Loading video...
Video Failed to Load
What if workouts were generated like this? Built a dumbbell routine as a motion sheet with GPT Image 2 Then turned it into a video with Seedance 2.0 I tested 4 exercises in 15s, it works, but 2–3 exercises would probably give the best output. Motion sheet: Monochrome grayscale... show more
99,122 views • 5 months ago •via X (Twitter)
0 Comments
No comments available
Comments from the original post will appear here
Related Videos
![GPT Image 2 + Seedance 2.0 I used a movement sheet as a reference image to animate the dance. Prompt: Monochromatic grayscale illustration, 3D-rendered character, clean instructional reference sheet. White background, comic-style cell grid layout, technical diagram aesthetic. [LAYOUT] 4×4 grid layout (16 panels total). Each panel separated by thin black border lines. Panels are evenly sized and consistently aligned. Each cell is clearly numbered from 1 to 16. [CHARACTER] (Insert character description) Example: Young female dancer with an athletic build, ponytail hairstyle, wearing a crop top, baggy pants, and sneakers. The same character must appear consistently in all panels. [PANEL STRUCTURE – per cell] Top-left: bold number badge + Korean title text Center: full-body character pose illustration Bottom-left: Korean description text (3–4 lines) Overlay: directional arrows indicating movement flow [ARROWS / MOTION INDICATORS] Curved arrows, straight arrows, and circular rotation indicators. Arrows should be placed around the character to clearly show movement direction and flow. [RENDERING STYLE] Highly detailed 3D sculpted style. Soft studio lighting with subtle shadows. No color — grayscale only. Clean linework, polished finish, game concept art quality. [NEGATIVE PROMPT] No background scenery. No color tones. No additional characters. No cluttered or complex backgrounds.](https://image.24vids.com/tw-2049007457918198128/ext_tw_video_thumb/2049007398061477888/pu/img/2whopeD4MH7TQKOf.jpg)
![john wick seedance text to video prompt： [STYLE / CINEMATIC SETUP] A 10.5-second, 16:9 photorealistic AAA action-game cinematic rendered at real-time speed with no slow motion. The setting is a cramped, cluttered late-night Asian restaurant connected to a rain-soaked street. Cyan-green fluorescent light, red neon and warm practical lamps create a high-contrast mixed-light environment, with reflections across wet floors and pavement. Shoot with a 35mm spherical lens, shallow-to-moderate depth of field and cinematic motion blur appropriate to the actual speed of movement. Use close shoulder-mounted and handheld coverage, connecting seven short close-combat shots with fast hard cuts. The camera instinctively pans, retreats or drops with each block, takedown and collision while keeping the action and contact points readable. No dialogue, no subtitles and no BGM. Generate only synchronized rain, appliance hum, urgent footsteps, fabric movement, body impacts, gunshots, metal contact and breaking glass. [IMAGE REFERENCES] No external still-image reference. Follow the written character and environment descriptions consistently. If the platform supports reference video, use the supplied video only as a reference for editing rhythm, camera distance, action direction and lighting atmosphere, not for copying a specific actor’s identity. The protagonist remains the same lean, agile man in his early forties throughout the sequence: neck-length black hair swept back, a short beard, a tired but focused face, a slightly wrinkled black suit, white shirt and narrow black tie, all carrying faint rain and wear marks. Preserve his face, hairstyle, body proportions, clothing and screen direction across all seven shots. Keep every opponent visually distinct: a man in a blue work uniform, a bald man in a navy jacket, a heavy man in a black jacket, a bald counter attacker, a red-headband attacker, a red-jacketed armed attacker and a heavy man in a dark green coat outside. [TIMELINE SECOND BY SECOND] 0–1.9s: [Shoulder-height medium close-up, tight lateral handheld tracking, real-time speed] The protagonist stands on screen left, pinning the blue-uniformed attacker against a glass refrigerator with his left forearm and palm. He delivers two compact, weighted elbow and palm-heel strikes. Each impact drives the attacker’s head into the refrigerator door, loosening his white headband and leaving a small blood trace on the glass; the attacker finishes sliding down the door while the protagonist remains standing. 1.9–4.3s: [Medium shot transitioning into a high-angle overhead, shoulder-mounted drop, real-time speed] Hard cut near the restaurant’s rear entrance. The bald attacker in a navy jacket locks the protagonist from behind. The protagonist lowers his center of gravity, traps the attacker’s arm and rotates his hips, throwing him heavily over the shoulder onto the wet floor. The camera drops with them into an overhead view. Kneeling across the attacker’s torso, the protagonist draws a compact black pistol and fires one downward shot; recoil travels through his wrist and the attacker jolts once before becoming still. 4.3–5.9s: [Tight medium shot, lateral handheld follow, real-time speed] Hard cut with both men already upright. A heavy attacker in a black jacket swings from screen right. The protagonist slips outside the punch, allowing it to pass close to his face, circles behind the attacker and locks his shoulder and neck off balance. He presses the pistol close to the side of the attacker’s head and fires. The muzzle flash briefly illuminates both faces; the attacker’s head and shoulders snap backward and his body begins to collapse. 5.9–7.9s: [Counter-height medium close-up, subtle handheld push-in, real-time speed] Hard cut to the restaurant counter. Another bald attacker bends forward and clamps around the protagonist’s waist. The protagonist pins the attacker’s head and neck under his left arm while grabbing a short, rigid pointed utensil from the counter. He drives two compact downward thrusts into the upper shoulder and side of the neck. Each contact bends the attacker’s knees further; a restrained amount of blood marks the shirt and counter edge before the attacker hangs helplessly beneath the protagonist’s controlling arm. 7.9–9.0s: [Two-person medium close-up, fast pan with a short retreat, real-time speed] Hard cut as the red-headband attacker rushes into close range. He throws a wide hook from screen right. The protagonist raises his forearm to block, catches the wrist and pulls it outward, then drives a palm heel and forearm into the attacker’s face. The camera retreats with the impact as the attacker loses his balance and staggers toward the rear right of the frame. 9.0–9.9s: [Low-angle wide shot, slight arc around the action, real-time speed] Hard cut to a wider section of the restaurant. The red-jacketed armed attacker advances from screen left. Holding a long black firearm with both hands, the protagonist uses it as a blunt weapon and swings horizontally from right to left. The weapon strikes the attacker’s upper chest and shoulder, rotating his torso, crossing his feet and sending him off balance toward screen left. 9.9–10.5s: [Exterior rainy-street medium shot, fast parallel tracking, real-time speed] Hard cut outside the restaurant. The protagonist already controls a heavy attacker in a dark green coat and uses his forward momentum to drive the man’s head and upper body into the side window of a parked black station wagon. The glass bursts inward at the contact point, scattering both large and fine fragments. The attacker folds through the broken window while the protagonist regains stable footing beside the car, ending with glass fragments still falling. [STYLE & QUALITY BOOSTERS] Maintain the protagonist’s face, black suit, white shirt, tie, hairstyle and body proportions through every hard cut. The pistol, pointed utensil, injuries and blood marks must appear only in their designated shots and must never morph or change ownership. Throws, recoil, strike reactions, loss of balance and window breakage must show believable weight, inertia and precise contact. Apply motion blur only to rapidly moving arms, weapons, glass fragments and camera-relative backgrounds. No sudden face or costume changes; no extra fingers, fused limbs or inverted joints; no morphing weapons, utensils or vehicles; no foot sliding or rubber-like collision reactions; no blood, bullet damage or glass fragments appearing before physical contact.](https://image.24vids.com/tw-2086349180948345309/amplify_video_thumb/2086348909522378752/img/Rj8L9yLglxtuCEcl.jpg)
 private bedroom in daylight; clean, modern, intimate, naturally lived-in. Large curtain several meters behind Sharon, simple desk/console farther behind, minimal personal objects and subtle decoration. Enough depth for subject separation. Background softly out of focus; Sharon remains sharp and readable. CAMERA / LIGHTING Eye-level handheld, medium-wide/full-body framing with room for lateral movement and shoe actions, moderate shallow depth of field. Soft natural daylight, natural skin tones, soft highlights, gentle realistic shadows, warm clean atmosphere. Camera is operated physically with Sharon: lateral tracking, short push-in, reactive pull-back, quick pans, tilts and reframing. Never perfectly smooth or automated; movement is quick, light, imperfect and physically motivated by her actions. ACTION + CAMERA 0.0–1.1s — Sharon enters from RIGHT holding TWO SHOES, one in each hand, and walks toward center. Camera: handheld lateral tracking LEFT, physically stepping sideways while keeping medium-wide framing. 1.1–1.8s — Sharon @[Image 1](image_1) stops near center, raises one shoe toward camera as if showing it, then brings it toward her nose. Camera: short handheld push-in; keep face and shoe sharp. 1.8–2.4s — Sharon smells the shoe, immediately recoils with surprised disgust, pulls her face away and gives a short head shake. Camera: small reactive pull-back, then immediately settle toward her face. 2.4–3.0s — Sharon casually throws the first shoe toward the side of the room. Camera: quick reactive pan following the shoe briefly, then fast pan back to Sinta; believable handheld imperfection. 3.0–3.8s — Sharon shifts sideways, focuses on the second shoe, and throws it vertically upward. Camera: tilt up following the shoe; as it reaches the top of its trajectory, quickly tilt back down toward Sinta while keeping awareness of her and the descending shoe. 3.8–4.4s — Sharon tracks the descending shoe with her eyes, adjusts footing, rotates slightly sideways and prepares a high side kick. Camera: short lateral handheld adjustment keeping body and falling shoe in frame; subtle natural Dutch tilt may develop. 4.4–5.0s — Shoe descends into kicking range. Sharon performs a fast, precise HIGH SIDE KICK: leg extends sharply sideways, torso rotates slightly, supporting leg grounded, arms naturally counterbalance, eyes locked on the shoe. Full real-time. Camera: quick handheld lateral reposition and reactive pan following the kick; frame momentarily shifts with the force. EXACT MATCH CUT — 5.0s Hard cut at the exact moment Sharons extended foot contacts the airborne shoe. The kick is still at full speed and the cut happens DURING the action. Outdoor shot continues the same body direction, leg extension, torso rotation and momentum. SHOT 2 — NIGHT / QUIET CITY STREET | 5.0–10.0s ENVIRONMENT Relatively quiet modern urban street at night with broad paved roadway, streetlights, scattered storefronts, illuminated windows, trees, signage and distant buildings creating layered practical lighting. Sparse distant traffic. Spacious, cinematic, quiet. A WHITE SPORT MOTORCYCLE is behind Sinta and slightly toward one SIDE of frame, not centered directly behind her. Open street creates a clear diagonal path from Sharon to the motorcycle. LIGHTING / OUTFIT Naturalistic night lighting: warm streetlights mixed with cooler ambient city illumination, realistic highlights on black riding outfit, natural reflections on white motorcycle and asphalt, cinematic contrast with realistic exposure. Sharon wears a coordinated black-and-white motorcycle riding set: fitted black racing jacket with clean white shoulder/sleeve panels; fitted black short riding pants with subtle white detailing; compact black knee/shin protection; black motorcycle gloves with small white accents; clean white low-top sport sneakers; white crew socks to mid-calf; loose natural hair; no helmet. Motorcycle: white sport motorcycle. CAMERA Handheld kinetic cinematography. Operator physically follows Sharon using diagonal tracking, short arc movement, reactive panning, slight push-in and quick reframing. Never a perfectly programmed path; camera reacts to her changing body direction. ACTION + CAMERA 5.0–5.5s — HARD CUT. Sharon appears outdoors continuing the indoor side kick: kicking leg extended, torso rotated, momentum continuing. White sport motorcycle partially visible behind her toward one side. Camera immediately reacts. Camera: quick handheld pan/reframe catching the continuing kick trajectory. 5.5–6.3s — Sharon lowers her kicking leg naturally and does not stop. She moves DIAGONALLY across frame toward the motorcycle, forward-diagonal rather than straight backward/sideways, gradually turning torso and hips toward it while moving. Camera: handheld diagonal tracking with slight forward tracking plus lateral shift; keep Sharon dominant while motorcycle remains visible near the side. 6.3–7.2s — Sharon continues diagonally; body progressively rotates toward motorcycle. This is a traveling diagonal turn, NOT a stationary turn-in-place. Feet keep carrying her forward while torso rotates. Camera: short handheld arc around Sharon while continuing diagonal tracking; slight angle change and subtle pan to keep her centered; motorcycle remains partially visible at the side. 7.2–8.0s — SLOW MOTION BEGINS. Sharon is already mid-diagonal movement toward motorcycle. Body continues diagonal rotation; loose hair swings naturally; jacket moves with rotation; movement becomes elegant and cinematic. Camera: slightly smoother handheld character, subtle handheld push-in combined with short arc; stay physically close; motorcycle remains visible toward the side. 8.0–8.4s — Gradually return to normal speed. Sharon completes diagonal rotation and now faces motorcycle more directly. Camera: normal handheld movement; quick reframing keeps Sharon and motorcycle visually connected. 8.4–10.0s — Sharon moves confidently toward the white sport motorcycle, purposeful and energetic. Motorcycle stays slightly off-center. Camera: handheld forward tracking, maintaining medium-wide framing, subtle push-in, then small reactive pan toward motorcycle as Sharon reaches it. End with Sharon immediately beside the motorcycle. SPEED PRIORITY 0.0–5.0s: full real-time; shoe throw and high side kick are fast; match cut at full-speed impact. 5.0–7.2s: full real-time immediately after cut. 7.2–8.0s: subtle slow motion only during diagonal body rotation toward motorcycle. 8.0–10.0s: normal real-time. MATCH CUT PRIORITY Cut exactly on impact. Preserve across the cut: leg extension, torso rotation, body orientation, movement direction, screen position and continuous physical momentum. Location, time of day, lighting, wardrobe and motorcycle may change entirely through the hard cut. The transition must feel instantaneous, physical, stylish and seamless. #DomoAI #DomoAICPP](https://image.24vids.com/tw-2099332819768291755/amplify_video_thumb/2099332274944958465/img/iQvn_ieT_tihYCyo.jpg)
![借图用H3本地生成视频，还不错。 H3 提示语： subject_definitions: : The single referenced young adult fashion model: slim build, light skin, long dark brown hair, soft oval face, dark eyes, gentle expression, small light dangling earrings, and a pale blush-pink sheer long-sleeved floral dress with fitted waist and layered ruffled skirt; barefoot throughout. Source(s): , . summary: A continuous vertical intimate fashion-photo-session video: the referenced woman moves fluidly through the nine studio poses in the supplied storyboard, beginning from the supplied first-frame kneeling pose. Hard constraints: Exactly one continuous 15.083333-second vertical shot; no cuts, hidden transitions, narration, subtitles, or spoken dialogue. | Open on the rear-facing kneeling, over-the-shoulder composition established by . | Retain the same single young adult woman, long dark hair, pale-pink floral sheer ruffled dress, bare feet, warm blush seamless studio, and soft fashion-portrait lighting. | Follow the nine-pose reference progression from through continuous body repositioning; do not depict the reference as a visible collage or introduce additional people, furniture, text, or props. | Keep face, hands, feet, and dress inside the central vertical safe area during reframing. Generation controls (authoritative) — Prompt-text rule: every section label and descriptive sentence is silent production direction, never speech content. Do not speak, recite, chant, sing, or read this prompt aloud. Background music: enabled. Generate a context-appropriate non-diegetic score unless the user explicitly requests silence or no music. Dialogue permission is enabled, but this plan contains no dialogue lines. Generate no character speech, conversation, chanting, singing, or other vocals. Dialogue language: automatic. Preserve each explicit language tag; otherwise use the language required by the scene and user intent. Narration: disabled. Generate no narrator, voice-over, spoken description, or audible reading of prompt text, section labels, instructions, asset tags, or metadata. Subtitles: disabled. Do not render subtitles or dialogue captions. Creative direction (authoritative within explicit user intent and reference fidelity) Priority: Apply these creative directives clearly wherever they do not conflict with explicit user requirements, identity retention, or fixed first/last-frame composition. Camera execution: Follow the action continuously in a single unbroken take, using only motivated pans, small translations, and reframing needed to preserve spatial clarity. Look: Treat connected visual references as authoritative for identity, wardrobe, objects, environment, composition, lighting, color, and medium; do not impose an unrelated restyle. Pacing and composition: Use moderate, readable motion with natural acceleration and enough settling time for each important beat. Use exactly one continuous shot with no hidden or explicit cuts; express all action beats through blocking, performance, camera motion, reframing, and synchronized sound. An explicit user-requested shot or cut count remains authoritative over this density preference. Compose for a vertical frame: protect faces, hands, and essential action inside the central mobile-safe area; favor depth movement and avoid losing subjects at narrow side edges. retention_analysis: -> first_frame: Use as the fixed first-frame reference and primary authority for the woman’s identity, rear-facing kneeling pose, over-the-right-shoulder gaze, pale-pink floral dress, barefoot styling, warm peach-beige seamless studio, and soft directional fashion lighting.. -> composition: Use as the strict pose-storyboard reference for a continuous sequence of seated, kneeling, hands-and-knees, reclining, and floor poses; retain its vertical blush studio fashion-editorial presentation, wardrobe, subject appearance, and bare-foot styling.. detailed_description: [Shot 1] At 00:00.000-00:15.083, In a quiet blush-pink seamless studio during an intimate fashion photo session, begins exactly in the rear-facing kneeling pose: folded legs beneath her, bare feet toward the camera, torso turned back over her right shoulder with a calm closed-lip smile. Her long dark hair, pearl-like earring, and pale blush floral ruffled dress are clearly visible under soft warm editorial light. She then transitions fluidly through the supplied storyboard’s pose language without cuts: she turns into a seated pose with one leg extended; rises briefly to hands and knees and looks toward the lens; lowers into a stomach recline with her head supported by one hand and one bent leg lifting behind; pivots to lean back on one hand with one knee upright; returns to a centered kneel with hands together on the floor; sits with an arm extended overhead; draws her knees close in a compact seated pose; and finally reclines onto her back, hair spreading across the floor as her crossed ankles lift elegantly. Each pose gets a brief settle-and-hold beat suitable for shutter capture. Her performance stays poised, gentle, and natural; no vocal performance. Camera: One uninterrupted stabilized handheld fashion-camera take at low-to-mid height. Start in a full-body rear three-quarter framing matching the first image, with her feet in the lower foreground and her turned face in the upper central safe area. Make a slow, motivated leftward arc and slight push-in as she rotates into seated poses, then gently pan and make small lateral translations to retain her whole body through kneeling, floor, and reclining positions. Ease backward and slightly higher for the final lying pose so raised crossed legs, face, and spread hair remain fully visible. Natural parallax only; no optical zoom, whip pan, jump cut, or collage framing. Motion: Moderate, readable continuous movement: initial stillness and over-shoulder hold, then smooth pivots, controlled lowering and rising, and carefully paced floor transitions. Hair and ruffled skirt respond softly to each movement. Every pose briefly stabilizes before the next transition; the final raised-leg recline settles calmly. Synchronized audio: 0.0-15.083333: low-volume non-vocal fashion-editorial instrumental score.; 0.0-2.0: soft fabric movement and a restrained camera shutter click as the opening pose settles.; 2.0-12.8: light floor contact, dress rustle, and occasional quiet shutter clicks aligned with each completed pose.; 12.8-15.083333: fabric settles; final subtle shutter click and sustained soft studio ambience. overall_soundscape: Quiet studio atmosphere with soft fabric rustle, subtle bare-foot and hand contact on the seamless floor, faint breathing during exertion, and discreet camera-shutter clicks timed to settled poses. No dialogue, narration, captions, crowd noise, or other voices. No narration, voice-over, spoken description, or audible prompt reading. non_diegetic_music: A soft, understated airy fashion-editorial instrumental bed plays throughout at low volume, with gentle warm synth pads and sparse muted percussion; no vocals, lyrics, or speech.](https://image.24vids.com/tw-2105679463690428689/amplify_video_thumb/2105679270458834945/img/uvHhqHbx8JXiE6vr.jpg)
0:16
Sensitive content
借图用H3本地生成视频，还不错。 H3 提示语： subject_definitions: : The single referenced young adult fashion model: slim build, light skin, long dark brown hair, soft oval face, dark eyes, gentle expression, small light dangling earrings, and a pale blush-pink sheer long-sleeved floral dress with fitted waist and layered ruffled skirt; barefoot throughout. Source(s): , . summary: A continuous vertical intimate fashion-photo-session video: the referenced woman moves fluidly through the nine studio poses in the supplied storyboard, beginning from the supplied first-frame kneeling pose. Hard constraints: Exactly one continuous 15.083333-second vertical shot; no cuts, hidden transitions, narration, subtitles, or spoken dialogue. | Open on the rear-facing kneeling, over-the-shoulder composition established by . | Retain the same single young adult woman, long dark hair, pale-pink floral sheer ruffled dress, bare feet, warm blush seamless studio, and soft fashion-portrait lighting. | Follow the nine-pose reference progression from through continuous body repositioning; do not depict the reference as a visible collage or introduce additional people, furniture, text, or props. | Keep face, hands, feet, and dress inside the central vertical safe area during reframing. Generation controls (authoritative) — Prompt-text rule: every section label and descriptive sentence is silent production direction, never speech content. Do not speak, recite, chant, sing, or read this prompt aloud. Background music: enabled. Generate a context-appropriate non-diegetic score unless the user explicitly requests silence or no music. Dialogue permission is enabled, but this plan contains no dialogue lines. Generate no character speech, conversation, chanting, singing, or other vocals. Dialogue language: automatic. Preserve each explicit language tag; otherwise use the language required by the scene and user intent. Narration: disabled. Generate no narrator, voice-over, spoken description, or audible reading of prompt text, section labels, instructions, asset tags, or metadata. Subtitles: disabled. Do not render subtitles or dialogue captions. Creative direction (authoritative within explicit user intent and reference fidelity) Priority: Apply these creative directives clearly wherever they do not conflict with explicit user requirements, identity retention, or fixed first/last-frame composition. Camera execution: Follow the action continuously in a single unbroken take, using only motivated pans, small translations, and reframing needed to preserve spatial clarity. Look: Treat connected visual references as authoritative for identity, wardrobe, objects, environment, composition, lighting, color, and medium; do not impose an unrelated restyle. Pacing and composition: Use moderate, readable motion with natural acceleration and enough settling time for each important beat. Use exactly one continuous shot with no hidden or explicit cuts; express all action beats through blocking, performance, camera motion, reframing, and synchronized sound. An explicit user-requested shot or cut count remains authoritative over this density preference. Compose for a vertical frame: protect faces, hands, and essential action inside the central mobile-safe area; favor depth movement and avoid losing subjects at narrow side edges. retention_analysis: -> first_frame: Use as the fixed first-frame reference and primary authority for the woman’s identity, rear-facing kneeling pose, over-the-right-shoulder gaze, pale-pink floral dress, barefoot styling, warm peach-beige seamless studio, and soft directional fashion lighting.. -> composition: Use as the strict pose-storyboard reference for a continuous sequence of seated, kneeling, hands-and-knees, reclining, and floor poses; retain its vertical blush studio fashion-editorial presentation, wardrobe, subject appearance, and bare-foot styling.. detailed_description: [Shot 1] At 00:00.000-00:15.083, In a quiet blush-pink seamless studio during an intimate fashion photo session, begins exactly in the rear-facing kneeling pose: folded legs beneath her, bare feet toward the camera, torso turned back over her right shoulder with a calm closed-lip smile. Her long dark hair, pearl-like earring, and pale blush floral ruffled dress are clearly visible under soft warm editorial light. She then transitions fluidly through the supplied storyboard’s pose language without cuts: she turns into a seated pose with one leg extended; rises briefly to hands and knees and looks toward the lens; lowers into a stomach recline with her head supported by one hand and one bent leg lifting behind; pivots to lean back on one hand with one knee upright; returns to a centered kneel with hands together on the floor; sits with an arm extended overhead; draws her knees close in a compact seated pose; and finally reclines onto her back, hair spreading across the floor as her crossed ankles lift elegantly. Each pose gets a brief settle-and-hold beat suitable for shutter capture. Her performance stays poised, gentle, and natural; no vocal performance. Camera: One uninterrupted stabilized handheld fashion-camera take at low-to-mid height. Start in a full-body rear three-quarter framing matching the first image, with her feet in the lower foreground and her turned face in the upper central safe area. Make a slow, motivated leftward arc and slight push-in as she rotates into seated poses, then gently pan and make small lateral translations to retain her whole body through kneeling, floor, and reclining positions. Ease backward and slightly higher for the final lying pose so raised crossed legs, face, and spread hair remain fully visible. Natural parallax only; no optical zoom, whip pan, jump cut, or collage framing. Motion: Moderate, readable continuous movement: initial stillness and over-shoulder hold, then smooth pivots, controlled lowering and rising, and carefully paced floor transitions. Hair and ruffled skirt respond softly to each movement. Every pose briefly stabilizes before the next transition; the final raised-leg recline settles calmly. Synchronized audio: 0.0-15.083333: low-volume non-vocal fashion-editorial instrumental score.; 0.0-2.0: soft fabric movement and a restrained camera shutter click as the opening pose settles.; 2.0-12.8: light floor contact, dress rustle, and occasional quiet shutter clicks aligned with each completed pose.; 12.8-15.083333: fabric settles; final subtle shutter click and sustained soft studio ambience. overall_soundscape: Quiet studio atmosphere with soft fabric rustle, subtle bare-foot and hand contact on the seamless floor, faint breathing during exertion, and discreet camera-shutter clicks timed to settled poses. No dialogue, narration, captions, crowd noise, or other voices. No narration, voice-over, spoken description, or audible prompt reading. non_diegetic_music: A soft, understated airy fashion-editorial instrumental bed plays throughout at low volume, with gentle warm synth pads and sparse muted percussion; no vocals, lyrics, or speech.
leolee
194,563 views • 3 days ago
![Hold up, here is the prompt: works with almost any model. enjoy :) Role & Objective: Act as an Elite UI/UX Front-End Engineer specializing in Apple-tier micro-interactions and advanced CSS. Your task is to program a perfectly centered navigation bar in a strictly SINGLE HTML file containing all HTML, vanilla CSS, and vanilla JavaScript. No external libraries or frameworks (No Tailwind, React, etc.). Design Concept - "True Liquid Glass": CRITICAL INSTRUCTION: Do NOT generate standard, flat "glassmorphism" or basic frosted glass. I require a physically accurate "Liquid Glass" aesthetic. It must look like wet, poured clear resin, combining the high-gloss specular highlights of classic macOS Aqua with the volumetric spatial depth of modern Apple VisionOS. 1. The Liquid Glass Material & Lighting (CSS): - Deep Refraction: Use `backdrop-filter` with extreme blur (e.g., 50px) and over-saturation (200%). - Specular Highlight: Create a curved, semi-transparent white gradient on the top half using a pseudo-element (`::before`) to simulate a hard light reflection on a wet, rounded 3D surface. - Caustics & Volume: Use multi-layered inner and outer `box-shadow` properties to simulate light refracting at the bottom edge and casting a realistic ambient drop shadow. - Interactive Glare: Implement a soft radial-gradient spotlight inside the glass that dynamically tracks the user's mouse cursor (X/Y coordinates) using JavaScript and CSS variables (`mix-blend-mode: overlay`). 2. Navigation Layout & Elements: - Center the pill-shaped navigation bar perfectly in the middle of the viewport. - Include 3 main navigation items with minimalist, inline SVG stroke icons and text labels: "Home", "Call", and "List". - Add a subtle vertical divider line after the main buttons. - Next to the divider, add a Dark/Light Mode toggle button containing inline SVG Sun and Moon icons. 3. Animations & "Apple Magic": - Sliding Active Pill: Create a solid background "pill" that sits *behind* the active navigation item's text/icon. When a different item is clicked, this pill must dynamically recalculate its width and slide to the new position. - Spring Physics: The sliding transition MUST use an exact Apple-style bouncy spring easing curve (e.g., `transition: all 0.5s cubic-bezier(0.34, 1.2, 0.64, 1)`). - Tactile Feedback: Buttons and icons must physically press down slightly (`transform: scale(0.92)`) when clicked (`:active`). - Theme Switch: The Sun and Moon icons must smoothly rotate, scale, and cross-fade during the transition. 4. Background Environment (Crucial): - Glass needs light and color to refract! Create a full-viewport, smoothly animated mesh gradient background using 3 large, heavily blurred, floating color blobs. - Implement full Dark/Light mode logic using CSS variables (`:root` and `[data-theme="dark"]`). Toggling the theme must seamlessly transition the background blob colors, glass opacity, shadow intensity, and text colors. Output ONLY the pristine, production-ready code. Prioritize maximum visual fidelity and silky-smooth 60fps animations.](https://image.24vids.com/tw-2032212276447490106/amplify_video_thumb/2032212244692336641/img/JoGBG5XEJRS4Xl0O.jpg)
 = established baby pterodactyl character. BRACHIOSAURUS = same established massive adult Brachiosaurus from previous scenes. THIS IS AN EDIT OF THE EXISTING VIDEO 1. DO NOT RECREATE VIDEO 1. DO NOT GENERATE A DIFFERENT PERFORMER. DO NOT REPLACE THE ORIGINAL PERFORMANCE. DO NOT REPLACE THE ORIGINAL CAMERA MOVEMENT. DO NOT REPLACE THE ORIGINAL VOICE. ONLY INTEGRATE: 1. @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) on the performer's LEFT SHOULDER 2. the established Brachiosaurus behind/near the performer 3. the physical cracker interactions 4. the Brachiosaurus sneeze and resulting goo ================================================== ORIGINAL VIDEO / PERFORMANCE LOCK ================================================== KEEP THE ACTUAL VIDEO 1 FOOTAGE AS THE MASTER. Preserve the performer's exact: face, identity, hair, beard, skin, clothing, tattoos, body, hands, expressions, eye movements, mouth/lip movements, gestures, cracker movement, body movements, camera position, camera angle, camera motion, handheld shake, micro-shake, timing, and complete original performance. DO NOT reinterpret his movements. DO NOT invent new hand movements. DO NOT alter his existing reaction to accommodate the sneeze. Generated elements must conform to the ORIGINAL SOURCE PERFORMANCE. ================================================== ORIGINAL AUDIO — ABSOLUTE LOCK ================================================== KEEP VIDEO 1'S COMPLETE ORIGINAL AUDIO TRACK FROM 0:00–25.07. DO NOT regenerate the performer's voice. DO NOT replace his voice. DO NOT clone his voice. DO NOT recreate his dialogue. DO NOT remove commentary. DO NOT rewrite commentary. DO NOT shorten commentary. DO NOT move dialogue. DO NOT change dialogue timing. DO NOT change pitch, cadence, pronunciation or microphone characteristics. EVERY ORIGINAL WORD AND REACTION REMAINS AT ITS EXACT SOURCE TIMESTAMP. Generated creature sounds are ADDITIVE ONLY. ORIGINAL SOURCE AUDIO ALWAYS HAS PRIORITY. ================================================== @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) — LEFT SHOULDER LOCK ================================================== @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) is physically perched on the performer's LEFT SHOULDER for the ENTIRE 25.07-second sequence. @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) remains approximately 10 INCHES TALL. SAME @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d). SAME SIZE. SAME PROPORTIONS. SAME LEFT SHOULDER. Preserve his established: head, small beak, large expressive but realistic eyes, developing crest, skin, coloration, markings, tiny wings, wing membranes, legs, feet, claws, and juvenile proportions. He remains physically anchored to the LEFT shoulder with: correct foot contact, tiny claw placement, realistic weight, balance, contact shadows, body inertia, and natural occlusion. He may blink, tilt his head, make tiny balancing movements and react naturally. DO NOT resize him. DO NOT move him to another shoulder. DO NOT let him fly away. DO NOT make him disappear. DO NOT make him float. ================================================== BRACHIOSAURUS — SAME ESTABLISHED CHARACTER ================================================== Use the SAME massive adult Brachiosaurus established in the previous shots. Approximately 40–45 FEET TALL AT THE HEAD. Preserve its established: massive body, huge legs, long upright neck, small head, gray-brown / olive natural coloration, realistic prehistoric skin, and enormous scale. DO NOT shrink the Brachiosaurus to fit frame. The Brachiosaurus is physically CLOSE BEHIND the performer and @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d). It is peacefully grazing. Its body orientation places it behind them, calmly eating grass. It is NOT threatening them. It is NOT hunting them. It is NOT behaving aggressively. ================================================== 0:00–1.00 — CRACKER COMES OUT ================================================== During the opening second: preserve the source performer's EXACT movement as he pulls a cracker from his pocket. DO NOT replace the hand. DO NOT change which pocket he uses. DO NOT invent a different cracker movement. The cracker should remain physically consistent in: size, shape, orientation, color, and position. @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) notices the cracker. He becomes subtly curious. Tiny head tilt. Eyes track the cracker. Small interested movement toward it while remaining on the LEFT shoulder. The Brachiosaurus remains behind them peacefully grazing. ================================================== 1.00–4.06 — OFFERING CRACKER TO @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) ================================================== The performer offers the cracker toward @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) according to the EXACT existing source hand movement. @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) remains perched on the LEFT shoulder. He becomes increasingly interested. Use subtle believable baby-animal behavior: watching cracker, tiny head movements, small sniffing/inspection motion, slight forward lean, gentle blinking. DO NOT make him immediately eat. DO NOT make him leave the shoulder. ================================================== 4.06 — @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) TAKES A HUGE BITE ================================================== At EXACTLY approximately 4.06 seconds: @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) suddenly takes a surprisingly HUGE BITE from the cracker. This should be an adorable comedic beat. His little beak physically contacts the cracker. He bites off a noticeably large piece relative to his tiny body. The cracker must visibly lose the corresponding piece. DO NOT regenerate a whole cracker immediately afterward. Maintain cracker continuity. @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) then begins chewing the piece. Cute but PHOTOREALISTIC. Tiny jaw/beak movement. Happy interested baby-animal energy without human facial expressions. A few VERY SMALL realistic cracker crumbs may fall. NO cartoon crumb explosion. NO exaggerated animation. @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) REMAINS ON THE LEFT SHOULDER. ================================================== 4.06–12.03 — @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) CHEWS / BRACHIOSAURUS GRAZES ================================================== Preserve the performer's complete source performance. @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) finishes chewing his large bite. He may: blink, make tiny chewing movements, look toward remaining cracker, make a tiny satisfied head movement. The Brachiosaurus remains close behind them. It is peacefully eating grass. Show realistic herbivore behavior: slow neck movement, head lowered toward grass, slow chewing, occasional weight shift, subtle breathing. Its enormous size remains obvious. NO aggression. ================================================== 12.03 — CRACKER OFFERED TO BRACHIOSAURUS ================================================== At EXACTLY approximately 12.03 seconds: preserve the source performer's EXACT hand/arm movement as he offers the remaining cracker toward the enormous Brachiosaurus. DO NOT change the performer's movement. The Brachiosaurus notices the cracker. It slowly and curiously moves its enormous head toward the offered cracker. CRITICAL SCALE: The Brachiosaurus head is HUGE compared with the performer's hand and cracker. DO NOT shrink its head to make the interaction easier. The performer should look extremely small beside it. The dinosaur remains gentle and curious. ================================================== 12.03–14.07 — BRACHIOSAURUS INVESTIGATES CRACKER ================================================== The Brachiosaurus slowly lowers/brings its head close enough to inspect the cracker. Its movement is: slow, heavy, curious, gentle. The nostrils approach the cracker. The huge animal sniffs cautiously. Use subtle nostril movement and breathing. The cracker may move VERY slightly from the dinosaur's breath. DO NOT have it eat the cracker. DO NOT have it bite the performer. DO NOT make it aggressive. ================================================== 14.07 — BRACHIOSAURUS SNIFFS CRACKER ================================================== At EXACTLY approximately 14.07 seconds: the Brachiosaurus takes a clear sniff of the cracker. Immediately after the sniff, something begins irritating its enormous nostrils. THIS IS THE SETUP FOR THE COMEDIC SNEEZE. The Brachiosaurus does NOT sneeze immediately at 14.07. First create a short, recognizable PRE-SNEEZE BUILDUP. ================================================== 14.07–16.14 — MASSIVE PRE-SNEEZE BUILDUP ================================================== Immediately after sniffing: the Brachiosaurus begins preparing to sneeze. Make this visually recognizable but realistic. The huge nostrils twitch. Its breathing changes. Small involuntary head movement. Another nostril twitch. Its eyes briefly narrow/blink. Its enormous head subtly pulls back. A deep inhalation begins. The neck and head show physical tension from the incoming sneeze. This should create a funny moment where the audience realizes: "OH NO." DO NOT sneeze early. BUILD THE ANTICIPATION FROM 14.07 UNTIL 16.14. @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) remains on the LEFT shoulder. He can become subtly confused/alert: tiny head tilt, blink, slight wing adjustment. DO NOT make @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) leave the shoulder. ================================================== 16.14 — MASSIVE BRACHIOSAURUS SNEEZE ================================================== At EXACTLY approximately 16.14 seconds: THE BRACHIOSAURUS SNEEZES. The sneeze is: sudden, enormous, powerful, wet, unexpected, and VERY FUNNY. The enormous head makes a believable involuntary forward sneeze motion. Generate a powerful burst of GREENISH-WHITE DINOSAUR NASAL MUCUS / SALIVA. The material is: pale greenish-white, semi-translucent, wet, slimy, stringy in places, slightly foamy in places, viscous, physically believable. NOT neon green. NOT glowing. NOT blood. NOT vomit. NOT feces. NOT gore. This is disgusting but comedic dinosaur sneeze mucus. ================================================== SNEEZE TRAJECTORY / PHYSICS ================================================== The sneeze spray must originate physically from the Brachiosaurus's nostrils/mouth area. It travels through REAL three-dimensional space toward the performer and @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d). Use realistic: spray trajectory, droplet size variation, larger mucus strands, smaller wet droplets, momentum, gravity, depth, motion blur, occlusion. The goo must NOT simply appear magically on the performer. THE AUDIENCE SHOULD SEE THE SPRAY TRAVEL FROM THE DINOSAUR TO THEM. ================================================== 16.14 — PERFORMER AND @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) GET COVERED ================================================== The huge sneeze blasts BOTH the performer AND @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d). A ridiculous amount of greenish-white mucus lands across the performer. Depending on source framing, physically coat visible areas such as: hair, forehead, face, beard, shoulders, shirt/clothing, arms, and nearby body surfaces. @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) ALSO gets covered because he is still physically sitting on the performer's LEFT shoulder. The mucus may coat portions of: @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d)'s head, crest, beak, tiny wings, body, and feathers/fuzz/skin surfaces appropriate to his established design. IMPORTANT: DO NOT completely obscure the performer's face. His identity and expressions must remain recognizable. DO NOT deform his face. DO NOT change his mouth/teeth. The goo is an OVERLAY physically landing on the EXISTING performer. DO NOT regenerate the performer after impact. ================================================== @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) REACTION TO SNEEZE ================================================== @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) is surprised by the sudden blast. Use a quick but believable baby-animal reaction: rapid blink, brief tiny wing flutter, small startled body movement, little head shake. BUT: @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) DOES NOT FLY AWAY. @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) DOES NOT FALL OFF. @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) REMAINS ON THE LEFT SHOULDER. Afterward he can look confused and slightly pathetic while covered in goo. This should be extremely funny because the tiny baby creature trusted the performer and now BOTH of them are covered. ================================================== 16.14–25.07 — AFTERMATH ================================================== Preserve the performer's EXACT ORIGINAL SOURCE REACTION and camera movement after the sneeze. DO NOT replace his reaction. DO NOT invent a new reaction. The mucus remains physically present on the performer and @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) for the rest of the shot. CONTINUITY IS CRITICAL. DO NOT make the goo disappear. DO NOT magically clean them. DO NOT reset clothing. DO NOT reset @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d). The mucus can naturally: drip slowly, stretch slightly, slide under gravity, cling to hair, cling to clothing, cling to @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d). Keep it believable. The Brachiosaurus recovers from its sneeze. It can make a small head shake/blink and then look completely innocent. THIS IS FUNNIER IF THE BRACHIOSAURUS ACTS LIKE NOTHING HAPPENED. It may casually return toward grazing afterward. NO second sneeze. NO attack. ================================================== COMEDY TONE ================================================== PLAY THE EVENT STRAIGHT. DO NOT make the scene cartoonish. The comedy comes from: tiny @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) taking a ridiculously big cracker bite, the performer deciding to offer the same cracker to an enormous Brachiosaurus, the dinosaur innocently sniffing it, the audience recognizing the incoming sneeze, and then the completely disproportionate amount of disgusting mucus covering both of them. THE MORE PHOTOREALISTIC THE EVENT LOOKS, THE FUNNIER IT IS. No cartoon effects. No comedy sound effects. No exaggerated reaction generated for performer. ================================================== LIGHTING / COMPOSITING ================================================== KEEP VIDEO 1'S ORIGINAL LIGHTING. Integrate the Brachiosaurus, @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) and mucus into the source footage. Match: white balance, exposure, color temperature, contrast, shadow softness, black levels, highlight rolloff, green environmental bounce, camera sharpness, and motion blur. Mucus must respond to existing lighting. Wet areas should have subtle natural specular highlights. No CGI glow. No compositing halos. No artificial rim light. ================================================== CAMERA — ABSOLUTE LOCK ================================================== USE VIDEO 1'S ACTUAL CAMERA FOOTAGE. ONE PERSON. ONE PHONE. ONE CONTINUOUS TAKE. NO third-person camera. NO cutaway. NO alternate angle. NO cinematic close-up. NO dinosaur POV. NO @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) POV. NO stabilization. NO gimbal. NO slow motion. NO cuts. ================================================== FINAL AUDIO LOCK ================================================== KEEP THE COMPLETE ORIGINAL VIDEO 1 AUDIO. Generated audio may ONLY add subtle: @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) cracker bite/chewing, Brachiosaurus grazing, Brachiosaurus sniff at 14.07, deep inhale during 14.07–16.14, massive wet sneeze at 16.14, wet splatter, and natural pasture ambience. ALL GENERATED SFX MUST SIT UNDER THE ORIGINAL VOICE. IF GENERATED AUDIO INTERFERES WITH THE PERFORMER'S ORIGINAL VOICE: REDUCE OR REMOVE GENERATED AUDIO. NEVER REMOVE OR REGENERATE THE ORIGINAL VOICE. ================================================== FINAL HARD LOCK ================================================== TOTAL LENGTH: EXACTLY 25.07 SECONDS. FINAL OUTPUT: EXACTLY 24 FPS. VIDEO 1 = MASTER FOOTAGE. VIDEO 1 = MASTER PERFORMANCE. VIDEO 1 = MASTER CAMERA. VIDEO 1 AUDIO = MASTER AUDIO. @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d): LEFT SHOULDER THE ENTIRE SHOT. APPROXIMATELY 10 INCHES TALL. SAME SIZE EVERY FRAME. BRACHIOSAURUS: SAME ESTABLISHED MASSIVE ADULT. APPROXIMATELY 40–45 FEET TALL. CLOSE BEHIND PERFORMER. PEACEFULLY GRAZING. 0:00–1.00: performer pulls cracker from pocket. 1.00–4.06: performer offers cracker to @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d). 4.06: @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) takes a HUGE BITE from cracker. 4.06–12.03: @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) chews while Brachiosaurus grazes behind them. 12.03: performer offers remaining cracker to Brachiosaurus. 14.07: Brachiosaurus sniffs cracker. 14.07–16.14: VISIBLE PRE-SNEEZE BUILDUP. NOSTRIL TWITCH. BLINK. DEEP INHALE. HEAD PULLS BACK SLIGHTLY. DO NOT SNEEZE EARLY. 16.14: MASSIVE BRACHIOSAURUS SNEEZE. GREENISH-WHITE WET DINOSAUR MUCUS BLASTS ACROSS BOTH THE PERFORMER AND @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d). @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) REMAINS ON LEFT SHOULDER. 16.14–25.07: PRESERVE EXACT SOURCE REACTION. GOO REMAINS VISIBLE AND NATURALLY DRIPS. BRACHIOSAURUS RECOVERS AND ACTS INNOCENT. NO SECOND SNEEZE. NO ATTACK. NO OTHER DINOSAURS. NO @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) FLYING AWAY. NO @[garlic](25abf54f-7508-4ce8-9e67-776907b18e4d) RESIZING. NO REGENERATED PERFORMER. NO REGENERATED HUMAN VOICE. NO CAMERA REPLACEMENT. NO CUTS. KEEP ACTUAL VIDEO 1 FOOTAGE AND AUDIO. FINAL OUTPUT: EXACTLY 24 FPS. ``` The **2-second pre-sneeze from 14.07 → 16.14** is important. I’d keep that instead of making him instantly sneeze after sniffing—the audience gets just enough time to see the nostrils twitch and realize what's about to happen before you and Garlic get absolutely blasted.](https://image.24vids.com/tw-2101731253498024399/amplify_video_thumb/2101730634670485504/img/RnHSBeKRB9gx1bVo.jpg)
![深藏不漏的本地视频生成大师 Gary 用黑白深度+精准分镜提示词复刻了陶阿狗君的创意换装视频 我用 Minimax H3 + gary的黑白深度，微调了一下提示词，就用新的模特复现了 复刻的具体步骤： 1. 准备好模特的人物三视图 2. 生成四个场景下的人物参考图，可以用 gpt image 2.5 换人 3. 稍微调整提示词里对原来模特的特征锁定，按照新模特重写 4. 用新的提示词 + 参考图片 + 黑白深度视频交给 Minimax H3 生成 微调后的提示词👇 defines Rei's opening outfit only: a fitted black satin mini dress with thin spaghetti straps, a lace-trimmed V-neckline, a small front bow with trailing ribbons, off-the-shoulder lace ruffle sleeves, a ruched bodice, a ruffled lace hem, bare legs and black pointed-toe stiletto pumps. Preserve the dress's silhouette, materials and front/back construction as shown. Use this outfit for the white-studio opening only; do not reproduce the character-sheet layout. defines her Paris outfit, front-facing presentation pose, drink, sunglasses, city map and UI. defines her Rome outfit, front/three-quarter presentation pose, props, city map and UI. defines her Cairo outfit, presentation pose, shopping bags, city map and UI. defines her Sydney outfit, front-facing finishing pose, city map and UI. is an unmodified slightly turned standard face crop from the original Rei character card. It is the highest-priority facial identity reference for ALL outfits: preserve its eye shape and spacing, eyelids, nose, lips and natural proportions without beautification. Pictures 2–5 supply new city outfits and environments, never a substitute face. This is the same adult woman in different clothes throughout the entire video. is a black-and-white relative-depth reference for body movement, camera pullback and chronological timing only. Depth brightness represents distance, not skin color or face detail. Render natural full color using the pictures. A featureless face in the depth map must not become the back of Rei's head. Use the scene pictures to resolve which way her face and chest point after each turn. Generate ONE continuous 12-second vertical video. The timed Shot labels below are successive phases of this one output, not instructions to insert camera cuts. Keep the reference timeline at its original speed. Do not compress the opening to make room for the cities. Only Rei rotates during transformation; the camera must not orbit her. A back view is a brief passing orientation during a spin, never a held destination pose. Each completed transformation reveals her face and the FRONT of the new outfit, as in its corresponding picture. Change clothing, handheld props, city map and city-name UI together; do not change only the background while leaving the previous outfit. Shot 1 [0.00–2.50 seconds]: White studio and opening black sailor uniform from . Rei looks at the phone held in front of her chest. Follow the opening camera pullback in . Her torso remains generally facing the camera; allow the original small phone and head gestures. This interval contains no full-body spin, no location pin yet, no city background and no wardrobe change. Shot 2 [2.50–3.15 seconds]: The red location pin appears above Rei. This event ONLY adds the pin. She continues looking at her phone in the white studio, still wearing the opening black sailor uniform. The pin does not trigger a spin or a scene change. Do not begin the transformation here. Shot 3 [3.15–4.05 seconds]: Follow the small preparatory side pivot in , then return toward the camera-facing starting orientation while holding the phone. This is the preparatory movement, not the rapid transformation spin. Retain the opening black sailor uniform, white background and red pin throughout this interval. No Paris map or summer outfit before 4.05 seconds. Shot 4 [4.05–6.00 seconds]: At 4.05 seconds begin the rapid transformation rotation following . Pass continuously through the side and back orientations without pausing. Around 4.25 seconds, during this rotation, change together into the Paris outfit, drink, sunglasses, map and navigation UI from . By 4.50 seconds complete the rotation and reveal Rei FACING THE CAMERA, with her face and the front of her navy-and-ivory striped top visible. From 4.50 to 6.00 seconds remain in this front/three-quarter FRONT presentation, with the drink and sunglasses gesture from . The cream full-length trousers, striped top and red neck scarf replace the opening black sailor uniform completely. No back-facing hold, no phone, no opening black sailor uniform during the Paris presentation. The top search bar and bottom location card both read 巴黎. Shot 5 [6.00–8.00 seconds]: Begin the next reference turn at 6.00 seconds. Around 6.25 seconds change outfit, props, city and UI to Rome from . Complete the turn by 6.55 seconds into a front/three-quarter FRONT view showing Rei's face, sage-green midi dress with brown belt. Until 8.00 seconds use the Rome pose with the paper guide and warm Trajan column and Roman Forum map. Both city labels read 罗马. Back-facing frames occur only while the turn is in progress; no stopped back view after the turn. Shot 6 [8.00–10.00 seconds]: Begin the next reference turn at 8.00 seconds. Around 8.25 seconds change together to the ivory linen shirt, beige full-length trousers, ochre scarf, shopping bags, Cairo map and UI from . By 8.55 seconds reveal her face and the front of the ivory linen shirt. Hold the front/three-quarter presentation with natural small movements until 10.00 seconds. Both city labels read 开罗. Keep the Cairo outfit and map together; do not introduce previous clothes or Sydney early. Shot 7 [10.00–12.00 seconds]: Begin the final reference turn at 10.00 seconds. Around 10.25 seconds replace the Cairo clothes and shopping bags, city and labels with the Sydney sky-blue overshirt, white T-shirt, navy knee-length shorts and white sneakers, Sydney Tower map and UI from . By 10.55 seconds face the camera with the white T-shirt beneath the sky-blue overshirt visible, hands raised and one leg bent backward as in . Keep this front-facing Sydney presentation with subtle natural movement through 12.00 seconds. Both city labels read 悉尼. No additional spin, destination or wardrobe change after this final reveal. Keep Rei's facial identity, natural body proportions, hair and bangs throughout. Clothing changes must not alter her face, age, body shape, hair color or hair length. Do not reproduce character-sheet panels, extra people, face closeups or depth-map gray colors. Do not reproduce the blank faces in Picture 1's full-body clothing views; Rei must have her normal face whenever her face is visible. Keep the city UI style consistent; update both location labels at each city change. No generated speech or music. The angle in Picture 6 describes identity only, NOT a fixed head pose. Face direction, expression, head tilt, hand gestures and full body movement follow Video 1, with each completed city presentation matching its corresponding scene picture. In Paris the sunglasses are opaque black and fully cover both eyes and eye sockets. Keep the sunglasses on throughout the Paris presentation. At the Rome transformation, switch to the accessories shown in Picture 3.](https://image.24vids.com/tw-2101904919540429295/amplify_video_thumb/2101901822952976384/img/enwE2APiSSfU8iWS.jpg)
