AI Prompt Library

Make this image into her wearing same outfit and a blue vail in her hair the riding a camel with music Tinariwen in the background delete the picture keep the part where she is riding stoand ,eliminate the dialogue why is riding backwards put Tiwhyye...

Tom Cruise performing a boring soliloquy in the role of has-been alcoholic food taster Plurpooty Tzavavastovo in the rediscovered but overly complicated Eugene O'Neill play Schmutz on the Psyche.

Create a short 16:9 photorealistic Korean cinematic zombie-horror scene in an abandoned farmhouse kitchen. A crying female survivor from Korea with messy dark hair, dried blood on her forehead, and a dirty olive-green hooded anorak aims a black pistol at her infected lover. She is trembling, tears running down her face, but cannot pull the trigger. The infected man has tangled dark hair, pale dirty skin, milky-white eyes, dark veins, torn clothing, and an increasingly feral expression. He snarls loudly and screams directly at her. She slowly lowers the pistol, drops it beside her, and opens her arms toward him. He suddenly screams again, lunges forward and violently grabs her face. Hard smash-cut to warm golden-hour memories of the same couple happily together in a vast wheat field — laughing, holding each other, walking hand-in-hand through the golden grass, and sitting together beneath the sunset. Make the contrast between the cold present and beautiful memories emotionally powerful. Photorealistic live-action cinema, natural skin and tears, realistic infected eyes and facial expressions, handheld camera, practical-effects horror, 35mm film grain, believable movement and lighting. No gunshot, no gore, no dialogue, no slow motion, no extra plot, no CGI look, no animation, no distorted anatomy, no duplicate characters, no subtitles, no text, no watermark.

My rooster 🐓 get out of bed to have breakfast, I made you chilaquiles with lots of cream and cheese, hot bolillo bread, orange juice, I love you 🐓🫀❤️💋

Better yet land a raptor booster rocket on Harvard university with a Grock 4.... Learn about anything anywhere

A beautiful Korean girl with long dark hair, wearing a fitted black sleeveless top, black athletic shorts, and white sneakers, is playing basketball on an outdoor orange-colored basketball court surrounded by lush green trees. A cute oversized white cartoon-style dog mascot with black floppy ears is standing opposite her, holding and bouncing a basketball. The scene begins with a wide cinematic shot showing the girl facing the giant dog character near the basketball hoop. She playfully interacts with the mascot while dribbling the basketball, creating a fun and charming atmosphere. The camera smoothly moves between wide shots and medium close-ups, capturing the girl's natural expressions, flowing hair, realistic body movement, and the mascot's cute reactions. At the middle of the video, the girl steps closer to the camera while holding the basketball, looking confident and slightly playful. The giant dog character remains visible in the background, reacting humorously to her movements. Toward the end, she moves back toward the basketball hoop and prepares for another playful basketball moment while the mascot is seen in the foreground. Photorealistic Korean girl, natural skin texture, realistic facial features, consistent identity, detailed hair strands, realistic athletic movement, cinematic outdoor lighting, soft overcast daylight, shallow depth of field, smooth handheld camera movement, realistic basketball court textures, natural shadows, high-detail 4K cinematic quality, playful K-drama-inspired visual style, no face distortion, no extra fingers, no unnatural body movement, no text or watermark.

Create a 9:16 38 second video of someone drinking tea from first person perspective, as the cyber truck drives them around FSD style the desert in Phoenix, Arizona.

Create a photorealistic cinematic full-body scene in the same dark gothic cathedral with dramatic volumetric light rays and stone columns. The mysterious armored knight king in black ornate armor, golden crown, red velvet hooded cloak with gold embro...

Cinematic realistic texture, pure ancient Chinese Xianxia aesthetics. Core focus on mature conceptual conflict, restrained martial arts character performance, and veteran screenwriter-style dialogue driven by subtext, pauses, and reversals. Adopt Arri Alexa film camera texture, natural volumetric lighting, and delicate film grain. This core reversal revolves around the distinction between "loyalty" and "obedience": Everyone thought the senior sword immortal would demand unconditional loyalty from the junior sister The true reversal is she actively teaches the junior sister: True loyalty is not always listening to her, but having the courage to draw a sword and stop her when she goes wrong Strictly use @Image 1 and @Image 2 as character identity anchors. All background and location reference images uploaded this round jointly determine the same environment DNA. Before formal composition, silently reconstruct compatible real terrain, architectural language, material age, vegetation, water bodies, weather, mountain mist, reflections, main light direction, and atmospheric depth, forming a unique, complete, unified new location for this round. Background remains persistently alive but absolutely neutral narratively. Character Settings Character ID A Always the same @Image 1 Senior Sword Immortal Sister: 25-30 year old East Asian female Oval fair face Dark almond eyes Black long hair half-tied, fixed with white jade hairpin Tall and slender figure Wearing same set of white embroidered silk Hanfu Silver waist sash Jade pendant White cloth boots Holding single silver longsword Character ID B Always the same @Image 2 Junior Sword Immortal Sister: 20-25 year old East Asian female Round lively face Black hair braided Petite figure Wearing same set of green linen Hanfu Dark belt Wooden hairpin Black cloth shoes Holding single dark steel sword Other Secondary Characters The following characters exist only as secondary witnesses: An elderly master Two sect disciples Several bystanders A captured enemy commander Segment Structure 0-5s | Wide or Long Shot Clearly establish oath-taking site, character relationships, and spatial order. An elderly master presiding over formal oath-taking. He says solemnly: "Take oath — never disobey senior sister's command in this life." Junior sister prepares to kneel. The same white-robed sword immortal suddenly interrupts: "Delete this line." First half of this segment must quickly form a hook, making viewers mistakenly think she will propose stricter loyalty demands, but she instead negates this oath. 5-10s | Medium Shot or Cowboy Shot Maintain same two women, same costumes, same swords, and completely consistent geographical space. Master clearly confused asks: "Are you afraid she won't be loyal?" Senior sister calmly answers: "I am afraid she is too loyal." Entire venue instantly quiet. In shallow depth of field behind, the same enemy commander's original mocking smile also slightly disappears. Senior sister truly turns to junior sister, only asks: "If one day, I am wrong?" Junior sister freezes completely for the first time. Wind, water, mountain mist, sleeves, hair, and distant figures in background continue natural motion but completely do not participate in this choice. 10-15s | Close-up or Extreme Close-up The same junior sister does not continue kneeling, but slowly stands straight. She only draws the dark steel sword halfway, using the blade not fully sheathed to block horizontally in front of senior sister, forming a clear barrier without killing intent, saying: "Stop you first." Senior sister looks at her, asks: "If you can't stop me?" Full pause of half a beat. Junior sister finally truly raises eyes to meet hers, answers: "Then defeat you." Extreme close-up: The same senior sword immortal's originally serious and restrained expression finally reveals an extremely light, truly approving smile. She uses only two fingers to gently push away the blade blocking in front, saying: "This is more like my junior sister." In shallow depth of field behind: The same elderly master completely silent The same enemy commander slowly lowers gaze Junior sister ultimately does not kneel again Hard Requirements Strict total duration 15 seconds 16:9 landscape Strictly three continuous clear shots Native synchronized Mandarin dialogue Precise lip sync and eye-line relationships Character identity, hairstyle, costume, sword, supporting role positions, and geographical space stable throughout Character micro-expressions must be restrained and realistic Half-draw sword and horizontal blocking actions must be simple, clear, readable Natural physics for silk fabric, metal longsword, and hair Real parallax and synchronized spatial ambient sound maintained across foreground, midground, background No subtitles generated Seedance 2.0 Mini Execution Focus For Seedance 2.0 Mini, emphasize: Reference character consistency Visual hierarchy among multiple characters Few but precise action nodes Camera continuity Light and shadow continuity Sword state continuity Precise audio-visual synchronization of dialogue, sword drawing sound, scabbard friction, fabric sounds, and environmental sounds Negative blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props

Sea of ink. When Ningning runs her brush, the peaks she touches turn into ice and snow. The Big Dipper is far away, and the Heavenly Palace is even further. A white wolf rises from within the ice and howls. The end of 'Mayfly World'. People are lost. One remains in the realm. Put down the brush, or stay with the wolf? The ink is still not dry. Only where the brush touches becomes ice. The Big Dipper is small. The wolf emerges from the peak, not the page. Put down the brush? Stay with the wolf and the realm?

Create a 30-second, 4:3 horizontal aspect ratio, highly realistic personal fitness Vlog that captures the feel of a friend casually recording a daily workout with a early-2000s home DV camcorder. It is not a fitness ad or a polished cinematic short. The 30 seconds is an edited summary of the fitness process, connecting leaving home, preparation, training, and ending through natural jump cuts; do not rush the character to complete everything in 30 seconds, and do not use speed-ups. [Character & Clothing] Use the uploaded full-body image of the person in grey sportswear [@Image1] as the sole character reference. The protagonist is the adult female from the reference image, strictly maintaining her facial features, face shape, eyes, nose, lips, thin-framed glasses, hairline, and overall age appearance. She must remain the same person from different angles, during exercise, speaking, and smiling; she cannot become another similar-looking face. The reference image is only used to determine identity, clothing, and body appearance; do not reuse the white studio background or the fixed standing pose from the original image. The character has a natural, healthy fitness physique with moderate muscle definition in shoulders, arms, waist, abdomen, and legs, showing real muscle contraction and stable body control during movement. Maintain the overall height and body proportions from the reference image; do not exaggerate muscles, overly cinch the waist, or lengthen legs. Keep skin fair and delicate but with natural texture; slight redness may appear after exercise, but no excessive smoothing or plastic look. Wear the same set of sportswear from the reference image throughout: heather grey wide-neck short-sleeve T-shirt with the neckline naturally tilted, exposing her right shoulder (left side of the frame when facing front); the hem tied at the same-side waist forming a cropped style exposing the waist/abdomen, keeping the original pink-purple print on the chest; underneath is a pink-purple thin-strapped sports bra with straps and edges naturally visible; bottom wears heather grey high-waisted tight sports shorts, paired with white ribbed mid-calf sports socks and the same white lace-up sneakers as in the reference image. Clothes should have real wrinkles and slight displacement due to movement, but cannot change style, color, material, knot position, or exposed shoulder direction. Do not change into black tops, long leggings, blue socks, or boots. When leaving, keep the loose black long hair from the reference; tie it into a ponytail by hand before entering the gym, then maintain the same ponytail throughout, keeping natural bangs and sideburns; do not suddenly change bangs or hair volume. Glasses are worn throughout, maintaining reasonable position during exercise. Props are fixed: a small black gym bag, a transparent water bottle with a white cap, and a small white towel; do not change their appearance across shots. [Shot Flow] 0–3s | Going to nearby gym. Quiet community street, natural daylight. Friend films from her side-front while walking; she wears the aforementioned grey sportswear, carrying a small black gym bag on one shoulder, walking towards the nearby gym. Black long hair sways gently with steps. She briefly looks at the camera with a natural small smile, then continues looking at the road, not posing deliberately. Camera has slight undulation from walking, composition slightly off, like casual recording. 3–6s | Tying hair. Stops near gym entrance, side medium close-up. She raises hands to gather long hair, ties it into a neat ponytail with a black hair tie, then adjusts glasses and bag strap. Natural jump cuts may skip part of the tying process, but viewers must see the actual action from loose hair to ponytail; hairstyle cannot change magically. Movements are relaxed and skilled, contact between fingers and hair is realistic. 6–9s | Putting things down, simple warm-up. Cut to ordinary community gym, black rubber floor, dumbbell rack, bench, wall mirrors, environment realistic with traces of life usage, not luxurious empty commercial studio. She places black gym bag next to bench against wall, puts water bottle and white towel on one end of bench. Natural jump cut to her lightly moving shoulders, stretching arms, adjusting breathing. Camera feels like friend shooting casually from side, not deliberately showcasing body. 9–15s | Simple strength training. Two normal-speed training clips: first film her doing light dumbbell curls, fully presenting smooth lift, brief pause, controlled lowering; shoulders don't shake wildly, palms grip dumbbells realistically, arms show natural muscle lines with effort; then cut to side-front medium-full shot filming her completing one bodyweight squat, from standing to squatting and back up stably, feet contact ground, knee and hip movement reasonable, torso stable. She focuses on breathing, exhales softly when exerting force, doesn't pose for fitness camera. Sportswear shows natural stretch and wrinkles, ponytail swings slightly with movements. 15–20s | Treadmill jogging. Side-front handheld medium shot, she jogs easily on treadmill, stride moderate, left and right feet alternately contact belt, arms swing naturally, ponytail sways rhythmically with steps. Breathing becomes slightly heavier, small amount of sweat appears gradually on forehead, nose wings, and neck sides, not suddenly soaking wet. She glances at camera, smiles lightly with expression tired yet amused. Then natural cut to treadmill slowing/stopping, she confirms stability before stepping down, does not jump off running belt. 20–25s | Drinking water, wiping sweat. Returns to same bench, unscrews same water bottle, takes two small sips, then presses small white towel gently on forehead and neck sides. Towel has real contact and occlusion with skin, does not pass through glasses, does not wipe away all sweat directly. She accidentally sees sweaty self in mirror, laughs lightly, a real relaxed reaction after exercise, not exaggerated acting. Reflection's actions, clothing, and position must accurately correspond to person. 25–30s | Done working out. Sits on bench, breathing still slightly rapid, shoulders rising/falling with breath, holding towel. Friend brings camera closer, she looks up at camera, says naturally in Chinese tone with smile: "Today's workout felt pretty good!" Voice carries post-exercise breath, mouth shapes accurate, ends with light laugh. Finally natural cut to her carrying same black gym bag towards exit, ponytail swinging lightly, camera follows half-beat slow, ending in lifelike action, no advertising freeze-frame. [Photography & Visual Quality] Entire segment presents early-2000s consumer MiniDV recording quality: slight handheld shake, imperfect composition, occasional delayed follow-focus, slight autofocus search, brief exposure/white balance changes when moving outdoors to indoors, soft digital details, slight shadow noise, normal motion blur, and one unskilled small zoom. These flaws should be restrained and random, not every shot intentionally out-of-focus or violently shaking. Character's face always clear enough to recognize same person from reference. Primarily eye-level medium shots, medium-full shots, and natural facial close-ups; training shots retain necessary body/equipment info, no deliberate close-ups on chest/buttocks. No stabilizer-smooth moves, blockbuster grading, slow-mo, lens flares, film burn, exaggerated grain, or fake tape glitches. DV device itself does not appear in frame. [Audio] Only ambient sounds: community footsteps, slight street noise, door push, bag strap/cloth friction, gym AC hum, distant blurred conversation, light dumbbell placement, shoe-ground contact, treadmill motor sound, gradually heavier breathing, bottle opening/drinking, towel friction, natural laughter, and final character dialogue. Audio quality has slight noise/space sense from home DV mic, no studio vocals. No BGM, no narration, no subtitles. [Negative Constraints] Prohibit identity drift, face changing, glasses disappearing/deforming, hairstyle switching without reason, clothes changing color/style, exposed shoulder flipping left/right, body proportion changes, exaggerated muscles, plastic skin, beauty filters, abnormal skin texture, unreasonable sweat, distorted palms, extra fingers, equipment deformation, dumbbells passing through hands, foot sliding, distorted running motions, items floating/teleporting, wrong mirror reflections, duplicate protagonists, props appearing suddenly. Except for existing prints/marks on reference clothing, do not add brand logos, watermarks, date/timestamps, UI text, or other screen text.

Cinematic 16:9 live-action, 24 sec, realistic high school hallway, bright fluorescent lighting, shiny floor, grey lockers, shallow depth of field. Characters: Girl A: long wavy brown hair, blue plaid shirt over white tank top, jeans. Girl B: short dark bob, navy-and-cream letterman jacket with red "R". Scene 1 (0-2s): Wide shot. Girl A stands against lockers, Girl B faces her, confronting her. Students walk in the background. Scene 2 (2-4s): Close-up of Girl A, nervous and calm, Girl B's head blurred in the foreground. Cut to Girl B's close-up, smirking. Scene 3 (4-7s): Medium two-shot over Girl B's shoulder. Girl A looks tense and stares back. Scene 4 (7-8s): Girl B slaps Girl A. Girl A's head whips sideways, hair flying, and her eyes flash glowing white. Scene 5 (8-9s): Wide handheld shot. Girl A, eyes glowing, thrusts her arm out, blue-white electric energy crackles along her arm. Students in the hallway watch in shock. Scene 6 (10-15s): Close-up. Girl A's face, glowing white eyes, angry and shaken. Her glowing hand rises toward the camera, energy sparking around her fingers. Scene 7 (16-19s): Wide long hallway shot. Two jocks in varsity jackets rush at Girl A. She unleashes streaks of white energy that hurl them backward through the air. Scene 8 (20-24s): Front-facing tracking shot. Girl A walks down the empty hallway toward the camera, glowing energy on her arms and eyes. The glow fades, her eyes turn normal, and she looks breathless and shocked. Style: realistic teen superhero drama, natural skin texture, motion blur on energy effects, smooth camera moves, cool blue-white glow, no text or subtitles.

Constructive criticism can be a good thing, but it only comes from people who genuinely care about what you are doing.

CHARACTER LOCK: the main character is a man in his 30s, dark casual jacket, , short dark hair — consistent into Part 2. Muted color grading, natural sound throughout, tension score entering early. [0-1s] A woman leans close to a mannequin to inspect an outfit — its head turns toward her unexpectedly. [1-2s] It steps off its stand and reaches for her, pulling her out of frame. [2-3s] Wide shot: the four other mannequins nearby begin moving too, stepping down from their platforms. [3-4s] They move toward nearby shoppers with quick, unnatural motion. [4-5s] People scatter and call out in alarm through the section. [5-6s] One figure reaches a shopper near a clothing rack, pulling him off balance. [6-7s] Wide shot: concern spreads through the main corridor, people moving quickly away. [7-8s] The main character ducks behind a support pillar, assessing the situation. [8-9s] He spots a storage room nearby and waves urgently for others to follow. [9-10s] A group of shoppers hurries toward him and into the room. [10-11s] He pulls the last few inside and shuts the door firmly. [11-12s] Interior: the room full of worried people, some holding each other close. [12-13s] He leans against the door, then notices a wall mirror reflecting the corridor. [13-14s] Through the mirror he sees one figure standing still over a man on the floor. [14-15s] Close-up: his expression tightens with concern. [15-16s] He spots three more people hiding behind a distant pillar through the mirror. [16-17s] He glances at the room, then carefully opens the door a crack. [17-18s] The sound draws a nearby figure's attention toward the doorway. [18-19s] He grabs a life-size cardboard standee and sets it out in the corridor. [19-20s] The figure moves toward the standee instead, momentarily distracted. [20-21s] He slips out and moves low along the wall, away from it. [21-22s] Tracking shot: he hurries toward the three people behind the pillar. [22-23s] Close-up: their worried faces as he reaches them, signaling quiet. [23-24s] He motions for them to follow, checking the corridor both ways. [24-25s] Wide shot: the four of them move quickly back toward the storage room. [25-26s] Behind them, another figure's attention turns toward the movement. [26-27s] It begins following, picking up speed. [27-28s] He urges the group to move faster, glancing back. [28-29s] They reach the storage room door, hands on the handle. [29-30s]: the door swings open, light spilling out, the figure closing the distance behind them. Cut to black. Natural sound throughout — fabric movement, calls of alarm, footsteps, door sounds, breathing — with a tense instrumental score building steadily. No text overlay, no watermark. Varied camera work — close-ups, wide shots, mirror reflections, tracking shots. Natural retail lighting.

Ultra-realistic cinematic sci-fi action scene, a powerful warrior in a flowing beige futuristic outfit sprinting down a massive industrial corridor while wielding a glowing blue energy blade, two armored enemies approaching ahead, dramatic tilted camera angle, intense motion, dynamic movement, realistic fabric details, metallic futuristic architecture, atmospheric lighting, volumetric shadows, cinematic depth of field, high contrast, photorealistic, 8K, epic Hollywood sci-fi movie aesthetic, 35mm lens, vertical 9:16 composition.

Create a smooth, realistic fashion walk video using the reference image as the exact character and outfit reference. Preserve her facial features, hairstyle, clothing, body proportions, colors, and overall identity throughout the entire video. Full-body framing, cinematic fashion photography, natural realistic movement, soft daylight. Scene 1 – Walk Forward: She begins standing confidently, then slowly walks toward the camera with natural elegant steps. Her hands remain casually inside the varsity jacket pockets, hair gently moving with each step. Scene 2 – Side Pose: While walking, she slightly turns her body toward the side, looks briefly toward the camera, and gives a soft confident smile. Her hair naturally follows the movement. Scene 3 – Jacket Pose: She stops for a moment, shifts her weight onto one leg, slightly pulls her shoulders back, keeps one hand in the jacket pocket, and casually adjusts the jacket with the other hand. Scene 4 – Final Walk & Turn: She resumes walking past the camera, then gently turns her head over her shoulder with a subtle smile before continuing forward. Her skirt and hair move naturally with the motion. Smooth camera tracking, subtle cinematic camera movement, realistic walking physics, natural facial expressions, realistic fabric and hair motion, no sudden movements, no body distortion, no face changes, no extra fingers or limbs, consistent outfit and appearance, premium fashion campaign aesthetic, vertical 2:3, 8–10 seconds.

15-second cinematic photorealistic science-fiction action short, 16:9. A gigantic futuristic city travels through deep space inside an enormous asteroid storm. Thousands of spacecraft fly alongside it, actively manipulating the asteroids into a constantly moving defensive shield. Suddenly an enemy fleet attacks. Hundreds of fighters dive into the asteroid field. The city accelerates. Asteroids slam into attacking ships. Defensive spacecraft race between enormous rocks, pushing them into new trajectories. A massive enemy warship breaks through the asteroid shield and fires directly at the city. The entire city suddenly changes direction. The asteroid field moves with it. Millions of rocks swing into formation around the city like a gigantic mechanical organism. The attacking warship realizes too late that the asteroid field itself is the city's weapon. A colossal impact fills the screen. End on the city disappearing into the moving storm. Photorealistic hard science fiction, spectacular asteroid environments, relentless combat, massive moving structures, fast camera movement, detailed spacecraft, huge scale, cinematic action, no text, no logos, no anime, no cartoon.

Claymation Capt. apathy drinking at a bar while villains destroy the world on tv.

An enormous staircase emerges from the middle of the ocean and rises into the clouds. People gather in disbelief. A young explorer begins climbing. Each step reveals Earth further into the future. First step: futuristic cities. Next step: forests growing on skyscrapers. Next: oceans filled with floating civilizations. Higher: giant orbital rings surrounding Earth. Higher: cities drifting through the atmosphere. Higher: humanity traveling among stars. The climb becomes faster and more dangerous. Thousands follow behind. The staircase stretches beyond the clouds and into space. The explorer reaches the final visible step. Beyond it lies a future so vast and magnificent it cannot fully be understood. A brilliant light floods everything. The staircase disappears. Leaving only the ocean below. Epic science fiction adventure, continuous upward motion, escalating future visions, breathtaking scale, emotional wonder, photorealistic environments, cinematic camera movement, dynamic action, masterpiece visuals, 16:9.

Cinematic photorealistic texture, pure ancient Chinese Xianxia high-tension dual combat. This time completely break out of previous modes: Constant weapon changes Single combat breaking The core becomes: The two protagonists themselves are a continuously moving dual tactical system. One absorbs pressure from the front The other changes the situation from the flank Immediately swap roles in the next second The real thrill is not flashy sword qi, but that the two protagonists almost don't need to turn back to confirm, can constantly cover each other's blind spots, forming stronger and stronger tacit understanding and tension. Character and Asset Locking Strictly lock only @image 1 and @image 2 as the two core characters. @image 1 | Sword Immortal Senior Sister Image 1 Sword Immortal Senior Sister always maintains original: Adult East Asian female identity Face Black long hair half-up White jade hairpin Tall slender proportion White embroidered silk Hanfu Semi-transparent layered wide sleeves Silver waist seal Jade pendant White cloth boots Only one silver straight sword @image 2 | Junior Sister Image 2 Junior Sister always maintains original: Adult East Asian female identity Face Braided black hair Green linen Hanfu Dark belt Wooden hairpin Black cloth shoes Only one dark steel sword Other Characters Enemies, Master, Passersby are all functional characters only, no need for complex face locking, clothing locking. Environment DNA All uploaded background and location reference images this round jointly determine the same set of Environment DNA. Before formal generation, silently analyze compatible elements among them: Terrain Architecture Height differences Spatial scale Material age Vegetation Water bodies Weather Mountain mist Lighting Reflections Air depth Routes passable by characters Then recombine into a unique but credible new space for this round. Space and Route Principles The entire 15 seconds must occur in a continuous understandable combat route, cannot suddenly switch to another world. Background remains dynamically active but narratively neutral: Wind Water Mist Leaves Clothing hems Reflections Distant figures Always naturally active. Only when characters truly: Step Collide Grazing Weapons touching environment Do these appear: Dust Ripples Debris Scratches Clothing displacement etc. passive physical feedback. Strictly Prohibited Bridge suddenly breaking Mist suddenly saving people Tree suddenly blocking sword Building collapsing itself to help either side Segmented Structure 0–5s | Wide shot entering medium shot Same white-robed Sword Immortal Senior Sister and same green-robed Junior Sister standing back-to-back. Three enemy swordsmen who only bear combat function press in actively from different directions. 0–1s Use 24mm fixed wide panorama, letting audience understand at once: Positions of five people Attack directions Space available for movement next Junior Sister lowers voice, says only one line: "This time, don't turn back to save me." Senior Sister never turns back throughout, calmly answers: "Good." As soon as the last word lands, enemies launch simultaneously without warning. Camera quickly moves from fixed 24mm into 35mm medium-close range motion, but doesn't shake randomly, instead brought in by the characters' true movement lines. First Round Engagement One enemy attacks Senior Sister from above Another enemy cuts into Junior Sister's blind side simultaneously The two women explode in opposite directions almost instantly: Senior Sister briefly changes attack line of first sword then directly advances position Junior Sister lowers center of gravity grazing second attack, only counter-attacks enemy's weapon path, doesn't stop to pose Two immediately start migrating forward along routes truly existing in reference environment. A high-speed foreground passing enemy body briefly fills lens, using this real occlusion to complete first hidden cut, audience barely feels camera position has changed. 5–10s | Medium shot continuous follow Maintain: Same space Same two protagonists Same weapon ownership Enemies absolutely cannot queue up to send moves, they continuously: Chase Surround Intercept At this time: Senior Sister bears continuous pressure from two enemies Junior Sister faces another enemy Cannot split screen into "two fighting separately", must let two combat lines constantly interweave. First Tactical Complement Senior Sister deliberately yields half step, bringing one pursuing enemy into Junior Sister's advancing attack line. Junior Sister doesn't look at Senior Sister at all, only at the instant enemy's sword tip truly enters her space, briefly catches and changes weapon direction with dark steel sword, immediately releases, continues handling person in front. Second Tactical Complement Less than a second later, exact opposite happens again. Another enemy launches true attack from behind Junior Sister. Same white-robed Sword Immortal doesn't even turn back, silver sword tip enters from other side of frame at high speed, uses only one extremely short metal impact to push that sword out of dangerous line behind Junior Sister, then silver sword immediately leaves frame, Senior Sister continues own fight. Core State Two people never confirm each other's positions, yet accurately know where the other is. Camera glides smoothly between foreground and midground, utilizing following elements sweeping past lens at high speed to form 2-3 extremely natural hidden transitions: Enemy shoulders White wide sleeves Green clothing hem Weapons Rhythm Requirements Action rhythm isn't one speed from start to finish, but: Two fast exchanges One truly weighted weapon collision Half-beat silence Then sudden explosion Same older Master stays in distant safe zone observing, doesn't act from start to finish, doesn't solve problems for anyone. 10–15s | Close shot entering final wider medium shot Three enemies discover single pursuit ineffective, first time truly change strategy simultaneously, compressing space from three directions, forcing Senior Sister and Junior Sister toward same central area. Form obvious deadlock. Two don't continue retreating. Same white-robed Sword Immortal and same green-robed Junior Sister suddenly burst sprint towards each other simultaneously. Camera doesn't cut immediately, lets audience fully see: Two shoulder lines graze in high speed, bodies cross through each other with minimal distance. At moment of crossing, two fully swap front-back positions. And neither looks at the other. Tactical Flip After Swap Senior Sister while passing Junior Sister, directly takes over enemy originally attacking Junior Sister's blind side Junior Sister simultaneously cuts into line of enemy originally chasing Senior Sister One enemy longsword sweeps across entire camera at high speed, forming only one obvious weapon occlusion hard cut. Cut to brand new reverse axis: Senior Sister now stands at position Junior Sister just left Junior Sister also stands at position Senior Sister just left Both immediately complete two extremely short, extremely direct, no showy rotation reverse breaks: Silver sword tip safely stops one finger-width before an enemy's chin Dark steel sword simultaneously safely stops outside another enemy's sword-wielding wrist Third enemy prepares to strike again, but finds both effective attack lines completely blocked by companion's position, can only force retreat. Sudden Stop Moment Previously dense: Whooshing sounds Metal collisions Shoe sole skid sounds Collapse suddenly at this moment. Leaving only: Two women's true breathing Extremely light residual vibration of swords Silk clothing hems gradually falling Senior Sister still looking at enemy in front, asks without turning head: "Still alive?" Junior Sister pauses almost none: "Easier than you." Senior Sister's mouth corner shows only extremely brief, extremely light hint of smile. Distant same Master finally lightly exhales breath held throughout, but doesn't preach, doesn't explain relationship between two. Ending State After victory confirmed, absolutely no victory poses. Two women lower sword tips simultaneously, maintain original pace continuing forward through same space; three enemies instinctively yield road. Hair, clothing hems, environmental wind, water mist, debris continue natural movement, picture ends directly while characters still moving forward. Camera and Editing Requirements Strict total duration 15 seconds 16:9 landscape Maintain 0–5s / 5–10s / 10–15s three clear narrative segments Visually dominated by one continuous silky camera path Whole film allows only about 4-5 hidden cuts or cuts truly triggered by impacts Prohibit crazy fragmented cutting for "action feel" Seedance 2.0 Mini Execution Focus For Seedance 2.0 Mini, actively control prompt budget. Most important is: Image 1, Image 2 two protagonist identities stable Two swords' ownership stable Hands and bodies continuous Two people's spatial relationship continuous Core environment route continuous Three enemies only need to maintain: Ancient style enemy swordsmen Basic functional appearance That's enough, don't waste model attention strictly locking faces, clothes and details. Sound and Motion Requirements Native synchronized Mandarin dialogue Native synchronized spatial audio effects Focus strengthening: Sword tip brief whoosh Real metal collisions Shoe sole friction Silk clothing hem twitching Characters' true breathing Final sudden quiet sound contrast Motion Texture 24fps cinematic motion texture Natural motion blur Actions must have clear: Start Acceleration Force application Line change Inertia Braking Strictly Prohibited Teleportation

Main Subject: Young Korean woman, 24, naturally attractive, realistic skin, minimal makeup, long dark hair loosely down. Wearing an oversized maroon hoodie and loose casual pants, carrying a simple canvas shoulder bag. Preserve her exact identity, facial features, hairstyle, body proportions and appearance throughout. Location: Quiet older Seoul neighborhood on a pleasant morning. Narrow residential street with low-rise apartment buildings, small local shops, parked bicycles, potted plants and modest storefronts. A little Korean girl, around 5–6 years old, is standing safely near the sidewalk with a small ice cream cone in one hand. Her shoelaces have come completely undone. Lighting & Atmosphere: Warm, cheerful and cozy morning atmosphere. Soft sunlight filters between the buildings, creating gentle warm highlights while some areas remain naturally shaded. Muted surroundings, soft shadows, slightly faded colors and a nostalgic early-2000s feeling. The scene should feel wholesome and ordinary rather than sentimental or cinematic. Style: Ultra-realistic early-2000s Sony MiniDV home video filmed by another person casually walking with her. Multi-shot but completely candid and unstaged. Natural handheld movement, subtle camera shake, imperfect framing, gentle reframing, occasional autofocus hunting, mild exposure shifts, faded colors, soft contrast, authentic DV compression, subtle digital noise and natural microphone noise. Shot 1 — 00:00–00:04: Medium-wide handheld shot as the young woman walks casually down the quiet street. She notices a little girl standing near the sidewalk, holding an ice cream cone while looking down at her untied shoelaces with a confused expression. Shot 2 — 00:04–00:07: The camera moves slightly closer as the woman slows down. The little girl looks at her shoelaces, then at her ice cream, clearly unsure how to deal with both at once. The woman understands the problem and gently gestures toward the laces, asking if she can help. Shot 3 — 00:07–00:11: The woman crouches down beside the child and carefully ties the loose shoelaces into a secure bow while the child stands still, carefully holding her ice cream away from them. The woman's movements are gentle and efficient. Shot 4 — 00:11–00:14: She gives the finished shoelaces a quick little check and stands back up. The child looks down at her shoes, then looks up at the woman with a small grateful smile. Shot 5 — 00:14–00:17: The woman gives the child a warm little smile and a tiny nod, then continues walking down the street. The child happily takes another bite of her ice cream. Shot 6 — 00:17–00:20: As the woman walks away, she briefly turns toward the camcorder and gives a quiet, contented smile before looking forward again and continuing down the street. Audio: Natural sound only—soft footsteps, distant traffic, subtle neighborhood ambience, children's distant voices, light breeze, fabric movement and the natural sounds of the street. The ch

15 seconds, 9:16 vertical screen, photorealistic mobile phone travel vlog, entirely self-shot by an adult female protagonist using the front camera. The protagonist's identity refers to #1 @0ba07db1-974c-467d-80dc-d9dffddac0ba, clothing, shoes, socks, and accessories strictly refer to #2 @c6a3d787-bf2f-4ae9-a647-8da9db2702e3, do not replace the protagonist with characters from scene images. Scene references include the sea of clouds mechanical colossus in #3 @cf1b1405-e241-46d5-818c-7838463fe334 and the cave giant in #4 @7953261f-23e7-4c97-b6a0-14bcf07aabe4. Use explicit travel jump cuts between the two locations to indicate that the journey in between has been omitted, rather than showing a single step crossing space. She always holds the phone in her right hand, while her left hand is used to steady herself on rocks or maintain balance. The phone is about one arm's length from her face; in the wide-angle selfie, her face is positioned on one side of the frame, with the environment unfolding behind her shoulder. The character and environment share natural light, shadows, dust, and wind, preserving realistic skin texture. Only include shaking consistent with foot and wrist movements, brief exposure adjustments, and motion blur. No beauty filters, no background music, no subtitles. [0-4 seconds] On a broad rock platform above the sea of clouds, the female protagonist slowly walks along the inner side away from the cliff edge. She turns her body sideways so that two golden mechanical colossi embedded in the mountain appear behind her shoulder: huge breastplates occupy the background, legs disappearing into the clouds, with distant travelers appearing extremely small. Sunset illuminates one side of her cheek, wind ruffles her hair tips. She first looks up, then at the lens, whispering with suppressed awe: "This scenic spot, the security guards are taller than mountains." [4-7 seconds] She stops to continue looking up. The orange glow on one colossus's chest slowly intensifies, its head rotates slightly; moments later, low-frequency mechanical sounds reach the platform. She listens first, then confirms visually, her smile gradually fading. Her left hand instinctively steadies the nearby rock wall, pulling the phone slightly closer. She stops speaking, only taking a short breath. Background travelers stop individually to observe, without turning heads uniformly. [7-11 seconds] Explicit hard cut, omitting transition journey: She has arrived at the gravel path outside the cave referenced in #4. Light changes to gray-white daylight reflected from the cave entrance, with sheep, wooden fences, and scattered baskets behind her. She was walking along the path when a panicked ancient soldier runs past her left side, followed by two more rushing around the gravel. She steps aside first, watching them suspiciously; then heavy footsteps sound, small stones on the ground tremble. She turns back to look at the cave entrance, rotating her body to reveal the giant's face between the rock walls behind her shoulder. She whispers: "Wait... they're not here to queue." [11-15 seconds] The giant squeezes toward the cave entrance, shoulders brushing off falling rocks, dust obscuring part of the wooden fence. The protagonist immediately stops speaking. She first checks the escape route ahead, then follows the fleeing crowd quickly leaving along the path, bringing the phone close with her right hand, raising her left arm to protect her forehead. The selfie footage shakes with her footsteps, the giant only briefly appears behind her shoulder, not seeking full-body composition. In the last two seconds, she moves sideways into a recess on the right rock wall, bending her knees to lower her body, supporting herself on the rock surface with her left hand. Ending shot: She leans against the rock wall, right hand holding the phone slightly upward at chest level, thin dust on her face, lips slightly parted, breathing heavily; the left edge of the frame still shows dust drifting from the cave direction. Sound: High-altitude wind, low-frequency mechanical sounds; after the jump cut, replaced by sheep bleating, running footsteps, rolling gravel, giant's breathing, and her close-range panting. Only the protagonist speaks clear lines, background figures' shouts are indistinct. Prohibit third-person tracking shots, aerial shots, floating phones, continuous direct gaze while running, sudden outfit changes, smiling explanations ignoring danger. The giant does not teleport in front of her.

cinematic street racing sequence at night, a focused driver inside a high-performance car grips the steering wheel, intense eye focus, city lights reflecting on windshield, tension building before sudden acceleration camera: rapid multi-angle system with seamless transitions, interior close-up → over-the-shoulder → exterior tracking → low ground shots, ultra dynamic camera movement, whip pans + speed ramp transitions + motion blur masking cuts, continuous flow illusion (0-2s) interior close-up on driver, hand tightens on gear shift, subtle breathing, dashboard lights glowing (2-4s) over-the-shoulder shot, road ahead stretching into neon-lit city, engine vibration building (4-6s) extreme close-up on finger pressing NOS button, instant ignition reaction (6-8s) explosive acceleration, camera snaps to exterior side tracking shot, car launches forward with violent speed surge (8-10s) ultra low ground shot near asphalt, wheels spinning at extreme velocity, environment streaking past (10-12s) high-speed chase through tight streets, sharp turns, camera whip pans between angles, reflections and light trails enhancing speed Dense urban night environment, wet asphalt reflecting neon lights, tunnel passages, street lights streaking, high-speed city atmosphere Ultra realistic, fast and furious inspired energy, photorealistic lighting, intense motion blur, high contrast neon reflections, cinematic depth of field, extreme sense of speed, fluid transitions, no distortion, no stretching

Created a 20 seconds cinematic Japanese-style scene of a young schoolgirl walking alone through a quiet Japanese residential street during warm golden-hour sunlight, shown from behind as she slowly approaches a railway crossing with a train passing in the background, then transitioning to a close-up of her face and flower-decorated hair as she watches the train, followed by a wider shot of her standing near a quiet canal with soft evening light reflecting on the water, then showing her gently touching small white flowers in a golden field, with close-up shots of her hand and the flowers moving naturally in the breeze, gradually transitioning to a wide sunset landscape with the girl standing peacefully in the field, and finally ending with a warm close-up of her face as she softly looks toward the camera, maintaining the same character, hairstyle, school uniform, realistic skin details, natural expressions, smooth cinematic camera movement, soft depth of field, warm sunset lighting, realistic Japanese environment, subtle film grain, peaceful emotional atmosphere, and a dark fade-out at the very end.