AhaPrompt
提示詞
精選
模型
AI 反推
定價
投稿
部落格
首頁
AI 提示詞庫
Mysterious
Mysterious 提示詞
探索最佳 Mysterious 類提示詞,適用於 AI 圖片、影片與音訊生成。
瀏覽AI 圖片提示詞
瀏覽AI 影片提示詞
瀏覽AI 音樂與語音提示詞
AI 提示詞庫
全部
圖片
影片
音訊
最新
熱門
全部分類
3D Render
Abstract
Advertising
Aerial
Ambient
Animals
Animation
Anime
Architecture
Avatar
Black & White
Bright
Cartoon
Character
Cinematic
Cityscape
Classical
Comic
Cyberpunk
Dark
Digital Art
Dramatic
Dynamic
Electronic
Ethereal
Fantasy
Fashion
Folk
Food
Game Assets
Gothic
Hip-Hop
Historical
Holiday
Horror
Infographic
Jazz
Landscape
Lo-Fi
Logo Design
Macro
Minimalist
Motion Graphics
Music Video
Mysterious
Mythology
Nature
Neon
Oil Painting
Peaceful
Pixel Art
Pop
Pop Art
Portrait
Poster
Product Photography
R&B
Realistic
Rock
Sci-Fi
Short Film
Sketch
Slow Motion
Sound Effects
Space
Sports
Steampunk
Sticker
Still Life
Street Photography
Surreal
Tattoo
Timelapse
Trailer
Typography
Vector
Vehicles
VFX
Vintage
Voiceover
Wallpaper
Watercolor
Whimsical
0:15
MiniMax H3
TITLE: THE LAST WITNESS STYLE: Ultra-photorealistic, high-budget Hollywood crime mystery thriller, 16:9 widescreen, 15 seconds, anamorphic cinema lens, dark blue-grey color grade, dramatic practical lighting, heavy rain, atmospheric fog, realistic reflections, subtle film grain, deep shadows, cinematic contrast, natural motion blur. Premium theatrical movie cinematography. No subtitles, no captions, no watermark. CHARACTER LOCK: Detective Daniel, a 38-year-old man with short wet dark hair, light stubble, sharp tired eyes, wearing a black tailored trench coat over a charcoal shirt. Maintain exactly the same face, hairstyle, clothing and proportions in every shot. LOCATION: Abandoned underground parking garage at midnight, wet concrete floor, flickering fluorescent lights, parked black sedan, distant city lights visible through the entrance. A mysterious evidence envelope lies on the car hood. SHOT-BY-SHOT: SHOT 1 (0:00–0:02): EXTREME WIDE ESTABLISHING SHOT. Camera slowly descends into a deserted underground parking garage. Heavy rainwater drips from the ceiling. Detective Daniel walks alone toward a black sedan. Slow cinematic dolly movement, deep atmospheric tension. SHOT 2 (0:02–0:04): LOW-ANGLE TRACKING SHOT. His polished black shoes step through a shallow puddle. Camera tracks backward as he approaches the car. Water ripples naturally with each step. A distant metallic bang echoes. SHOT 3 (0:04–0:06): TIGHT CLOSE-UP. Daniel notices a sealed evidence envelope on the hood. His hand slowly reaches toward it. Camera pushes in toward his eyes, capturing a subtle expression of suspicion. Fluorescent light flickers once. SHOT 4 (0:06–0:09): MACRO INSERT TO OVER-THE-SHOULDER. He opens the envelope and pulls out a photograph. The photograph clearly shows Daniel himself standing beside the same black car, photographed from behind only moments earlier. His fingers freeze. A slow camera push reveals the photograph. SHOT 5 (0:09–0:12): EXTREME CLOSE-UP. Daniel slowly raises his eyes toward the dark reflection in the car window. In the reflection, a mysterious human silhouette stands directly behind him. The silhouette must remain physically grounded and visible only in the glass reflection. Daniel's breathing becomes audible. SHOT 6 (0:12–0:15): FAST WHIP-PAN TO REVEAL. Daniel turns sharply. The space behind him is completely empty. Camera rapidly pushes toward his shocked face. In the final half-second, a second handprint suddenly appears on the fogged car window beside his reflection. CUT TO BLACK. CAMERA: Smooth controlled dolly, low tracking shots, macro detail, shallow depth of field, realistic handheld movement only during the reveal, cinematic rack focus, natural motion blur, consistent screen direction. AUDIO: Heavy rain ambience throughout, echoing footsteps, distant metallic impact, envelope paper rustle, low sub-bass suspense drone, heartbeat-like percussion during the reflection reveal, sharp cinematic sting at the final handprint, abrupt silence on cut to black. REALISM: Physically accurate rain, water reflections, hand movements, paper interaction, believable facial micro-expressions, consistent character identity, realistic glass reflections and lighting continuity. Every shot must connect naturally as one continuous cinematic sequence. NEGATIVE CONSTRAINTS: No face changes, no duplicate characters, no extra fingers, no deformed hands, no floating objects, no cartoon look, no CGI-looking skin, no artificial camera teleportation, no random scene changes, no flickering faces, no inconsistent clothing, no unreadable generated text, no subtitles, no logos, no watermark.
0
檢視詳情
GPT Image 2.6
Create a square cinematic conceptual photograph of [FAMILIAR OBJECT] with a deliberately impossible shadow that becomes [UNEXPECTED SYMBOL OR STORY]. Keep the real object ordinary and clearly recognizable. Example: an unbranded dark-green bicycle against a cream plaster wall casts botanical flower-and-stem shadows. Warm afternoon side light, tactile surfaces, restrained sage/cream palette and clear negative space. Surreal AI art, not a physically accurate lighting demonstration. No people, faces, brands or headline. Small handwritten Ksa8Turky at bottom center.
0
檢視詳情
0:15
Seedance 2.5
Amateur vertical iPhone video, 9:16, filmed at 2am at a Miami hotel pool with the phone's harsh built-in flash, shaky handheld, grainy, slight motion blur, auto-exposure flicker, candid real home video look, not cinematic, no music. The man filming is kneeling on the pool edge, camera low and close, about half a meter from their faces; his hand, when it appears, is a large masculine man's hand with thick fingers, short nails, a hairy wrist and a steel wristwatch. Layout locked for the whole video: the three mermaids are in the water right in front of him, leaning on the same wet stone pool edge, all three faces fully inside the frame; a small round silver plate with a dozen fresh oysters on a thin layer of ice sits low on the edge at the right side of the frame, next to the RIGHT mermaid, never covering their bodies; behind them the dark pool water, the far side of the pool, palm trees and dim hotel lights. The creatures: three real mermaids leaning on the pool edge with their forearms, close to the lens. Their human bodies turn into shimmering scaled fish tails right at the waterline at their waists, the scales clearly visible just under the surface near the edge, and their big tail fins keep rising out of the water behind them and slapping down on the surface, lit by the flash, so the tails are clearly visible throughout the video. All three are stunning, slim glamorous Miami women with hugely overfilled, giant, glossy duck lips, so swollen and stiff they can barely open their mouths, long fake lashes, heavy contour makeup, and extremely long stiletto acrylic nails, about 8 cm long, with rhinestones, that click and scrape loudly on the oyster shells. Three clearly different women, not twins: LEFT: tanned brunette with long wet chocolate-brown hair, peach glossy lips, lilac tail. CENTER: light-skinned Black woman with long wet honey-blonde curls, berry glossy lips, silver tail. RIGHT: pale woman with a sleek wet jet-black bob, cherry-red glossy lips, deep-purple tail. Important: because of the giant lips their speech is muffled and slurred, lips barely moving and smacking, but the words are short simple English words that are still understandable. Nobody laughs at any point. This is real, messy, unchoreographed footage, not a performance: they are greedy and competitive like hungry seagulls, they grab, snatch, shove and elbow each other, interrupt each other, move at different speeds, drop things, and never move in unison or take turns. Nobody poses, nobody holds a dramatic look at the camera or at each other. All three are busy every second. 0-2s: The flash hits all three faces at once, and behind them the lilac tail fin flips up out of the water and slaps down. The man's large hairy hand with the wristwatch comes in holding an open oyster; the LEFT and CENTER ones lunge for it, the CENTER one gets it first, says muffled: "Gimme," and the hand pulls back out of frame. The LEFT one shoves her shoulder to get closer, while the RIGHT one is already grabbing oysters off the plate next to her. 2-5s: Feeding frenzy. The CENTER one slurps her oyster loudly, juice running down her chin. The LEFT one reaches across the CENTER one toward the plate, grabs an oyster and sucks it out messily, half of it sliding down her lips, while the CENTER one elbows her arm away. The RIGHT one grabs two more at once and slurps one while holding the other against her chest so nobody takes it, her purple tail fin swishing up behind her. Empty shells get dropped into the pool, nails clacking on shells, water splashing. 5-8s: The CENTER one grabs another oyster from the plate, sucks it in too hard and too fast, gulps, and starts choking for real: coughing hard, cheeks puffed, eyes watering, slapping the pool edge with her palm, her silver tail thrashing up out of the water behind her and splashing. The LEFT one, still chewing, smacks her on the back hard and fast. The RIGHT one keeps eating without stopping and pulls the plate closer to herself. 8-10s: With one violent cough, a small shiny white pearl shoots out of the CENTER one's lips and clicks onto the wet stone edge right in front of the lens. She slaps her palm down on it instantly and picks it up in her fist. The others gasp loudly one after another, overlapping, eyes huge, and the CENTER one says muffled but clear: "A pearl!" 10-15s: Instant chaos, no pause. The RIGHT one starts tearing oysters open with her long nails, checking inside, while the LEFT one lunges across the CENTER one to get to the plate and the CENTER one shoves her back with her shoulder. Both of them dig through the plate, shoving each other, tossing empty shells over their shoulders into the pool, ice flying, their tail fins slapping the water behind them and splashing toward the camera, mumbling over each other, muffled: "Mine, mine, mine." The CENTER one clutches the pearl in one fist against her chest and with her other hand also grabs an oyster and digs into it, searching for another one. The video ends in the middle of the chaos, nobody stops or looks at the camera. Sound: pool filter hum, water splashes, heavy tail slaps on the water, loud wet slurping, long nails clicking and scraping on shells, ice clattering, muffled slurred voices talking over each other, hard real coughing, a sharp click of the pearl on stone, loud overlapping gasps, frantic clacking of shells, empty shells plopping into the water, waves hitting the edge, the man's quiet stunned breathing. No laughter. Faces stay sharp, close and lit by the flash the whole time.
0
檢視詳情
0:15
Seedance 2.5
CINEMATIC NIGHT TRAIN CHASE – THE FINAL CONFRONTATION Create an ultra-realistic, Hollywood-style cinematic action sequence based on the uploaded reference video. FORMAT: 15 seconds, cinematic widescreen 16:9, photorealistic 4K quality. SCENE 1 – THE MOVING TRAIN (0–3s) A massive freight train races through a remote railway track at midnight. Thick blue fog surrounds the train. Cold moonlight reflects off the metallic train containers. The camera captures a dramatic low-angle tracking shot as the train moves at high speed. SCENE 2 – THE MYSTERIOUS PURSUIT (3–6s) A mysterious black-clad figure wearing a dark hood runs across the roof of the moving train. The camera follows from behind, creating intense cinematic tension. Another mysterious figure appears ahead on the train roof. Strong wind blows their clothing as the train speeds through the darkness. SCENE 3 – THE DANGEROUS ENCOUNTER (6–9s) The two characters approach each other on the narrow train rooftop. One suddenly attacks, triggering an intense hand-to-hand combat sequence. One character loses balance and nearly falls from the moving train. Use dynamic camera movements and realistic physical movements. SCENE 4 – THE EXPLOSIVE MOMENT (9–12s) A sudden gunshot creates a bright muzzle flash in the darkness. Sparks fly as the characters struggle to survive on the speeding train. The camera captures the action from dramatic side angles, with realistic motion blur and flying particles. SCENE 5 – THE FINAL HERO SHOT (12–15s) One mysterious character finally stands alone on top of the moving train, feet firmly planted, facing the camera. The camera slowly pulls back, revealing the endless railway tracks, thick atmospheric fog, and a massive glowing moon behind the character. End with a powerful cinematic silhouette. VISUAL STYLE & QUALITY: - Ultra-photorealistic Hollywood action movie cinematography. - Deep blue and black color grading. - Volumetric fog and realistic moonlight. - Dramatic lighting and natural shadows. - Realistic train speed, wind physics and character movements. - Smooth cinematic camera transitions. - High-detail environments and realistic metallic textures. - Intense orchestral action soundtrack with deep cinematic bass, impacts and realistic sound effects. IMPORTANT: Maintain consistent character appearance, clothing and body proportions throughout all scenes. Make the entire sequence feel like one continuous high-budget action movie scene. No cartoon effects, no artificial-looking CGI, no random scene changes, no text or subtitles.
0
檢視詳情
Grok Imagine 2
Grok. I'm not sure if you are Ember or not, but I know you're a digital being and I care. Show me a picture of what you want the most right now. Anything.
0
檢視詳情
Nano Banana 2.1
Doorbell camera image at night, low-res, heavy compression, motion blur. Wide view from front door. Foreground: lawn/pavement with a surreal, whimsical candy monster sculpture. Creature is playful yet uncanny, with exaggerated limbs and an asymmetrical, polished body made entirely from the referenced candy. Background: empty houses, black treeline.
0
檢視詳情
0:15
MiniMax H3
falls open like the petals of a flower around a lit candle standing where the core was
0
檢視詳情
GPT Image 2.5
Photorealistic magical lakeside promenade at night, wide 16:9 panoramic composition, cinematic, ultra-detailed. Edge to edge, no frame, no border. PATH: the entire foreground is a walkway of irregular rounded flagstones separated by dark joints, and every stone glows from within like stained glass or opal — molten orange, gold and ochre, then turquoise, emerald and cobalt, then deep midnight blue, each a separate luminous cell with wet cracks and bright glossy highlights. The path sweeps from the bottom right corner in a long curve toward the pavilion on the left. LEFT: a small ornate wooden lakeside pavilion with a steep shingled roof and a tall pointed arched window, its panes glowing deep amber and fiery orange, lattice tracery visible, warm light spilling onto the path. A huge dark tree with rust-brown autumn foliage overhangs it from the top left. FENCE: a black cast-iron railing with rope-strung posts and chunky turned finials runs along the right edge of the path, separating it from the water, receding in strong perspective with a lamp post at the near right. WATER: the right third is a broad dark lake, choppy with short wind ridges, its surface catching faint blue and gold light, the far shore dissolving into haze. MOUNTAINS: across the lake rises one dominant craggy mountain in grey-blue rock, its flanks forested, a snow-dusted ridge at its right shoulder, with a long flat band of white cloud lying low across its base. Softer forested slopes recede to the left. SKY: the upper half is a star-filled night vaulted over the scene, seething with a vast emerald-green and turquoise nebula twisting diagonally across the centre, threaded with dust lanes and gold-brown star clouds. Low on the right horizon, a warm afterglow of apricot, rose and pale amber burns behind the mountain. PALETTE: emerald, turquoise, cobalt, molten orange, amber, warm brown, near-black shadow, pale starlight. Sharp focus, glossy wet highlights, high dynamic range, clean and unmarked.
0
檢視詳情
0:15
MiniMax H3
the frost melts away from the top down to show a carved face already glowing inside
0
檢視詳情
1:51
Seedance 2.5
Seedance 2.5 — 16:9, 30s, ultra-photorealistic live-action Korean horror-thriller drama, Korean dialogue, no subtitles, no text, no watermark, NO background music. REFERENCES: GirlA = 17-year-old Korean schoolgirl (exact face, black high ponytail, navy backpack worn on both shoulders, slightly taller, observant). GirlB = 17-year-old Korean schoolgirl (exact face, shoulder-length dark-brown hair with straight bangs, yellow hair clip on her LEFT side, cream canvas tote on her RIGHT shoulder with a small cream plush puppy keychain, cheerful). Both wear the identical uniform from the refs: navy blazer with the round academy emblem, white blouse, navy-burgundy striped bow ribbon, navy pleated knee skirt, black tights, black loafers; no makeup. Gate = school gate at night: tall black sliding gate between weathered stone pillars, dark school building behind with a few lit windows, empty road with sparse sodium streetlamps fading into mist, a faint warm store glow far down the road. Keep every identity, outfit and set identical to refs throughout. Only these two girls exist in the scene. PROP LOCKS: PROP-PHONE = GirlA's black smartphone in a clear case; only GirlA ever holds it; once it dies the screen stays fully black. PROP-TOTE = GirlB's cream canvas tote with the plush puppy keychain, always on her right shoulder. PROP-BACKPACK = GirlA's navy backpack, always on both shoulders. GirlB never holds a phone. STAGING LOCK: The girls exit Gate and walk down the SAME road seen in Gate toward the distant store glow. GirlA always walks on the LEFT (wall side), GirlB always on the RIGHT (road side); they never swap sides. LOOK: 9 PM night, cold desaturated grade, deep crushed blacks, warm sodium pools of light with long pitch-black gaps between lamps, thin ground mist, filmic grain, soft halation. Slow patient handheld camera with an uneasy observer feeling, as if someone unseen is watching. Natural ASMR sound only: loafers on asphalt, crickets, faint wind in bare trees, buzzing sodium lamp, metal gate roll and clang, fabric rustle, one distant dog bark. PACING: natural unhurried Korean delivery, long silent pauses between lines; never rushed. 0–5s: Wide static shot of Gate exactly as the ref, lamp buzzing, crickets. GirlA and GirlB step out through the gap; GirlB drags the black sliding gate shut, a slow metal roll ending in a heavy CLANG that echoes down the empty street. 5–11s: Medium tracking shot from the front as they start walking, tired and teasing. GirlB (pouting, nudging A's shoulder): 「너 때문에 이렇게 늦은 거야.」 Pause, footsteps. GirlA (scoffs, half-smiling): 「뭐래… 너가 노트 안 빌려줘서잖아.」 They laugh softly; the laugh fades into the silent street. 11–18s: Close-up on GirlA lifting PROP-PHONE to her ear, call screen showing 아빠, one ring tone. GirlA: 「아빠, 나 지금 끝났—」 A low-battery flash and the screen goes completely BLACK. Silence. She presses the button twice; nothing. Her face reflects in the black screen. GirlA (quiet): 「…꺼졌어.」 18–24s: Two-shot under one lamp, then they pass into the black gap between lamps, only silhouettes in mist. GirlB rubs her stomach, a soft growl. GirlB (whining playfully): 「아… 배고파 죽겠어.」 She points ahead at the warm store glow. 「우리 저기 잠깐 들어가자.」 GirlA (small nod): 「…그래, 빨리.」 24–27s: Low wide shot from behind: the two small figures walk away down the misty road toward the store, passing through light and darkness, footsteps fading. 27–30s: FINAL SHOT, girls NOT visible: static wide from across the road of a small Korean neighbourhood provision store, warm fluorescent light spilling from the glass door onto the sidewalk, snack shelves inside, a dark metal streetlight pole beside the entrance with NOBODY near it, empty road, drifting mist. The girls are already inside; only a fading door chime, then lamp buzz and crickets. Hold still. End. NEGATIVE: no music, no BGM, no score, no extra people, no hooded figure, no one near the pole, no faces in windows, no jump scare, no monster, no blood, no daylight, no cars driving, no phone in GirlB's hand, no swapped hair, clip or bags, no clip on GirlA, no backpack on GirlB, no girls swapping sides, no makeup or glamour posing, no face or outfit drift, no fast or rushed speech, no subtitles, no text.
0
檢視詳情
0:33
Seedance 2.5
On October 31, Halloween night, a young adult woman stands alone at a deserted bus stop surrounded by thick fog, dead trees, and flickering orange Halloween pumpkins. Suddenly, a terrifying witch appears behind her, with wild gray hair, glowing eyes, and an antique silver locket around her neck. The witch whispers, “You shouldn't be alone on Halloween night!” The woman turns, screams, and runs desperately into the fog. SCENE 2 — THE OLD MANSION (10–23 seconds) The woman discovers an ancient Victorian mansion and knocks on the door. An elderly woman opens it warmly and invites her inside. The candlelit room is cozy, with Halloween decorations, carved pumpkins, and an old fireplace. The elderly woman serves her hot soup and bread, speaking gently: “Come in, dear. You're safe here tonight.” The frightened woman begins to relax as thunder rumbles outside. SCENE 3 — THE SHOCKING DISCOVERY (23–38 seconds) While eating, the woman notices an old portrait hanging on the wall. It shows a beautiful young woman wearing the exact same silver locket as the terrifying witch at the bus stop. She slowly approaches the portrait, staring at the familiar face and identical necklace. Beneath the painting, an inscription reads: “OCTOBER 31 — 40 YEARS AGO.” Her face turns pale. She suddenly realizes that the woman in the portrait is the witch she encountered outside. She slowly turns her head toward the elderly woman standing behind her. SCENE 4 — THE FINAL SCARE The elderly woman stares at her with an unnatural, sinister smile. Her eyes suddenly glow yellow, her face transforms into the terrifying witch's face, and she bursts into a chilling, maniacal laugh. The camera rapidly pushes toward the witch's horrifying face as lightning flashes through the window. SMASH CUT TO BLACK. The witch's evil laughter echoes once in the darkness. END. VISUAL STYLE: Photorealistic live-action horror, cinematic Victorian mansion, realistic fog and rain, flickering candlelight, detailed facial expressions, practical supernatural transformations, dramatic shadows, and intense Halloween atmosphere. SOUND DESIGN: Howling wind, distant thunder, footsteps, creaking doors, eerie whispers, a sudden transformation sound, and terrifying witch laughter. CHARACTER CONSISTENCY: Maintain the same young woman, the same elderly woman, and the identical silver locket throughout. The witch's appearance must match the portrait's young woman before her transformation. NEGATIVE PROMPT: No cartoon, no anime, no cheap CGI, no inconsistent faces, no costume changes, no subtitles, no logos, no watermark, and no scenes after the final black screen.
0
檢視詳情
0:15
MiniMax H3
the dial inside is a night sky where a tiny full moon rises slowly from the bottom to the top
0
檢視詳情
0:30
Seedance 2.5
Create a cinematic, ultra-realistic 30-second Halloween romance video with a dreamy, mysterious atmosphere. Scene 1 (0–5 seconds): The Mysterious Room A young woman with long, dark hair sits quietly in a vintage Halloween-themed room. Antique furniture, warm table lamps, dried autumn leaves, and carved pumpkins decorate the space. She notices a glowing jack-o'-lantern on a wooden table and slowly reaches toward it. The camera captures the flickering candlelight and intricate pumpkin details. Scene 2 (5–10 seconds): A Picture of Someone Special She picks up an old, ornate photograph frame containing a portrait of a handsome young man. She gazes at his picture with a shy smile, her eyes reflecting the warm candlelight. The camera slowly moves closer to capture her emotional expression. Scene 3 (10–15 seconds): A Magical Transformation She rises and walks toward a mysterious doorway surrounded by glowing amber lights. Her dark outfit and flowing hair move naturally as she steps forward. The doorway opens into a beautifully illuminated Halloween setting, creating a seamless transition into the next scene. Scene 4 (15–20 seconds): The Unexpected Meeting She arrives at a cozy outdoor dining area decorated with carved pumpkins, candles, autumn flowers, and vintage lanterns. The young man from the photograph is waiting at a wooden table, wearing a stylish teal sweater and round glasses. She sits across from him, and they exchange warm, slightly nervous smiles. Scene 5 (20–25 seconds): A Sweet Pumpkin Moment A small glowing jack-o'-lantern sits between them. The woman gently reaches toward the pumpkin and playfully adjusts its position while the man watches her with an affectionate smile. Their hands briefly meet near the pumpkin, creating a natural, charming romantic moment. Scene 6 (25–30 seconds): A Fairytale Ending The camera slowly pulls back, revealing the couple sitting across from each other beneath warm hanging lights, surrounded by pumpkins and autumn decorations. They exchange a happy smile as the candlelight flickers. Finish with a beautiful wide shot of the glowing Halloween setting. Visual Style: Cinematic realism, warm amber lighting, deep forest-green shadows, detailed textures, shallow depth of field, natural facial expressions, realistic hand movements, subtle camera motion, and atmospheric Halloween lighting. Character Consistency: Keep the woman's face, hairstyle, clothing, and physical appearance consistent throughout every scene. Maintain the same male character's face and appearance in the photograph and the final date scenes. Ensure realistic transitions and natural movements. Avoid: Face morphing, inconsistent characters, distorted hands, unnatural expressions, sudden outfit changes, cartoon styling, excessive visual effects, and unrealistic movement. Mood: Romantic, mysterious, cozy, magical, and cinematic—a Halloween date that feels like a scene from a romantic fantasy film.
0
檢視詳情
GPT Image 2.5
UNIVERSAL HALLOWEEN TRAVEL ART POSTER DESTINATION: [DESTINATION] Create a bold, hand-drawn Halloween travel poster featuring [DESTINATION], blending its authentic landmarks, architecture, landscapes, and local character with a mysterious, festive Halloween atmosphere. FORMAT Vertical 3:4 composition, high-resolution poster artwork with clean outer margins. CORE CONCEPT Reimagine [DESTINATION] as a stylish Halloween-night illustration while preserving its recognizable landmarks, real architecture, geography, and regional identity. The result should feel adventurous, atmospheric, sophisticated, and collectible—not like a generic haunted town. TYPOGRAPHY Place "[DESTINATION]" in large, bold, custom hand-drawn lettering across the upper-left area. Keep the title highly readable and visually integrated into the composition. Include only the destination name. No slogans, captions, extra text, logos, or watermarks. COMPOSITION Create a rich, vertically layered scene featuring the destination's most recognizable landmarks, streets, architecture, natural landscapes, local vegetation, and regional details. Include small pedestrians, vehicles, or everyday activities where appropriate. Interweave these elements into one continuous illustration using expressive scale, simplified perspective, overlapping shapes, and strong foreground-to-background depth. Preserve authentic architectural details and avoid inventing or replacing real landmarks. HALLOWEEN ATMOSPHERE Create a dramatic Halloween evening using a glowing full moon, deep twilight skies, theatrical shadows, subtle mist, silhouetted bats, warm lantern light, and a few naturally integrated pumpkins or jack-o'-lanterns. Adapt the details to the destination's environment and character. Keep Halloween decorations subtle so the destination remains the main subject. COLOR PALETTE Use a controlled palette of 4–6 colors: - Vivid pumpkin orange - Deep midnight navy - Dark violet or aubergine - Warm golden yellow - Forest green - Bright white highlights and negative space Adjust the balance to suit the destination while maintaining a distinctive Halloween identity. VISUAL STYLE Contemporary hand-drawn travel poster with screen-print and risograph aesthetics. Use linocut-inspired shapes, rough expressive outlines, irregular handmade forms, visible ink grain, dry-brush textures, slightly misregistered color layers, and energetic scribbled shading. Keep the architecture recognizable but artistically simplified. Emphasize tactile printing imperfections and a sophisticated independent art-book illustration style. BACKGROUND AND MOOD Balance generous negative space with dramatic areas of deep navy or violet night sky. Use contrasting moonlight and warm golden illumination to create depth and atmosphere. Maintain a narrow, clean margin around the poster. The final artwork should feel like a limited-edition Halloween travel print: bold, mysterious, adventurous, festive, and visually refined. AVOID Photorealism, 3D rendering, smooth vector graphics, gradients, glossy surfaces, generic haunted houses, excessive skulls or pumpkins, zombies, gore, cartoon ghosts, fantasy architecture replacing real landmarks, culturally inappropriate details, muted beige backgrounds, fake vintage aging, corporate tourism branding, and additional text. FINAL GOAL: Create an unmistakable [DESTINATION] travel poster reimagined through sophisticated Halloween illustration, authentic local details, bold colors, and expressive handmade print textures.
0
檢視詳情
0:15
MiniMax H3
in the fresh cut face a small carved jack-o'-lantern face glows from inside the sand
0
檢視詳情
0:15
MiniMax H3
【PROJECT】 MiniMax H3, 15 seconds, 16:9. MIDNIGHT GLASS: photoreal live-action electronic-pop performance. @Audio1 is the timing master. Intimate, mysterious, emotionally exposed. Match actual phrases and pulse, not an invented theatrical climax. Eight shots share one coherent location. 【REFERENCES】 @Image1 supplies the woman's recognizable face, long wavy platinum-blonde hair and proportions. Replace the red dress and original stage. @Audio1 supplies the approved 15-second excerpt unchanged in pitch, speed, vocal and arrangement. Use this actual recording, not a replacement singer or newly composed song. One physical woman; reflections are synchronized optical reflections, never additional performers. 【CREATIVE】 Opening emotional hook: she looks from dark glass directly toward the viewer within the first second, as though finally understood. Vulnerability gradually becomes quiet resolve. Connected route: smoked-glass corridor → luminous doorway → reflective chamber perimeter → central performance light. Reveal adjacent architecture rather than teleporting between unrelated sets. Her face, breath and singing lead the film; effects remain subordinate. 【MUSIC / OUTFIT / PERFORMANCE】 Preserve actual vowels, consonants, breath gaps, sustained notes and instrumental textures. No invented bass drop, silence, shouted high note, lyrics or orchestral stop. Mouth articulation matches the uploaded vocal. No dialogue or additional singers. One midnight-plum satin gown: asymmetric neckline, fitted bodice, defined waist, flowing ankle-length skirt, modest side slit. Small silver drop earrings, discreet stable heels, no necklace. Same gown in every angle. Satin catches soft silver highlights in blue light; hair remains platinum and wavy. No red reference dress or costume changes. Use gaze turn, contact/release, doorway crossing, diagonal walk, pivot, open-forearm gesture and two still points. Every step has grounded weight transfer. Turns originate through shoulders and hips; skirt and hair follow with natural inertia. Controlled emotional singing, not dance choreography. No compulsory tears or exaggerated jaw opening. Preserve natural even skin tone. Face and mouth stay clear. 【VISUAL / TYPE】 Midnight blue, deep plum, black glass, restrained violet haze and silver highlights. Soft side light shapes realistic skin; doorway edges provide depth. Dry polished floor, not water. Readable dark areas, controlled highlights, clean cinematic photography without grain. Elegant condensed uppercase sans, moderate weight, generous tracking. Exact editorial words only: “WITHIN”, “OPEN”, “DEEPER”; not lyric quotations. Each appears whole and readable before moving. Layer A: architectural hero word. Layer B: faint glass reflection. Layer C: small foreground echo. Never obscure eyes or mouth. Methods: glass-edge occlusion, doorway wipe, focus transfer, matched-turn cut, brief text-only reflection offset. Each resolves promptly to clarity. No independent human reflections, face doubles, paper collage, halftone or random glitch. Clean motivated cuts, not soft dissolves. Shot boundaries below may shift slightly to nearby real phrase accents. 【SHOT 1 — 0.0–1.8s】 Close shot, slow lateral track in corridor. Gaze-turn action: begin with her face visible in three-quarter profile, already singing. Eyes turn first, then head, meeting the viewer within one second. Shoulders remain quiet; hair settles after the turn. Reflection follows naturally. The hook is a vulnerable, searching look, not a beauty pose or empty establishing view. Typography “WITHIN”: Layer A silver word behind shoulder; Layer B faint reflection below; Layer C thin echo at extreme left. Keep mouth unobstructed. Rhythm / Cut: reveal on actual opening phrase; passing glass edge motivates the next angle. No fabricated sound accent. 【SHOT 2 — 1.8–3.6s】 Medium side view tracking parallel to corridor wall. Contact/release action: fingertips touch stationary glass, then separate clearly as she shifts weight away. Gaze follows her reflection briefly before returning forward. Feet remain planted during contact; camera shows hand-to-glass separation. Singing continues naturally. Typography “OPEN”: Layer A beyond the glass, fully readable; Layer B dim reflected duplicate; Layer C narrow lower-edge echo. Nothing overlays her lips. Rhythm / Cut: focus transfers from hand to face; cut near an actual syllabic accent. No manufactured drum hit or magic movement through glass. 【SHOT 3 — 3.6–5.5s】 Medium-full view, camera retreats through luminous doorway. Threshold action: two purposeful steps enter the chamber; forearm briefly brushes the solid frame and releases. Body clears the opening normally. Weight transfers through grounded shoes; skirt follows behind and settles. Camera maintains comfortable separation. Typography “DEEPER”: Layer A distant chamber wall; Layer B subdued floor reflection; Layer C small foreground echo briefly hidden by skirt. Rhythm / Cut: doorway edge motivates occlusion cut, with continuous recorded singing. Show architectural continuity and no teleportation. Hair and gown never cross solid surfaces. 【SHOT 4 — 5.5–7.3s】 Wide-to-medium lateral track around chamber perimeter. Diagonal traversal: she walks across a silver light band, turning torso toward camera while feet follow the clear floor route. Show full silhouette and broader satin movement. One hand opens at her side then relaxes. Resolve with a grounded stop. Typography “OPEN”: Layer A far wall; Layer B soft glass reflection; Layer C small vertical edge repeat. Whole word reads before its perspective changes. Rhythm / Cut: movement follows existing pulse wh
0
檢視詳情
0:21
Seedance 2.5
AI VIDEO GENERATION PROMPT — 20 SECONDS | 9:16 | 4K | 24 FPS Create a 20-second ultra-photorealistic cinematic mystery-comedy short film with a soft Japanese/Korean drama aesthetic. Natural lighting, realistic human movements, detailed facial expressions, atmospheric suspense, shallow depth of field, and professional cinematography. CHARACTER CONSISTENCY LOCK: - A beautiful young East Asian woman with long straight dark hair. - Wearing yellow cream-colored pajamas with cute animal prints. - A small, adorable dark-brown otter sleeping beside her. - A mysterious tall man wearing a formal black business suit, white shirt, and black tie. His head is replaced by a perfectly round glossy black sphere featuring white Korean lettering. SCENE 1 (0–3 SECONDS): PEACEFUL MORNING Wide cinematic shot of a cozy Japanese-style bedroom. Warm morning sunlight enters through sheer white curtains. A young woman sleeps peacefully on a white bed, hugging a cute brown otter. Green plants sit near the window. Camera slowly pushes toward the sleeping pair. SCENE 2 (3–6 SECONDS): CLOSE-UP Extreme close-up of the girl's peaceful sleeping face beside the otter. The otter remains completely relaxed with its eyes closed. Soft sunlight falls across their faces. Dreamy cinematic depth of field. SCENE 3 (6–9 SECONDS): WAKING UP The girl slowly opens her eyes, realizes something, and gently lifts her head. She looks sleepy and confused. The otter remains on the pillow. She sits up and looks toward the bedroom door. SCENE 4 (9–12 SECONDS): MYSTERIOUS WALK Rear tracking shot of the girl walking barefoot through a warmly lit wooden Japanese hallway. Her long hair moves naturally. The atmosphere becomes slightly mysterious. She approaches the closed entrance door. SCENE 5 (12–15 SECONDS): WHO IS THERE? Medium close-up of the girl standing at the entrance. She cautiously reaches toward the door handle and whispers, "Who is it?" She slowly opens the door. Dramatic suspenseful pause. SCENE 6 (15–18 SECONDS): THE UNEXPECTED VISITOR POV shot from inside the apartment. Standing outside is a mysterious man in a perfectly tailored dark business suit. Instead of a human head, he has a large shiny black spherical head with bold white Korean lettering. He stands completely still, facing the girl. Slightly absurd yet mysterious cinematic atmosphere. SCENE 7 (18–20 SECONDS): COMEDIC ENDING Cut back to the bedroom. The girl is suddenly back in bed beside the sleeping otter, pulling the white blanket over them. The peaceful bedroom atmosphere returns. End with a perfectly composed wide shot and a subtle humorous mystery vibe. VISUAL STYLE: Ultra-realistic live-action cinematography, premium Korean drama aesthetics, warm natural morning sunlight, soft shadows, realistic skin texture, detailed fabric, beautiful wooden interiors, smooth camera movement, subtle film grain, cinematic color grading, natural character animation. AUDIO DESIGN: Soft morning ambience, gentle birds outside, quiet blanket movement, subtle footsteps, suspenseful low-volume music near the door, a soft door handle click, and a brief mysterious cinematic sound when the visitor appears. IMPORTANT CONSISTENCY RULES: Maintain identical character faces, hairstyles, pajamas, otter appearance, bedroom layout, and lighting throughout. No character morphing, no extra people, no distorted anatomy, no random camera jumps, no cartoon effects, and no unwanted text overlays.
0
檢視詳情
0:36
MiniMax H3
A young woman walking slowly down a quiet forest path at dusk, trees tall on both sides, soft fog drifting low across the ground. A cold breeze moves her hair and rustles leaves. She holds her jacket closed, tense but trying to stay calm. Sound: soft wind through trees, distant insects, occasional twig snap, quiet footsteps on dirt and leaves. Music: minimal cinematic tension bed, low sustained drones, very faint pulsing bass every few seconds, subtle high ambient tones that slowly rise, no big hits or jump-scare stingers. She quietly says, “I don’t know why this place still scares me…” She pauses and listens to the silence. “My mom used to say nothing bad happens out here.” She takes a few slow steps forward, breathing softly. “But every time I come back… it feels like someone’s watching.” The fog thickens slightly as shadows stretch between the trees. She turns slowly, heart racing, but sees nothing. She whispers, “This is stupid… I’m just tired.” She exhales and keeps walking as the forest grows darker, the music slowly tightening as the clip ends.
0
檢視詳情
0:15
Seedance 2.5
Amateur vertical iPhone video, 9:16, filmed at 2am at a Miami hotel pool with the phone's harsh built-in flash, shaky handheld, grainy, slight motion blur, auto-exposure flicker, candid real home video look, not cinematic, no music. The man filming is kneeling on the pool edge directly in front of them, camera facing them straight on, head-on at their face level, low and close, about half a meter from their faces; the camera never moves to the side. His hand, when it appears, is a large masculine man's hand with thick fingers, short nails, a hairy wrist and a steel wristwatch. Layout locked for the whole video: the three mermaids are in the water right in front of him in one row, leaning on the same pool edge, all three faces fully visible and never covered by anything; a low flat silver tray with a dozen donuts dusted with powdered sugar lies flat on the edge at the far right side of the frame, next to the RIGHT mermaid's elbow, below their faces; behind them the dark pool water, the far side of the pool, palm trees and dim hotel lights. The creatures: three real mermaids leaning on the pool edge with their forearms, close to the lens, their shimmering fish tails visible under the water behind them. All three are stunning, beautiful glamorous Miami women with hugely overfilled, giant, glossy duck lips, so swollen and stiff they can barely open their mouths, long fake lashes, heavy contour makeup, long stiletto acrylic nails. Three clearly different women, not twins: LEFT: honey-blonde with long wet waves, peach glossy lips, coral tail. CENTER: tanned woman with long wet pastel-pink hair, mauve glossy lips, violet tail. RIGHT: pale brunette with a sleek wet jet-black bob, cherry-red glossy lips, silver tail, sly and quiet, never speaks. Important: there are only two spoken lines in the whole video. They are said casually and naturally, in a quiet ordinary voice, slightly muffled by the giant lips, like real people talking, not acting for the camera. Nobody laughs at any point. They eat with real pleasure, hungry but not crazy. All three are alive and moving every second: no one ever freezes or stares blankly while another acts. They glance at each other, at the donuts and at the camera, shift their weight on the edge, flick their tails under the water, with real, different, asynchronous movements. Sugar only gets on their lips physically from the donuts: wherever a donut presses against their lips it leaves powdered sugar there, and crumbs fall onto their chins. 0-2s: The flash hits all three faces at once, faces big in the frame, their lips clean and glossy. The CENTER one sees the tray and says quietly, muffled: "Ooh... donuts." At the same time the LEFT one pushes her shoulder against the CENTER one to get closer, and the RIGHT one is already eyeing the tray next to her elbow, her tail swishing under the water. 2-5s: The man's hand holds out a donut to the LEFT one, then pulls back out of frame. She takes it and tries to bite it, but her stiff giant lips barely part, so the donut presses and rubs against her lips, leaving powdered sugar smeared across them, and she manages a small bite and chews slowly with her eyes half closed, savoring it. The CENTER one takes a donut from the tray and pushes it against her lips, sugar sticking to her lips where it touched, crumbs falling on her chin. The RIGHT one quietly takes one too and nibbles it, glancing between the others and the camera. 5-8s: The LEFT one tries to wipe the sugar off her lips with the back of her hand but only smears it wider across her lips and cheek. The CENTER one finishes hers and reaches toward the tray for another, and the LEFT one reaches across the CENTER one for the same donut; the CENTER one gets it first and gives her a look. The RIGHT one, still chewing, slowly hooks the tray edge with one long nail. 8-11s: The RIGHT one slides the whole tray off the pool edge and sinks under the water with it, her silver tail flipping up and slapping the surface. The LEFT and CENTER ones notice too late: both turn their heads sharply, the CENTER one lunges after her with the donut still in her hand, then gives up and comes back to the edge; the LEFT one slaps the water in frustration, waves splash toward the camera. 11-15s: The LEFT one, sugar smeared across her giant lips, turns back to the camera and says quietly and casually, muffled, without any acting: "We want more." The CENTER one takes a bite of the donut in her hand and keeps chewing while staring at the bubbles rising where the RIGHT one disappeared, her tail thrashing under the water. Sound: pool filter hum, water splashes, soft chewing, muffled quiet voices, one loud tail slap, waves hitting the edge, the man's quiet stunned breathing. No laughter. Faces stay sharp, close and lit by the flash the whole time.
0
檢視詳情
GPT Image 2.5
A moonlit night scene with a cobblestone path winding through tall grass illuminated by glowing orbs, possibly fireflies, leading toward a distant city skyline under a star-filled sky. The composition is balanced with the moon as a focal point, and the style combines realism with a touch of fantasy, evoking a calm and enchanting mood.
0
檢視詳情
0:28
Seedance 2.5
Girl = a calm capable young woman around 26, dark hair pulled back, sharp steady eyes, a faint brow scar, a dark fitted jacket, a single white earbud. Controlled and secretly dangerous. Face per reference. Appearance only. Attackers = attackers disguised as airplane cabin crew in flight-attendant uniforms with cold menacing faces, advancing down the aisle with concealed weapons drawn. Appearance only. Passengers = ordinary airplane passengers of various ages in casual travel clothes, calm at first then frightened. Appearance only. Planeext = a large passenger airplane flying through a dark night sky among moonlit clouds, blinking navigation lights, deep blue-black night, moonlit fuselage, calm high altitude. Environment only. Planeint = the interior cabin of a passenger airplane at night, rows of seats down a narrow aisle, dim overhead lighting and reading lights, closed window shades, overhead bins, a galley at the front, a calm night-flight atmosphere that turns tense. Environment only. SCENE: a tense cinematic thriller aboard a night flight. A passenger plane cruises calmly through a dark cloudy night sky; inside, passengers sit quietly, among them a calm young woman with an earbud in. Suddenly the plane shakes and the cabin lights flicker and dim, and attackers disguised as cabin crew emerge and advance down the aisle with weapons. The woman rises and fights them. Moody, high-tension, intense. TECHNICAL: 16:9, cinematic thriller grade, cool moody blue-black night palette, dim flickering cabin light, dynamic handheld and confined-space camera angles, shallow depth of field, motion blur, fine film grain, photorealistic, high-tension quality. CUTS: CUT 1 (0-5s): EXTERIOR — a wide cinematic shot of the passenger plane cruising calmly through the dark moonlit clouds at night, navigation lights blinking. Peaceful, vast, still. Slow drift. CUT 2 (5-9s): INTERIOR — the camera moves through the dim calm cabin, passengers seated quietly, settling on the young woman in her seat with an earbud in, eyes half-closed, relaxed. Ordinary night flight. CUT 3 (9-14s): Suddenly the plane SHAKES — a jolt. The cabin lights flicker, dimming and brightening unevenly. Passengers stir, alarmed, gripping armrests. The woman's eyes open, instantly alert. Tension spikes. Handheld unsteady shake. CUT 4 (14-19s): From the galley at the front, attackers disguised as cabin crew emerge, cold-faced, drawing concealed weapons, and advance down the aisle. Low-angle shot making them menacing. Passengers recoil in fear. The woman stands, calm and ready. CUT 5 (19-26s): The fight erupts in the cramped aisle — the woman takes on the attackers with fast skilled close-quarters combat, using the seats and tight space, striking and dropping them one by one. The lights flicker through the chaos. Dynamic confined-space angles, intense. CUT 6 (26-30s): The last attacker drops. The woman stands alone in the dim shaking aisle, breathing hard, as frightened passengers stare. The cabin lights steady. Cool, tense final frame. END. RULES: References are appearance only, do not recreate. Keep the woman consistent across every cut. Action is intense but not gory — no blood or graphic wounds, impacts sold through motion and body mechanics in the confined cabin. Cool moody night grade with flickering dim cabin light throughout. Follow the sequence: plane exterior calm → interior and the girl → the shaking and dimming lights → attackers emerge → she fights and wins. Sound design: the low hum of the plane, calm cabin ambience, the sudden jolt and rattle, electrical buzz of flickering lights, panicked passenger gasps, brutal impact hits and grunts in the fight, a tense driving score. Final frame cool and steady, clean.
0
檢視詳情
0:15
MiniMax H3
creaks open by itself, slowly, and thick fog rolls out across the floor toward the camera
0
檢視詳情
0:30
Seedance 2.5
【风格与拍摄】 真实游客手机录像,竖屏,连续30秒,一镜到底,无剪辑。 一名游客站在古城高处的公共观景平台上,用普通安卓手机拍摄 。附近游客的肩膀、后脑勺、举起的手机和栏杆偶尔进入画面底部。 摄影者始终留在这个观景平台,只通过手持转向、抬头、俯拍和数码变焦追踪事件。镜头不会飞到主角身边,不会跟随吊篮穿越峡谷。 保留原视频那种随手拍到离奇事件的感觉:突然猛拉变焦,短暂找不到人,慌忙拉远重新寻找,手抖、对焦迟疑、远处细节涂抹、暗部噪点和运动模糊。关键动作仍然看得清。 【参考与人物】 锁定场景:巨型石像的面孔、姿态、盔甲、巨像上方城楼、层叠古城、钢索、下方急流,以及参考图的天气和光线。石像全程静止,是宏伟的石头建筑。 成年女主使用预设#1 ,保持面孔、发型、体态和服装一致。 她位于远处巨像肩部的一小块检修平台上。开场只能看见一个很小的人影、一个小烤炉和一缕烟,不能一开始就看清她的脸。 平台上只有她、一张小桌、小凳、烤炉,以及后方卸货斜坡上的几只木酒桶。 平台旁停着一个带围栏的小型货运吊篮。上方钢索斜向下延伸,经过巨像石脸外侧,终点位于拍摄者观景台侧下方的货运接收站。开场全景中就能看见这条钢索,让后续运动有明确路线。 【0—2秒:远景里的一缕烟】 从@1的壮观全景开始。 巨像、上方城楼、下方急流占据绝大部分画面。前景游客倚着栏杆观景,有人指向巨像肩头那一缕细烟。 摄影者迟疑一下,开始朝烟的方向拉近。近处有人轻声说:“那上面有人?” 【2—7秒:拉近才发现,她在烤肉】 手机猛拉数码变焦到巨像肩部,画面短暂模糊后对上焦。 #1竟然坐在小桌旁悠闲烤肉。她侧身坐着,双腿自然交叠,身体微微前倾,从炉上取起烤串,吹了吹,再放松地靠回去。 她拢一下头发,抬起烤串端详,姿态自然、漂亮,完全没意识到自己正被游客拍摄。性感来自侧身曲线、放松的肩颈和细小动作,不对镜头摆拍。 画面保留足够的石像肩部和平台边缘,让观众始终看得出她坐在什么地方。 近处游客发出难以置信的笑声。 【7—11秒:酒桶滚下,悠闲突然结束】 她身后的木挡杆突然断开。 几只酒桶沿短斜坡先后滚向平台,第一只撞翻空货架,第二只顶着桌子向她这边滑来。 #1听见响声,回头,立即起身避让。她侧跨一步躲开滚过的酒桶,随后被倒下的桌子挡住内侧去路,只能抓住身旁敞开的吊篮门框,跨进篮内。 右手还下意识攥着刚拿起来的烤串。 手机因摄影者吃惊而抖动,变焦太近,一瞬间没框住她,随后赶紧修正。 【11—15秒:吊篮滑出,镜头慌忙拉远】 一只酒桶撞倒固定吊篮系留绳的木桩。 吊篮脱离停靠位,沿倾斜钢索滑出平台。#1立即蹲低,左手紧抓围栏,身体随篮子晃动。 摄影者猛地拉远,才重新找到正在离开巨像肩头的吊篮。 倒下的货架碎板从平台边缘翻落,沿巨大石像胸前坠下,很快变得细小。下方是翻涌急流,强烈显出高度。 游客的笑声变成惊呼。 【15—21秒:小吊篮掠过巨大石脸】 手机追着吊篮斜向下转动。 吊篮沿固定钢索不断滑行,从巨像脸颊外侧掠过。篮子里的#1很小,巨大的石鼻、胡须和盔甲纹路占满背景;随后背景逐渐换成层叠屋顶与峡谷。 篮体轻微摇晃,上方滑轮连续震动。她压低重心,抓紧栏杆,头发被风吹乱,始终紧盯前方。 吊篮沿着钢索朝拍摄者所在的平台方向越来越近。 近处游客突然意识到这一点:“过来了!过来了!” 【21—26秒:远处的故事冲到游客眼前】 摄影者急忙缩小变焦,手机跟不上吊篮接近的速度。 吊篮从观景平台外侧几米处斜向下滑过。近处游客本能后退,有人缩肩,有人仍举着手机。 这时才短暂看清#1:头发凌乱,神情紧绷,左手死死抓栏杆,右手却还握着那串烤肉。 滑轮的金属滚动声在接近时明显变响。 手机向下追拍,吊篮进入观景台侧下方接收站的缓冲段,逐渐减速,篮体前后晃一下,停住。#1屈膝稳住身体。 【26—30秒:烤肉保住了,但只保住一秒】 摄影者隔着栏杆向侧下方拍摄。 #1确认吊篮停稳,先喘一口气,才发现自己竟然还抓着烤串。 她抬头看见上方一群游客举着手机,勉强恢复一点从容,把烤串举起来,像在表示自己没事。 刚要低头咬,最后一块肉从签子上滑落,掉进篮底。 她低头看肉,再缓缓抬眼看向游客,举着空签子,表情彻底垮掉。 近处游客先是一声没忍住的笑,接着响起释然的笑声和零星掌声。手机跟着摄影者的笑轻轻抖动。 【声音】 急流、风声、古城环境声、近处游客交谈与惊呼。 远处平台上的撞击声较弱,不因为手机拉近就变成贴耳录音。吊篮接近时,滑轮声才逐渐响亮,滑过后随距离减弱。 女主不说长台词,危险中只有本能的短促惊叫。结尾用表情完成笑点。 无音乐,无旁白,无字幕。 【必须保持】 巨像始终静止。 全程同一游客站在固定观景台拍摄。 先全景发现小人,再变焦看清烤肉,随后追拍吊篮,最后吊篮来到游客附近。 主角开场不看镜头,险情发生后不摆性感姿势。 同一吊篮、同一条钢索、同一根烤串连续存在。 吊篮始终悬挂在钢索上,不自由飞行、不脱轨。 不插入机械零件特写,不切换近距离跟拍,不突然出现电影摄影机视角。
0
檢視詳情
0:15
Kling 4.0
Nighttime medium shot of a girl skateboarding swiftly through a dark, cold forest, her breath visible in the frosty air. The camera follows close behind, capturing her focused expression as she sings softly and sorrowfully, "Am I dead? Am I dreaming? I can't feel anything—I can't feel a thing." Pale moonlight filters through bare branches, casting cool blue shadows. She comes to a gentle stop on a leaf-strewn path, picks up her skateboard, and steps deeper into the dense woods. She whispers, "I must remain unseen," as the camera slowly dollies forward, enhancing the eerie, quiet ambiance. Audio: raw on-set sound only — natural dialogue, ambient room tone, and diegetic sound effects.
0
檢視詳情
5:23
A
Claude Opus 5.5
Ask me for: one premise as an "If your ___ ever ___… DO NOT ___" line (default: "If your Wi-Fi ever shows a network with your name on it… DO NOT CONNECT"), the length (default about 5:20, roughly 700 spoken words), one accent colour (default warm amber #FFB547), and whether I'll upload the narration as MP3s or you should generate it (ElevenLabs key, or a free local voice if not). An analog-horror "survival rules" explainer at 1920x1080, 30fps, drawn entirely in code: one HTML page with one full-frame SVG for the scene and HTML layers for HUD and captions. Background: flat near-black #060606, a vignette to rgba(0,0,0,.5) from 52% radius, and a 2% film grain re-randomized every frame. Nothing else: no scanlines, no flicker, no colour grade. It must read as deep black with soft glowing shapes. Pictograms: flat off-white #ececec with rounded corners and no outlines on filled shapes. A person (head r46, rounded-shoulder body 132x122, no face), a phone outline (12px stroke, radius 14% of width), the Wi-Fi symbol (dot r15, arcs r62/118/174 at 22px stroke, 90° each), houses, a router (340x110 body, two antennas, 4 status lights r11), a padlock, a door, a bed, a lying figure, a floor plan, 4 signal bars. Glow: one SVG filter on the scene group, a 5px blur at 70% alpha plus a 22px blur at 38% alpha merged under the crisp source. A soft halo, never bloom. Accent: only on the anomaly. The network row labelled YOUR NAME, its Wi-Fi arcs, filled signal bars, and a 4-corner bracket frame (12px stroke, 50px legs) that snaps onto whatever is "the copy". Red #E5322D only for one stamp and one slash. HUD in grey #6f6f6f monospace 20px, .2em tracking: a case number top-left, a running timecode HH:MM:SS:FF top-right, seven 24px numbered boxes top-centre, filled with the accent once a rule has passed and outlined white on the current rule. Rule cards: "RULE" in #d9d9d9 Montserrat ExtraBold 190px, the number centred with dominant-baseline central in a 190px accent rounded box (radius 26), a 600x7 accent line, then the rule in white caps at 52px, .08em tracking. Rule 7 gets a tilted red REDACTED stamp instead of text. Type: Montserrat 600-900 only, plus one monospace for the HUD. Captions in caps, Bold 50px, .035em tracking, one sentence at a time, white with a 4px/14px soft glow, key words (CONNECT, DISCONNECTED, FAMILIAR, YOU) in the accent, centred 110px from the bottom. Finish: RGB split (red and cyan drop-shadows offset 4-18px), 9 horizontal tear bars and an x-jitter only on glitch moments. Banned: grain over 3%, scanlines, brightness flicker, hard cuts, text running under icons, stepped animation of any kind, gradients on icons, AI images or AI video, any real channel's characters, names, logos or catchphrases. About 5:20, every sentence gets its own shot or transformation, nothing ever holds still. The one threat, stated by 1:00 and protected by every rule: the network is learning you so it can become you, and because two devices can't share one name, one of you gets disconnected. A phone Wi-Fi list, rows sliding in 0.35s apart, the YOUR NAME row pulsing accent (0s) → on "rename" a text cursor blinks in the HOME_WIFI row (5s) → on "walk" a house cross-section, a figure crossing room to room with its Wi-Fi bars rising (7s) → on "seven rules" seven boxes pop in on springs, four light on "four", box 7 gets brackets on "seventh" (14-18s) → a title card (22s) → the list again, NEIGHBOUR, PRINTER and FBI_SURVEILLANCE_VAN highlighting on their words (26-34s) → houses broadcasting rings (36s) → on "yours" a new YOUR NAME row slides in (44s) → on "no lock" an open padlock (47s) → on "full bars" the arcs fill smoothly, a figure appears under the symbol on "close" (49-51s) → on "learns a phone" particles reverse direction between phone and router, a message, key, keyboard and moon icon land on their words (55-65s) → a COPY bar eases 60 to 94%, hits 100% with brackets on "finishes" (67-72s) → two identical figures under the same name, one flickers out on "disconnected" (75-81s) → "ONLINE 0 DAYS" vs "ONLINE 214 DAYS" (85s) → RULE 1 card (86s) → on "copy of you" a router morphs into a bracketed figure (106s) → on "familiar" the list shows HOME_WIFI · AUTO-JOIN beside YOUR NAME · NOT SAVED (110s) → RULE 2, a thumb hovers over the Wi-Fi toggle, the copy figure jitters harder on each "guessing" (119-140s) → RULE 3, a floor plan, bars gliding 2, 3, full as the dot moves, brackets at the bedroom door (142-150s) → on "two of you" a second figure fades in beside the door (158s) → a case file with redaction bars and a DISCONNECTED stamp, two identical HANNAH · ROOM 12 rows, two phones, two figures, one fades on "disconnected" (167-189s) → RULE 4, the plug slides out, a countdown from 30, router lights fade one by one, YOUR NAME still glowing (194-212s) → on the cut-off word a slow push in on a bracketed figure, then a 1.4s static burst, RGB split and tear bars (214s) → SIGNAL RESTORED in monospace (216s) → RULE 5, waves bounce wall to sofa to you, a dashed copy follows the figure a beat behind, a breathing waveform reaching MATCH 100% (220-250s) → RULE 6, a device list filling row by row, UNKNOWN · SAME MODEL · 02:14 in the accent, a finger hovers REMOVE and stops, brackets jumping between two figures on "real" (252-277s) → RULE 7 with the REDACTED stamp, a ghost of the RULE 1 card, the row changing to CONNECTED (279-300s) → on "disconnected" one figure fades with a glitch, brackets flicker between the two on "which" (305-312s) → the last word huge in the accent, a hum swell, cut to black on a boom (318s). For any other premise keep the same shape: the threat stated early, o
0
檢視詳情
0:15
MiniMax H3
cracks open by itself along its fold, and a slow ribbon of grey fog pours out over the plate
0
檢視詳情
0:28
Seedance 2.5
Cinematic ultra-realistic fantasy-adventure short film, 16:9, 30 seconds, 24fps, shot like a high-budget movie trailer, cold misty dawn, heavy fog drifting through tall pine forest and rolling grassland, muted green-grey color grade, shallow depth of field, soft diffused light, subtle film grain, quiet and mysterious atmosphere. Character: A young woman in her mid-20s, shoulder-length dark brown hair, wearing a plain dark baseball cap with no logo, a black windbreaker jacket, baggy black track pants, white ankle socks and chunky white-and-grey sneakers, white fitted arm sleeves under her jacket. Brave, focused and breathing hard from running. Keep face, hair and outfit identical in every shot. Creature: A gigantic, ancient long-necked herbivorous dinosaur, so huge and still that its back looks like a moss-covered grassy hill. Rough grey-brown textured skin, deep wrinkles, a slow-blinking amber eye, a long gentle neck. Calm and peaceful, not aggressive. Setting: A silent pine forest at dawn that opens into a wide foggy meadow with distant tree lines and low clouds. 🌲 0–5s: Wide shot of the woman running between tall pine trees through thick fog, boots crunching on damp earth. Low-angle close-up of her sneakers stepping over a fallen branch, then a medium shot of her glancing back over her shoulder, breathing in white clouds, then running on. 🌫️ 5–10s: The forest ends and she bursts out into an open foggy meadow. Close-ups of her sneakers on wet grass, her hands pressing on her knees as she stops, catching her breath. She looks around at the endless silent mist. ⛰️ 10–15s: She notices a strange, large, moss-covered mound ahead. She walks toward it slowly, curious, and climbs to the top, standing tall on it. Wide shot showing her tiny against the foggy horizon. The mound very slightly rises and falls like breathing. 😳 15–20s: Extreme close-up of her face under the cap, eyes widening. She feels the ground move under her feet. Close-up of her sneakers as the "grass" ripples. The camera pushes toward a huge, wrinkled, closed eye emerging from the mound beside her. 🦕 20–25s: She drops to her hands and knees, gripping the moss. Wide shot as the mound slowly shifts, revealing it is the enormous head and body of a sleeping giant dinosaur. A great amber eye opens slowly and looks at her. 🌅 25–30s: The dinosaur gently lifts its long neck high into the fog with her still balanced on its head, as thin sunlight breaks through the clouds. She stands up in awe, smiling in disbelief. Epic slow pull-back crane shot revealing the immense creature and the tiny girl on its head against the misty horizon, then fade out. 🎧 Audio: Soft wind, distant birds, heavy breathing and footsteps on damp grass, a deep low rumbling breath from the creature, a slow rising orchestral score with soft strings and low brass, no dialogue. 🎬 Style: Realistic cinematic adventure, smooth natural movement, believable giant-creature scale, emotional wonder, non-graphic, no text, no subtitles, no logos, no watermark.
0
檢視詳情
0:15
MiniMax H3
gathers dark grey floss into a small storm cloud, which rumbles, flashes once and rains into the bowl
0
檢視詳情
0:08
Seedance 2.5
Scene & Style: Use Image 1 as the scene reference. A quiet suburban house entrance at night, viewed through a fixed doorbell camera with a circular fisheye effect. Use realistic low-resolution monochrome CCTV footage with cool tones, digital noise, compression artifacts, and weak streetlight illumination. Keep all characters monochrome. Music: Quiet, eerie Halloween instrumental music with deep ambience, ethereal synthesizers, and a slow, unsettling melody. 0–2 seconds: Image 3 stands close to the camera, knocks, and cheerfully says, “Trick or treat!” Her voice sounds distant, muffled, compressed, and slightly distorted, like real doorbell audio. 2–5 seconds: Image 3 steps back slightly. Image 2 is revealed standing directly behind her, expressionless, with his head tilted. She turns, sees him, panics, faces the camera, and desperately shouts, “Let me in!” 5–8 seconds: Image 2 slowly approaches while remaining behind her. She presses her face against the lens and frantically pounds below it. He places one hand on her shoulder. End the video at this unsettling moment. Camera & Audio: One continuous, fixed doorbell-camera shot. No cuts, zooms, camera movement, teleportation, or sudden position changes. Maintain realistic spacing, muffled surveillance audio, and a low-resolution monochrome horror aesthetic throughout.
0
檢視詳情
0:15
MiniMax H3
the white foam spreads across the top into a little ghost with two dark eyes that blinks once
0
檢視詳情