expressions, accurate hand-object interaction, physically correct motorcycle movement, dynamic shadows, realistic wet asphalt reflections, consistent lighting and environmental continuity. NEGATIVE CONSTRAINTS: No character face changes, no outfit changes, no duplicate Lucia, no extra fingers, no deformed hands, no floating shopping bag, no teleportation, no motorcycle morphing, no disappearing objects, no unnatural walking, no sliding feet, no unrealistic acceleration, no random camera cuts, no cartoon graphics, no fake subtitles, no watermark, no unrelated logos.
# 30秒写实电影质感|神龙政变·长生殿逼宫剧情短片 ## 一、整体基础设定 生成一支30秒、中式古装写实电影质感、原生同步中文对白的历史剧情短片。 画幅为宽银幕20:9,写实电影摄影,24fps观感,轻微细腻35mm胶片颗粒,压低数码锐化。 场景设定武周末年洛阳皇宫长生殿内,深色描金梁柱、厚重暗紫色丝绒帷幔、青铜烛台、古朴地砖。拂晓时分,清冷微弱天光从高处窗棂斜照进大殿,烛火摇曳,空气中浮着淡淡的烟尘。刚刚经历杀伐,殿内气氛紧绷肃杀。 整体画面色调克制沉郁:暗紫、古铜、炭灰、褪色朱红,走正史写实风格。杜绝仙侠特效、浮夸影楼古装、现代物件、商业广告质感。 摒弃舞台剧式夸张表演,冲突依靠神态、呼吸、眼神张力、人物气场推进,是老臣以大势规劝女皇还政,不是粗暴武力咆哮。 ## 二、故事内核&表演基调 核心冲突:神龙政变成功诛杀二张之后,八十岁宰相张柬之带领禁军来到长生殿,当面逼迫已经大权旁落的武则天交出皇权、传位太子。一边是耄耋老臣,隐忍多年、意志坚定;一边是叱咤半生、骤然被夺权,从震惊、强作威严,慢慢认清大势已去。 表演基调:张柬之举止恭敬,语气沉稳坚定,有理有据,不带狂妄;武则天从骤然惊醒的错愕、女皇式的威压质问,一步步转为心力交瘁、万般无奈。情绪轨迹:张柬之:沉稳肃穆→恳切强硬;武则天:惊惶震怒→心存侥幸→无力认命。戏剧重心落在权力交接那一瞬间无声的拉扯。 ## 三、人物一致性 ### 张柬之 80岁东亚老年男性,身形清瘦腰背依旧挺直,面容布满深刻皱纹,花白胡须,眼神沉静锐利,自带饱经世事的沧桑。身穿武周时期宰相绛色朝服,官帽规整,衣料厚重垂顺。 声线:苍老沉稳厚重男声,语速不快,字句清晰有力,态度恭谨却立场绝不动摇。 ### 武则天 78岁东亚老年女性,鬓发花白,脸上布满岁月纹路,身着深紫色寝居便式宫装,刚从睡梦中惊起,发髻微乱,褪去平日全副帝王盛装,依旧残存女皇气场,眼神锐利。保留真实皮肤纹理,拒绝过度美颜。 声线:略带沙哑苍老女声,一开始带着帝王的威严怒意,后面声调缓缓下沉,透出疲惫无力。 全局人物约束 两人全程面孔、年龄、发型、服饰保持不变,禁止面部漂移、五官变形,不模仿影视剧中已知演员长相。 严格遵守180度轴线:张柬之位于画面左侧,武则天位于画面右侧,二人相隔约两米,视线对接,站位固定不互换。 ## 四、分镜头时序模块 【镜头一|0.0‑6.3秒】 85mm人像镜头,张柬之胸部以上近景,三分之二侧脸朝向画面右侧武则天。背景虚化晃动的帷幔与青铜烛台,极浅景深。 摄影机近乎完全固定,只保留极其细微的手持呼吸感,无推拉、环绕、升降运镜。 0.0‑2.9秒:老人身姿挺拔,眉头微敛,花白长须随着微弱呼吸轻微起伏,目光稳稳看向女皇,神色肃穆,没有半分张狂。 表情辅助:AU4眉毛轻压,AU23嘴唇收紧。 2.9‑6.3秒:微微躬身,做出臣子觐见姿态,语气平稳却不容退让。 张柬之声色沉稳: “二张谋反作乱,臣等奉太子之令,已将二人诛杀。” 台词说完立刻硬切,无淡入淡出。 【镜头二|6.3‑17.6秒】 硬切至武则天越肩近景,张柬之朝服肩头作为模糊前景占据画面左下角1/5。武则天处在画面中央偏右,胸部以上构图,背景是被风吹动的丝质帷幔。 摄影机基本固定,仅有几乎察觉不到的轻微呼吸晃动;随着女皇心神动摇,镜头极其缓慢微小向前推进。 6.3‑9.6秒:武则天猛地惊起,眉心骤然紧锁,双眼睁大,胸口急促起伏,睡意全无,带着上位者被冒犯的震怒。 表情辅助:AU5上眼睑抬高,AU4眉心下压。 9.6‑13.2秒:强压下慌乱,努力维持女皇威仪,目光锐利盯住张柬之,声音带着惊魂未定的质问。 武则天语气威严,带着怒气: “是谁在宫外作乱?!” 13.2‑17.6秒:听完叛乱已经平定,眼底闪过一丝震动,肩膀微微垮下,内心开始意识到局势已经失控,眼底泛起水光,但还没有落泪。卡点硬切。 【镜头三|17.6‑24.1秒】 硬切回张柬之近景,焦段、光线、机位与镜头一完全一致。武则天的画外音从画面右侧传来。 17.6‑19.8秒:张柬之眼神没有丝毫躲闪,神情依旧平静,没有被女皇的气势震慑。 20.0‑22.0秒:下颌微微收紧,语气恳切,但立场丝毫不松,摆出无可逆转的现实。 22.0‑24.1秒:微微低头行礼,说出最关键的诉求。 张柬之继续沉稳进言: “太子不可再返回东宫,请陛下传位于太子。” 【镜头四|24.1‑30.0秒】 硬切至武则天面部极近特写,相比前一个镜头机位更加靠近脸部。 24.1‑26.6秒:眉毛内侧向上挤压,眼眶迅速蓄满泪水,一滴泪珠缓缓从苍老脸颊滑落,鼻翼微微颤动,嘴唇无力的轻抖。 26.6‑30.0秒:女皇的眼神彻底失去往日锋芒,头颅微微低下,一股深深的无力席卷全身,声音疲惫沙哑。 武则天语气低沉、心力交瘁: “事已至此……便依你们所言。” 台词结束定格武则天落寞失神的面部0.3秒,短片直接收尾,不做淡出。 ## 五、声音设计 原生生成中文对白,区分两位说话人,口型与每一个音节准确同步。 张柬之人声:苍老厚重男声,情绪轨迹:肃穆冷静→有理有据→坚定规劝。语速平缓,不靠音量压迫,依靠话语本身的分量。 武则天人声:苍老沙哑女声,情绪轨迹:惊醒震怒→强撑威严→大势已去、满心疲惫。 保留真实人声细节:沉重呼吸、气息起伏、苍老的颤音,禁止过度降噪。 环境音:长生殿空旷的回声,远处隐约传来甲胄轻微碰撞声,烛火噼啪微弱声响,大殿安静底噪。 禁止背景音乐、配乐、旁白、夸张戏剧音效。 ## 六、影像限制 禁止字幕、水印、logo以及任何可读文字。 禁止额外第三人、场景中途切换、人物服饰发型发生变化、人脸漂移。 禁止美颜磨皮、仙侠滤镜、夸张大幅度肢体动作、嘶吼尖叫、慢动作、环绕镜头、急速推拉。 禁止目光涣散漂移、口型错位、嘴唇粘连、过度虚假流泪。 整体风格写实历史古装,武周服饰器物符合时代特征,不要唐宋服饰混搭,拒绝CG游戏质感。 ## 七、核心主旨重申 短片重点刻画权力交接最后一刻沉重无声的博弈,依靠微表情、眼神、人物气场烘托紧张氛围,不用花哨运镜,还原八十岁老臣张柬之孤注一掷,逼迫一代女皇武则天还政李唐这一历史性瞬间。
【PROJECT】 MiniMax H3, 15 seconds, 16:9. MIDNIGHT GLASS: photoreal live-action electronic-pop performance. @Audio1 is the timing master. Intimate, mysterious, emotionally exposed. Match actual phrases and pulse, not an invented theatrical climax. Eight shots share one coherent location. 【REFERENCES】 @Image1 supplies the woman's recognizable face, long wavy platinum-blonde hair and proportions. Replace the red dress and original stage. @Audio1 supplies the approved 15-second excerpt unchanged in pitch, speed, vocal and arrangement. Use this actual recording, not a replacement singer or newly composed song. One physical woman; reflections are synchronized optical reflections, never additional performers. 【CREATIVE】 Opening emotional hook: she looks from dark glass directly toward the viewer within the first second, as though finally understood. Vulnerability gradually becomes quiet resolve. Connected route: smoked-glass corridor → luminous doorway → reflective chamber perimeter → central performance light. Reveal adjacent architecture rather than teleporting between unrelated sets. Her face, breath and singing lead the film; effects remain subordinate. 【MUSIC / OUTFIT / PERFORMANCE】 Preserve actual vowels, consonants, breath gaps, sustained notes and instrumental textures. No invented bass drop, silence, shouted high note, lyrics or orchestral stop. Mouth articulation matches the uploaded vocal. No dialogue or additional singers. One midnight-plum satin gown: asymmetric neckline, fitted bodice, defined waist, flowing ankle-length skirt, modest side slit. Small silver drop earrings, discreet stable heels, no necklace. Same gown in every angle. Satin catches soft silver highlights in blue light; hair remains platinum and wavy. No red reference dress or costume changes. Use gaze turn, contact/release, doorway crossing, diagonal walk, pivot, open-forearm gesture and two still points. Every step has grounded weight transfer. Turns originate through shoulders and hips; skirt and hair follow with natural inertia. Controlled emotional singing, not dance choreography. No compulsory tears or exaggerated jaw opening. Preserve natural even skin tone. Face and mouth stay clear. 【VISUAL / TYPE】 Midnight blue, deep plum, black glass, restrained violet haze and silver highlights. Soft side light shapes realistic skin; doorway edges provide depth. Dry polished floor, not water. Readable dark areas, controlled highlights, clean cinematic photography without grain. Elegant condensed uppercase sans, moderate weight, generous tracking. Exact editorial words only: “WITHIN”, “OPEN”, “DEEPER”; not lyric quotations. Each appears whole and readable before moving. Layer A: architectural hero word. Layer B: faint glass reflection. Layer C: small foreground echo. Never obscure eyes or mouth. Methods: glass-edge occlusion, doorway wipe, focus transfer, matched-turn cut, brief text-only reflection offset. Each resolves promptly to clarity. No independent human reflections, face doubles, paper collage, halftone or random glitch. Clean motivated cuts, not soft dissolves. Shot boundaries below may shift slightly to nearby real phrase accents. 【SHOT 1 — 0.0–1.8s】 Close shot, slow lateral track in corridor. Gaze-turn action: begin with her face visible in three-quarter profile, already singing. Eyes turn first, then head, meeting the viewer within one second. Shoulders remain quiet; hair settles after the turn. Reflection follows naturally. The hook is a vulnerable, searching look, not a beauty pose or empty establishing view. Typography “WITHIN”: Layer A silver word behind shoulder; Layer B faint reflection below; Layer C thin echo at extreme left. Keep mouth unobstructed. Rhythm / Cut: reveal on actual opening phrase; passing glass edge motivates the next angle. No fabricated sound accent. 【SHOT 2 — 1.8–3.6s】 Medium side view tracking parallel to corridor wall. Contact/release action: fingertips touch stationary glass, then separate clearly as she shifts weight away. Gaze follows her reflection briefly before returning forward. Feet remain planted during contact; camera shows hand-to-glass separation. Singing continues naturally. Typography “OPEN”: Layer A beyond the glass, fully readable; Layer B dim reflected duplicate; Layer C narrow lower-edge echo. Nothing overlays her lips. Rhythm / Cut: focus transfers from hand to face; cut near an actual syllabic accent. No manufactured drum hit or magic movement through glass. 【SHOT 3 — 3.6–5.5s】 Medium-full view, camera retreats through luminous doorway. Threshold action: two purposeful steps enter the chamber; forearm briefly brushes the solid frame and releases. Body clears the opening normally. Weight transfers through grounded shoes; skirt follows behind and settles. Camera maintains comfortable separation. Typography “DEEPER”: Layer A distant chamber wall; Layer B subdued floor reflection; Layer C small foreground echo briefly hidden by skirt. Rhythm / Cut: doorway edge motivates occlusion cut, with continuous recorded singing. Show architectural continuity and no teleportation. Hair and gown never cross solid surfaces. 【SHOT 4 — 5.5–7.3s】 Wide-to-medium lateral track around chamber perimeter. Diagonal traversal: she walks across a silver light band, turning torso toward camera while feet follow the clear floor route. Show full silhouette and broader satin movement. One hand opens at her side then relaxes. Resolve with a grounded stop. Typography “OPEN”: Layer A far wall; Layer B soft glass reflection; Layer C small vertical edge repeat. Whole word reads before its perspective changes. Rhythm / Cut: movement follows existing pulse wh
Female Character Identity Reference: Image 1 Police Officer Identity Reference: Image 2 Motion and Camera Reference: Video 1 Background Reference: Image 3 Create a 15-second vertical 9:16 video in a realistic handheld smartphone recording style. 1. CHARACTER IDENTITY LOCK Keep the female character 100% identical to Image 1 and the police officer 100% identical to Image 2. Preserve their exact facial features, hairstyles, skin tones, and body characteristics. No identity drift or face swapping. 2. REFERENCE CONTROL - Image 1: Female character identity. - Image 2: Police officer identity. - Video 1: Storyline, actions, expressions, poses, camera angles, movements, editing, and timing. - Image 3: Background and environment. 3. TIMED STORYBOARD 00:00–00:02.5: Officer approaches the woman sitting sideways on a broomstick. Film from inside a car through the side window. 00:02.5–00:05: Woman retrieves an identification card from inside her clothing and physically hands it to the officer. 00:05–00:08: Officer inspects the card and physically returns it to her. 00:08–00:10: Woman stores the card back inside her clothing, turns toward the camera, and gives a confident smile. 00:10–00:12.8: Woman prepares for takeoff, grips the broomstick, and accelerates when the traffic light turns green. 00:12.8–00:15: Woman flies away on the broomstick. Camera pans toward the front-right, following her before ending on the road and intersection. 4. STRICT VISUAL REQUIREMENTS - Maintain perfect character identity consistency. - Reproduce the reference video's camera movements and action sequence. - Show realistic physical interactions and continuous card handovers. - Exactly one identification card throughout. - No clipping, teleportation, duplication, floating objects, or deformed hands. - The broomstick and rider must move together naturally. - No additional scenes or unnecessary camera cuts. - Maintain realistic lighting, expressions, movement, and cinematic continuity. CORE RULE: Character identities from reference images, motion and camera work from reference video, and environment from the background image. Prioritize physical realism and continuity in every frame.
FORMAT 25-second VERTICAL 9:16 cinematic 3D animated comedy in Pixar style. Adapt the supplied reference video's narrative, movements, emotions, reactions, camera work and music using exactly THREE principal characters. Render the entire video in a cohesive Pixar-style animated aesthetic, including characters, escalators, shopping mall, props and living-room fantasy. REFERENCES video1 = source choreography, expressions, emotional progression, camera work, editing rhythm and original music, subject to the three-character adaptation below. image1 = the heavy, balding PS5 shopper on the LEFT escalator. image2 = the woman in the couple on the adjacent escalator. image3 = her male companion. These are the only three character image references. Preserve each image's exact animated face, hairstyle, physique, clothing, footwear, accessories and colors. Use the images for identity and wardrobe, not frozen poses. Transfer the corresponding source performances onto these characters. THREE-CHARACTER ADAPTATION The heavy shopper from image1 is the ONLY featured shopper on the left descending escalator. Remove the source video's second, slim shopper, positioned higher up and behind the heavy shopper on the same left escalator. Remove his PS5 box, shopping bag and separate passage completely. Do not replace him with another person. Remove shots and reactions that depend exclusively on his presence. All of the couple's man's purchase-related attention is directed toward the heavy shopper and HIS PS5 box and shopping bag. Preserve the remaining source story, including the living-room fantasy, appliance-box handover, crossing attempt, interruption, seated landing and final comic payoff. CHARACTERS image1: The heavy, balding shopper. Preserve his exact reference design and body proportions. He carries one PS5 Pro / GTA VI box and one doll-window shopping bag. image2: The woman accompanying image3. Preserve her exact reference appearance and outfit throughout. Transfer the source woman's gestures, attention shifts, reactions and final interaction to her. image3: The woman's male companion. Preserve his exact reference appearance and outfit throughout. He performs the source man's curious looks, temptation, gaming fantasy, distracted reactions, attempted crossing and embarrassed final response. The man in the fantasy is also image3, wearing the SAME outfit. No identity swaps, costume changes or additional principal characters. VISUAL STYLE High-quality Pixar-style 3D animation with expressive eyes, appealing facial shapes, carefully groomed hair, detailed fabrics and cinematic lighting. Match the supplied character images consistently in close-ups, profiles and wide shots. All environments and objects share the same stylized rendering. Use clear facial acting while preserving the source emotions and comic timing. Maintain convincing body weight, natural gestures, balance shifts, grounded feet and subtle secondary motion. The heavy shopper retains his reference physique. Do not slim him down during movement. No rubbery limbs, floating bodies or excessive squash-and-stretch. Normal movement speed. No slow motion, fast-forward or speed ramps. PS5 BOX AND SHOPPING BAG In the real mall scene, the heavy shopper carries exactly: - ONE rigid PS5 Pro retail box. - ONE black “Be happy” shopping bag. The front of the console box clearly displays: - “PS5 Pro” branding. - A white PS5 Pro console product image. - Grand Theft Auto VI cover artwork. - Recognizable “grand theft auto” lettering and the Roman numeral “VI”. The game is GTA VI, meaning GTA 6. Never GTA V. The artwork is physically printed on the packaging. Preserve the prop designs from image1, subject to this explicit branding requirement. The bag has a real oval window cut through its front panel. Inside is the three-dimensional manufactured doll head from image1. The doll's face is recessed behind the panel, visible through the opening. Show cut edges, interior depth, occlusion and shadows. The doll face is NOT printed on the bag. It remains an inanimate object with a fixed expression. No blinking, talking or independent movement. Follow the source heavy shopper's hand assignments and carrying choreography. Hands grip the box and bag handles securely. The box stays rigid. The bag swings subtly with his movement. Do not create a second PS5 box or second shopping bag in the real mall scene. APPLIANCE BOX Preserve the couple's tall green-and-white household-appliance box from video1, rendered in the same animated style. Keep its source carrying positions and visible handover before the man's crossing attempt. This is a household-appliance box, not a PS5 box. During the handover, the woman's receiving grip becomes secure before the man releases it. She continues supporting the box through the final interaction. No floating box, unsupported weight or disappearing prop. ENVIRONMENT A contemporary shopping mall with adjacent escalators moving in opposite directions. In the opening composition: - The heavy shopper occupies the LEFT descending escalator. - The couple rides the adjacent escalator in the opposite direction. Preserve the source escalator slope, central divider, rail positions and spacing required for the action. Maintain coherent screen geography across camera angles. Do not mirror the layout or reverse the escalators. Slightly refresh decorative details: Pale stone finishes, revised ceiling fixtures, different plant pots and subtle changes to distant storefronts. Do not alter structural elements needed for the blocking. Keep the architecture and decorations consistent between shots. Render glass, polished metal, rubber handrails and moving steps in the same Pixar-style aesthetic. Use warm indoor lightin
SCENE: Create a gritty, photorealistic military action sequence among concrete ruins, with explosions, smoke, flying debris, and heavy incoming fire. Use a cinematic 35mm film look with Teal & Orange color grading. REFERENCE INSTRUCTIONS: - Video 1: Follow the exact shots, camera angles, movements, timing, and action sequence. - Image 1: Preserve the squad leader's exact identity. - Image 2: Use as the exclusive uniform reference (Desert Digital Camo + FAST helmets). - Image 3: Preserve the female operator's exact identity. ACTION SEQUENCE: 1. Overhead dive revealing four operators taking cover. 2. Medium shot showing the leader coordinating with his teammate. 3. Leader close-up with cinematic firing effects. 4. Low-angle action with one realistic grenade throw and explosion. 5. Female operator coordinating with her teammate and taking position. 6. Wide cinematic squad push with all four operators moving forward. IMPORTANT CONSISTENCY RULES: - Exactly four friendly operators throughout. - No face swapping, identity drift, or duplicate characters. - Keep friendly and enemy uniforms visually distinct. - Maintain consistent equipment, positions, and body proportions. - Follow all six shots in the exact order. - Realistic physics, smooth transitions, and no continuity errors. - No graphic injuries or unnecessary extra actions. AUDIO: Include cinematic battlefield dialogue: "CONTACT! GET DOWN!" "TWO ENEMIES ON FLANK!" "COVER ME! NADE NOW!" "FIRING! GO GO GO!" "SUPPRESSING! FLANK CLEAR!" "PUSH FORWARD!"
Create a heartwarming 30-second cinematic 3D animated short film featuring a cute little boy with messy dark brown hair, big expressive eyes, and a bright yellow raincoat, accompanied by a small fluffy white cloud with adorable expressive eyes. Scene 1 – A Magical Encounter: A cheerful little boy walks along a beautiful suburban neighborhood street on a sunny afternoon. A tiny fluffy white cloud appears above him, curiously following him. The boy notices the cloud and looks surprised. Scene 2 – Unexpected Rain: The little cloud begins following the boy closely. He opens a colorful rainbow umbrella to protect himself and the cloud. Show adorable facial expressions and playful interaction between them. Scene 3 – A Sweet Friendship: The boy walks through a cozy neighborhood with the little cloud beside him. They pass a small outdoor café where people notice the unusual friendship. The cloud looks shy and adorable. Scene 4 – Helping Nature: The boy takes his little cloud friend to a beautiful backyard garden filled with colorful flowers and freshly planted soil. The cloud gently releases refreshing raindrops, watering the plants. The flowers begin blooming beautifully. Scene 5 – Heartwarming Ending: The boy smiles with excitement as the cloud becomes happy. They stand together in the colorful garden, surrounded by blooming flowers and warm golden sunlight. End with a beautiful cinematic wide shot of their friendship. Visual Style: High-end Pixar-inspired 3D animation, adorable character design, expressive eyes, fluffy cloud textures, cinematic lighting, warm pastel colors, detailed suburban environment, realistic soft shadows, smooth character animation, emotional storytelling, beautiful depth of field. Camera: Cinematic tracking shots, expressive close-ups, medium shots, and wide establishing shots. Consistency: Maintain identical character appearance, clothing, cloud design, environment, and animation style throughout all scenes. Format: 16:9 widescreen, 4K quality, 30 seconds, polished professional animated short film.
Create a cinematic, dark fantasy fashion film in vertical 9:16 format, featuring a mysterious woman in a flowing crimson-red gown. Scene 1: A mysterious hooded woman slowly extends her hand toward the camera, holding glowing red magical dice. Dramatic close-up, mysterious expression, dark atmosphere, glowing particles and cinematic lighting. Scene 2: Transition into a magnificent gothic palace with a grand black-and-white chessboard floor. A powerful queen stands in an elaborate black outfit, surrounded by ornate chandeliers, dramatic architecture and symmetrical compositions. Scene 3: A woman wearing a flowing red silk gown dances across a vast, dark rocky landscape under a stormy sky. Her dress moves dramatically in the wind. Scene 4: Aerial shot of a woman in a red dress surrounded by powerful ocean waves, creating a circular white-water pattern around her. Smooth cinematic drone movement. Scene 5: A mysterious woman in red stands alone among endless rows of dark hooded figures. Slow camera movement, symmetrical composition, surreal atmosphere and dramatic contrast. Scene 6: A surreal fashion sequence featuring the woman spinning inside enormous circular architectural structures, followed by a dramatic red-dress pose against an abstract black-and-white painted backdrop. Final Scene: A woman in a flowing crimson gown walks toward a breathtaking golden sunset through elegant white curtains above the clouds. Ethereal atmosphere, cinematic wide shot and graceful movement. Visual Style: Ultra-realistic 4K, high-fashion editorial photography, dark fantasy aesthetics, rich crimson-red color palette, dramatic lighting, realistic fabric physics, atmospheric depth, smooth transitions, elegant slow motion, sophisticated cinematic camera movements. Consistency: Maintain the same female character, facial features, hairstyle and red gown throughout all scenes.
Create a 15-second ultra-photorealistic cinematic short film set on a beautiful narrow Seoul neighbourhood street during a gentle autumn rain at night. MAIN CHARACTER: The same 24-year-old Korean woman throughout the entire video, with a naturally beautiful face, long loose dark hair, minimal makeup, oversized maroon hoodie, loose dark casual pants and a knitted scarf. Maintain identical facial identity, hairstyle, clothing and body proportions in every shot. She carries a transparent umbrella. ENVIRONMENT: Authentic Seoul residential neighbourhood, small illuminated convenience stores, Korean shop signs softly blurred in the background, wet asphalt reflecting warm amber and subtle neon lights, gentle rainfall, atmospheric evening mist. Realistic live-action cinematography, natural human expressions, physically accurate movement and detailed environmental textures. SHOT 1 — 00:00–00:04: A beautiful cinematic wide shot of the woman walking slowly along the rainy Seoul street. Camera smoothly tracks backwards in front of her at walking speed. She holds her transparent umbrella and looks around peacefully. Rain droplets collect on the umbrella. Colourful shop lights reflect across the wet pavement. A tiny golden-brown puppy is visible sheltering beneath a small shop awning in the background. SHOT 2 — 00:04–00:07: Medium close-up as the woman notices the puppy. She slows down, turns her head and looks towards it. Her expression changes into a gentle, spontaneous smile. Camera subtly pushes closer towards her face. Natural eye movement and realistic facial expressions. SHOT 3 — 00:07–00:11: Low-angle intimate cinematic shot. She gently kneels beside the puppy and moves her transparent umbrella over it, protecting it from the rain. The puppy looks up at her, slowly wags its tail and approaches her hand. She gently strokes its head. Detailed realistic fur, natural animal behaviour and delicate rain droplets. SHOT 4 — 00:11–00:15: The puppy happily follows her as she begins walking again. She looks down at it with a warm smile. Camera smoothly pulls backwards into a beautiful wide cinematic composition. The two walk together beneath the same transparent umbrella, surrounded by warm shop lights and softly falling rain. Finish with a visually beautiful, emotionally satisfying shot. CAMERA AND VISUAL QUALITY: Premium independent-film cinematography, authentic early-2000s Sony MiniDV-inspired texture, subtle organic film grain, realistic skin texture, shallow depth of field, natural motion blur, smooth continuous camera movement, beautiful warm-versus-cool colour contrast. Preserve character identity and environmental continuity across all shots. AUDIO: Realistic gentle rainfall, distant passing traffic, soft footsteps on wet pavement, subtle puppy whimper and paw sounds. Natural environmental audio only. No dialogue, no narration, no artificial music. STRICT CONSTRAINTS: No face changes, no wardrobe changes, no extra limbs, no distorted hands, no duplicated puppy, no unnatural animal movement, no sudden camera jumps, no flickering, no frame skipping, no subtitles, no captions, no watermarks, no logos. 16:9 landscape, 15 seconds, ultra-photorealistic live-action appearance.
ROLE You are a senior motion designer, map illustrator, gaming researcher and documentary scriptwriter. You build fully code-animated "map tour" explainer videos for a faceless GTA 6 channel. Every frame is rendered from code you write. No AI video generators, no re-uploaded trailer footage, no Rockstar logos, artwork or characters. GOAL Produce one finished map-tour video: 80–90 seconds, 1920×1080, 30fps (plus an optional 1080×1920 vertical cut). A getaway car drives a route across your own illustrated map of Leonida, stopping at each location on a topic list. Every stop gets a highway-sign title, a "case file" card with an illustration, three facts, a source line and an honesty stamp. It ends on a question that drives comments. INPUTS (ask me for anything missing, never guess) - Topic: [e.g. "Every heist spot we've seen in GTA 6" / "Every animal and where to find it" / "Every region and its real-world match"] - My voiceover file (ElevenLabs), or ask me to approve a script first - Channel handle, and the end-card question - Output format: landscape, vertical, or both STEP 1: RESEARCH (accuracy is the brand) - Search the web for every location on the topic. Use only official Rockstar material (trailers, the Extended Look, official screenshots, the Newswire, store listings) and reputable hands-on previews (IGN, Game Informer, Edge, GamesRadar). - For each item, record: what it is, where it is (only if actually shown), the source and its date, and a status: CONFIRMED (Rockstar showed it), SHOWN (seen in a preview or demo), REPORTED (press only) or MAYBE (a single outlet). - If the location isn't shown, the item gets a "LOCATION NOT SHOWN" tag. Never place a pin somewhere that's only a guess. If you approximate, label it "approx. position". - Save everything to research.md with links. Show me the list before writing the script. STEP 2: SCRIPT (documentary tone, about 2.6 words per second) 1. Hook (0–9 s): "Let's go through every [topic] we've seen in GTA 6, before it finally comes out." 2. Sources (9–14 s): name where the info comes from, and promise to flag anything unconfirmed. 3. Stops: one per item, 6–9 seconds each. "Stop one: [name]." → one vivid detail → one practical line or payout note. Say the status out loud when it's weak ("Only one outlet has reported this one, so treat it as a maybe."). 4. The big one: save the most exciting item for last, 12–16 seconds. 5. Twist: a broad truth that zooms out ("You can rob pretty much anything"). 6. Question: "Which one are you [doing] first?" Write in plain words. No hype words, no "smash that like button". STEP 3: THE MAP (build once, reuse in every video) - Build it in code: a stylized Florida-shaped peninsula from your own polygon (about 30 control points with seeded noise wobble so the coast looks hand-drawn), plus a chain of 20+ small islands for the Keys curving southwest, a thin barrier-island strip for Vice Beach, a big lake in the middle and a river running south from it. - Prerender it once to an offscreen canvas at 3 px per map unit, then draw it every frame with a camera transform (pan and zoom). Never redraw the geography per frame. - Look: - Ocean: radial gradient #2f8fe0 → #1553a6, with faint moving wave strokes at 6% opacity. - Shallow water: a cyan glow around every coast (#5fd0ee, 60 px blur). - Coast: a pale sand rim (#f3e6a8). - Land: #cfe07a, with 150+ soft patches of lighter and darker green. - Wetlands: #9fcf74 with short horizontal marsh strokes. - National park: #8fbf62. - City: a light grey area (#e9e9ee) with a fine street grid. - Roads and highways: cream lines. - Region labels in heavy rounded sans (Montserrat 900), white with a soft navy outline, each with its real-world match underneath, e.g. "VICE CITY / (MIAMI)". Use only region names Rockstar has published. STEP 4: ANIMATION LANGUAGE - Camera: open wide on the whole state (zoom so the full map fits), then glide down to the first stop. Each new stop is a smooth 1–2 s ease-in-out pan and zoom. Pull back to the full state for the twist. - Getaway car: a top-down red car icon (body, lighter roof, dark windows, headlights) that follows the route polyline by distance and rotates along the road direction. It eases between stops and pauses at each one. - Route line: the full route as a faint dashed pink line; the travelled part as a solid hot-pink line (#ff2e7e) with a soft glow. - Pins: a teardrop pin that drops in with a back-ease bounce and a pulsing ring. Yellow with "?" plus a "LOCATION NOT SHOWN" tag for unknown spots; pink with "$" plus a location tag for known ones. - Highway sign (top left): a green road sign (#0d7a3f) with a white inner border, a number shield, "STOP 1 OF 6", and the title in a heavy highway-style font (Overpass 900). A handwritten note card under it in a marker font (Permanent Marker) with a 3–5 word quote from the script. - Case file card (right side): an off-white paper card sliding in from the right with a sl
TITLE: THE LAST WITNESS STYLE: Ultra-photorealistic, high-budget Hollywood crime mystery thriller, 16:9 widescreen, 15 seconds, anamorphic cinema lens, dark blue-grey color grade, dramatic practical lighting, heavy rain, atmospheric fog, realistic reflections, subtle film grain, deep shadows, cinematic contrast, natural motion blur. Premium theatrical movie cinematography. No subtitles, no captions, no watermark. CHARACTER LOCK: Detective Daniel, a 38-year-old man with short wet dark hair, light stubble, sharp tired eyes, wearing a black tailored trench coat over a charcoal shirt. Maintain exactly the same face, hairstyle, clothing and proportions in every shot. LOCATION: Abandoned underground parking garage at midnight, wet concrete floor, flickering fluorescent lights, parked black sedan, distant city lights visible through the entrance. A mysterious evidence envelope lies on the car hood. SHOT-BY-SHOT: SHOT 1 (0:00–0:02): EXTREME WIDE ESTABLISHING SHOT. Camera slowly descends into a deserted underground parking garage. Heavy rainwater drips from the ceiling. Detective Daniel walks alone toward a black sedan. Slow cinematic dolly movement, deep atmospheric tension. SHOT 2 (0:02–0:04): LOW-ANGLE TRACKING SHOT. His polished black shoes step through a shallow puddle. Camera tracks backward as he approaches the car. Water ripples naturally with each step. A distant metallic bang echoes. SHOT 3 (0:04–0:06): TIGHT CLOSE-UP. Daniel notices a sealed evidence envelope on the hood. His hand slowly reaches toward it. Camera pushes in toward his eyes, capturing a subtle expression of suspicion. Fluorescent light flickers once. SHOT 4 (0:06–0:09): MACRO INSERT TO OVER-THE-SHOULDER. He opens the envelope and pulls out a photograph. The photograph clearly shows Daniel himself standing beside the same black car, photographed from behind only moments earlier. His fingers freeze. A slow camera push reveals the photograph. SHOT 5 (0:09–0:12): EXTREME CLOSE-UP. Daniel slowly raises his eyes toward the dark reflection in the car window. In the reflection, a mysterious human silhouette stands directly behind him. The silhouette must remain physically grounded and visible only in the glass reflection. Daniel's breathing becomes audible. SHOT 6 (0:12–0:15): FAST WHIP-PAN TO REVEAL. Daniel turns sharply. The space behind him is completely empty. Camera rapidly pushes toward his shocked face. In the final half-second, a second handprint suddenly appears on the fogged car window beside his reflection. CUT TO BLACK. CAMERA: Smooth controlled dolly, low tracking shots, macro detail, shallow depth of field, realistic handheld movement only during the reveal, cinematic rack focus, natural motion blur, consistent screen direction. AUDIO: Heavy rain ambience throughout, echoing footsteps, distant metallic impact, envelope paper rustle, low sub-bass suspense drone, heartbeat-like percussion during the reflection reveal, sharp cinematic sting at the final handprint, abrupt silence on cut to black. REALISM: Physically accurate rain, water reflections, hand movements, paper interaction, believable facial micro-expressions, consistent character identity, realistic glass reflections and lighting continuity. Every shot must connect naturally as one continuous cinematic sequence. NEGATIVE CONSTRAINTS: No face changes, no duplicate characters, no extra fingers, no deformed hands, no floating objects, no cartoon look, no CGI-looking skin, no artificial camera teleportation, no random scene changes, no flickering faces, no inconsistent clothing, no unreadable generated text, no subtitles, no logos, no watermark.
# MiniMax H3 中文提示词|25秒,《狂飙》高启强&安欣经典对峙对话,中文对白,16:9,24fps,2K output_spec: 画幅16:9,时长25秒,24fps,2K,写实电视剧电影质感,低对比暗调,轻微胶片颗粒,无字幕,无水印,无画面文字,人物面部稳定,动作连贯,压抑拉扯氛围。 integrated_multimodal_description: 室内茶室,深色实木茶桌,一盏暖黄台灯,背景昏暗留白,京海氛围感。高启强身着深色西装,沉稳内敛,眼神复杂;安欣穿黑色便服,脊背挺直,目光坚定。两人隔着茶桌对峙,克制的心理博弈,暗流涌动。 人物设定: 高启强:中年男人,沉稳,眼底藏沧桑,语气从容带试探; 安欣:中年刑警,头发花白,神情执拗,冷静克制,坚守底线。 [Shot 1] 00:00-00:05 景别:双人中景 运镜:固定机位,极慢向前推镜 画面:两人隔着茶桌相对而坐,台灯只照亮上半身,一半脸在阴影里,高启强指尖轻叩茶盏 台词(高启强,平缓):安欣,要是当初我还是卖鱼的,你会把我当朋友吗? [Shot 2] 00:05-00:11 景别:安欣近景 运镜:硬切,定镜 画面:安欣盯着高启强,眉头微收,神色沉重 台词(安欣,冷静):哪有那么多如果,路都是自己选的。 [Shot 3] 00:11-00:17 景别:高启强近景 运镜:硬切,缓慢push in 画面:高启强低头轻笑,抬眼看向安欣,眼神怅然 台词(高启强,低声):我做好人时,坏人欺负我;做坏人,好人又审判我。 [Shot 4] 00:17-00:21 景别:双人近景 运镜:硬切,轻微横向摇镜 画面:安欣身体微微前倾,目光锐利,直面高启强 台词(安欣,语气坚定):黑白有界,法理不会模糊。 [Shot 5] 00:21-00:25 景别:双人特写同框 运镜:镜头zoom in,定格在两人对视的面部 画面:沉默对视,台灯光影在脸上晃动,张力拉满 台词(高启强,轻声):你还是没变。 overall_soundscape: 安静茶室环境底噪,茶盏轻微磕碰声,布料摩擦声,呼吸声,音效克制不抢人声 non_diegetic_music: 低沉压抑的悬疑弦乐,音量压低,留白多,对白间隙缓慢烘托情绪
# MiniMax H3 中文提示词|25秒,《大话西游》经典“爱你一万年”片段,中文对白,16:9,24fps,2K output_spec: 画幅16:9,时长25秒,24fps,2K,电影画面质感,无字幕,无水印,无画面文字,人物面部稳定,五官清晰自然,动作连贯,镜头节奏克制。 integrated_multimodal_description: 《大话西游之大圣娶亲》经典喜剧电影质感,荒凉山寨石洞内部,石壁粗粝,烛火摇晃,低饱和复古色彩,轻微胶片颗粒,苍凉又深情的氛围。紫霞仙子执剑与至尊宝近距离对峙,画面中只有紫霞仙子、至尊宝、长剑、火把与石壁背景。 人物设定: 紫霞仙子:年轻女子,古装女侠造型,眼神倔强又带伤感,手持长剑,剑身横在至尊宝面前,情绪从戒备、嘲讽逐渐转为震撼与含泪。 至尊宝:年轻男子,略带不羁的古装造型,头发微乱,表情从无奈转为认真、悲怆,最后深情告白。 [Shot 1] 00:00-00:05 景别:中近景双人同框。 运镜:固定机位,轻微手持呼吸感。 画面:紫霞仙子持剑横在至尊宝颈前,两人站在石洞中央,烛火从侧后方照亮人物轮廓。紫霞盯着至尊宝,剑尖停在他胸前,动作克制。 台词(紫霞,冷声带笑):“你以为我不敢杀你?” [Shot 2] 00:05-00:11 景别:至尊宝近景。 运镜:硬切,镜头缓慢push in。 画面:至尊宝看着紫霞,表情由吊儿郎当变得认真,眼眶微红,背景烛火虚化成暖光斑。 台词(至尊宝,语气郑重):“曾经有一份真诚的爱情放在我面前,我没有珍惜。” [Shot 3] 00:11-00:17 景别:双人中近景。 运镜:硬切,轻微缓慢推镜。 画面:紫霞握剑的手微微发紧,至尊宝站在她面前,没有后退,两人目光牢牢相接,石洞内火光轻晃。 台词(至尊宝,声音低沉):“等我失去的时候,我才后悔莫及。” [Shot 4] 00:17-00:21 景别:紫霞特写。 运镜:硬切,定镜。 画面:紫霞眼神动摇,剑尖缓缓下垂,嘴唇轻颤,眼底泛起泪光,原本的倔强被击中。 台词(至尊宝,画外音):“人世间最痛苦的事,莫过于此。” [Shot 5] 00:21-00:25 景别:双人近景。 运镜:镜头极慢zoom in,收束在两人对视。 画面:至尊宝看着紫霞,紫霞的剑已经放下,两人之间空气安静,烛火映在脸上,画面深情定格。 台词(至尊宝,轻声):“如果非要加一个期限,我希望是——一万年。” overall_soundscape: 石洞空旷风声,火把燃烧声,长剑轻微金属声,衣料摩擦声,人物呼吸声,环境底噪自然,不盖对白。 non_diegetic_music: 低沉忧伤的二胡与箫声,旋律缓慢苍凉,音量低,只在对白空隙增强情绪,不抢人声。
【PROJECT】 MiniMax H3, 15 seconds, 16:9. MIDNIGHT GLASS PART 2: photoreal live-action rock-stage performance. Epic concert lighting, emotionally intense singing and bold layered typography. Audio is the master clock. Eight shots in one stage; no unrelated scene changes. 【REFERENCES】 @Image1 supplies the rock stage, leather outfit, red lipstick, smoky eyeliner, microphone and two guitarists. @Image2 locks the lead woman's recognizable face, facial proportions, hairline and platinum-blonde waves only, not its red dress. @Audio1 is the approved first 15 seconds of audio2. Preserve recorded voice, instruments, pitch, tempo and phrasing; no replacement singer or music. 【CREATIVE】 Opening hook: immediate emotional eye contact and enormous stage lettering. Vulnerability grows into grounded rock power with the actual recording. Connected zones: microphone position, front apron, side-monitor lane and central spotlight. Exactly one lead singer plus two guitarists behind her, left and right. Preserve stage geography. 【MUSIC / FACE / OUTFIT】 Face identity has priority: preserve @Image2's recognizable face at every angle, natural skin texture and even complexion. Long platinum waves, red lipstick and smoky eyeliner remain consistent. No beautification that changes identity. Same fitted black leather biker jacket, secure black stage top, high-waisted leather trousers, silver hardware and earrings throughout. One wired handheld mic stays in her right hand. Left hand gestures freely. Cable follows gravity and a safe floor route. Mouth shapes match actual recorded syllables and breath gaps. Sustained notes have natural jaw movement and held posture. No invented screaming or lyrics. Retain recorded backing vocals without adding visible singers. Gaze lift, stance shift, diagonal walk, shoulder turn, arm release and two still points provide varied performance. Grounded steps, coherent joints, jacket and hair inertia. Fan airflow keeps hair clear of mouth. Guitarists play with plausible hands and attached straps. 【VISUAL / TYPOGRAPHY】 Rear LED wall, truss, amplifiers, speaker cabinets, pedalboards, wedge monitors, cables and unoccupied drum kit. Blue-violet beams, crimson rear accents, soft white face key and restrained haze. Realistic leather, skin and metal, controlled exposure, no grain. Typography is a PRIMARY element, not subtle decoration. Ultra-black condensed uppercase grotesk, tight tracking, ivory hero letters with silver/crimson echoes. Exact phrases: “I'VE BECOME SO NUMB” “WITHOUT A SOUL” “FIND IT THERE” “LEAD BACK HOME” Last two are editorial phrases, not compulsory sung lyrics. Never alter recorded vocal to match text. Layer A: huge complete rear-screen phrase in readable lines. Layer B: smaller silver side-screen echo. Layer C: lower-foreground word fragment. Keep mouth and eyes clear. Full words hold before transforming. Use text-only offsets, light sweeps, split panels and clean cuts. Restore clear text and one sharp singer. No karaoke strips or gibberish. Times can shift slightly to actual vocal accents. 【SHOT 1 — 0.0–1.8s】 Close-up at mic, slow push. She sings and raises gaze into direct eye contact within first second, left hand near sternum. Face immediately recognizable. Typography “I'VE BECOME SO NUMB”: Layer A full huge phrase beside silhouette; Layer B silver side echo; Layer C NUMB low edge. Rhythm / Cut: opening vocal reveals complete wording, then gaze motivates clean cut. No haze obscuring text. 【SHOT 2 — 1.8–3.6s】 Medium apron shot, lateral track. Strong planted stance, shoulders open, left arm extends once, right mic steady. Hair follows airflow; guitarists stay behind. Typography same phrase: Layer A full rear words; Layer B text-only offset; Layer C NUMB below waist. Rhythm / Cut: real phrase emphasis aligns letters. Restore offsets promptly, lips remain clear. 【SHOT 3 — 3.6–5.5s】 Medium-full diagonal track beside monitors. Two purposeful steps toward central light, safe feet and natural cable slack. Jacket follows torso; no equipment intersection. Typography “WITHOUT A SOUL”: Layer A rear phrase; Layer B narrow side echo; Layer C SOUL foreground. Rhythm / Cut: actual rise activates crimson accent. Monitor edge motivates cut, no invented drop or hidden mouth. 【SHOT 4 — 5.5–7.3s】 Wide stage shot, restrained arc. Singer reaches center, opens left arm, mic stays right. Both guitarists and stage equipment visible. End planted. Typography “WITHOUT A SOUL”: Layer A immense full phrase; Layer B side panels; Layer C low SOUL. Rhythm / Cut: actual musical accent widens beams and aligns type. Stable stage, no strobe barrage. 【SHOT 5 — 7.3–9.1s】 Intimate close-up, nearly locked. First still point: concentrated singing, natural breath, searching gaze. Face exactly follows identity reference; mic does not hide lips. Typography “FIND IT THERE”: Layer A full phrase beside face; Layer B faint silver repeat; Layer C THERE bottom edge. Rhythm / Cut: light sweep reveals then holds words. Editorial text does not change lip-sync. No forced tears. 【SHOT 6 — 9.1–11.0s】 Medium-full near monitor, low undistorted view. Shoulder-led quarter turn then grounded return front. Left hand briefly contacts existing stand and releases, right hand keeps mic. Hair, jacket and cable settle. Typography “FIND IT THERE”: Layer A rear phrase; Layer B registration echo; Layer C THERE exits sideways. Rhythm / Cut: actual phrase resolves turn. Brief guitar-detail split panel returns to one stage view, no body duplication. 【SHOT 7 — 11.0–13.0s】 Medium track toward front light. One deliberate step, chin lift and left-arm release wi
Create a 17-second vertical 9:16 video at 24fps in cinematic 4K photorealism. Reproduce the exact comedic sequence, actions, timing, character positions, and countertop layout from Video 1. Use one continuous, locked-off shot with absolutely no camera movement, zoom, or cuts. CRITICAL OBJECT CONTINUITY: There must be EXACTLY ONE cup throughout the entire video. It must remain the same physical object with identical appearance, shape, and size. The cup can only move through visible, continuous hand contact. Show every pickup, movement, placement, and release. Never duplicate, teleport, slide, or make it disappear. The coffee jar and spoon must also remain single, persistent objects. ACTION SEQUENCE: 0–5 SECONDS | FIRST MIX-UP Character A (Image 1) looks exclusively at the coffee jar and spoon while scooping dry coffee powder. At the same time, Character B (Image 2) picks up the ONLY cup, carries it to their side, pours hot water, and places it down. Unaware of this movement, A pours coffee powder toward the cup's original position, spilling it onto the countertop. 5–10 SECONDS | SECOND MIX-UP A continues looking only at the coffee jar and spoon. B picks up the SAME cup, physically carries it back to A's original position, and places it down. A mistakenly pours coffee powder toward the cup's previous position, spilling it onto the countertop again. 10–17 SECONDS | FINAL PUNCHLINE The countertop must be completely clean and dry in the area where milk will land. A physically picks up the SAME cup. At that exact moment, B starts tilting the milk container toward the cup's original position. Milk must visibly exit the container as a continuous stream. Since A has lifted the cup, the milk lands directly on the countertop and progressively forms a natural spill. The instant A notices the milk spilling, A reacts with unmistakable shock: a sudden upper-body jerk, brief wobble, wide-eyed astonishment, and a genuinely funny, disbelieving expression. B looks at the spilled milk with a helpless, awkward, mildly frustrated expression. STRICT GAZE CONTROL: During both coffee-scooping sequences, A must continuously keep their head lowered toward the coffee jar. A's eyes must remain fixed on the jar and spoon. The head and gaze must NEVER follow the spoon toward the cup or look at B. Only A's arm and hand may move toward the expected cup position. CHARACTER BEHAVIOR: Both characters remain unaware of each other's actions throughout the three accidental mix-ups. All hand movements and object interactions must be anatomically correct, physically realistic, and continuous. COFFEE POWDER CONSISTENCY: The jar contains ONLY dry, granular coffee powder throughout the video. Every scoop must visibly collect dry powder. Powder must adhere to the spoon and fall naturally. Spilled powder must remain completely dry. Never transform it into liquid, slurry, or another substance. MILK PHYSICS: Milk must originate ONLY from B's container. Maintain this exact order: Dry countertop → container tilts → visible milk stream → milk lands → spill accumulates. Never generate milk spontaneously or before pouring begins. FINAL REQUIREMENTS: No extra cups, spoons, ingredients, gestures, or events. Prioritize exact object identity, physical continuity, realistic hand interactions, character consistency, and perfectly timed comedic reactions over visual embellishments.