Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

This Animation turned out cool 🔥 Seedance 2.0 on Higgsfield Full open-sourced prompts and assets below Prompt: Generation 1 Aoi = Image 1 · Kaijin = Image 2 · Mio = Image 3 · Ren = Image 4 · Classroom = Image 5 All shots take place in the...

lexx_aura's profile picture

Lex

18,144 subscribers

34,375 Aufrufe • vor 2 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

just copy the prompt below and paste on Utopai the PAI agent turns it into script, create storyline, generate clips and edit all by itself prompt: High-energy 3D CGI animated comedy short, Pixar quality, ultra-detailed character animation, exaggerated physics, vibrant colors, warm orange kitchen lighting with glowing flames, bright daylight city streets, dynamic camera work with fast pans, tilts and dramatic angles, subtle motion blur on fast movements, comedic timing and expressions, upbeat energetic music with whooshes and impacts. **Main Character Casting Descriptions:** - **Pizza Chef - Jack (main actor in kitchen)**: Early 50s energetic male, messy silver hair, large prominent nose, thick expressive eyebrows, sharp intense eyes, fair skin with slight blush from heat. Wears white double-breasted chef jacket, wear white chef hat with text “el.cine” in front, gree neckerchief. Highly animated face — furrowed brows, focused squint, dramatic determination turning to exhaustion. - **Pizza Delivery Guy - Tom (main actor on street/scooter)**: Late teens/early 20s lanky male, long blue hair, huge expressive brown eyes, long nose, very animated facial expressions (surprise, determination, panic, relief). Wears white helmet with spinning yellow propeller on to, light blue leather with text el.cine at back, white pants, sneakers. Fast, exaggerated movements. - **Customer (final shot)**: Large, middle-aged stern woman, brown hair, heavy eyebrows, downturned mouth, wearing beige suit jacket, white shirt, dark trousers. Standing in doorway with impatient/annoyed expression. SHOT 1 (0:00–0:02) – Cinematic fast motion, dramatic low angle with subtle Dutch tilt and intense push-in: fast push from kitchen wide shot to close up on the Pizza Chef’s face in the bustling kitchen. He grips the large pepperoni pizza on a metal tray with raw, over-the-top determination — brows dramatically furrowed into deep angry V-shapes, eyes sharply narrowed with a fierce glint and slight crazy wideness at the edges, teeth gritted in heroic effort, dramatic sweat beads flying off his forehead. Bright orange flames explode upward from the pizza in the foreground with massive sparks and heat waves licking toward his face. Dynamic camera orbits left while pushing in for maximum tension, subtle motion blur on the flames. Background shows chaotic kitchen with stacked pizza boxes, glowing ovens, and flying embers. SHOT 2 (0:02–0:04) – Medium close-up, eye-level: Chef lifts the flaming pizza higher with both hands, leans forward, eyes wide with concentration as flames lick upward toward his face. SHOT 3 (0:04–0:06) – Medium shot, eye-level, dynamic pan: Chef dramatically spins the flaming pizza on the peel in a huge fiery arc above his head, left hand on forehead in dramatic pose, right arm extended. Flames trail in a perfect circle. SHOT 4 (0:06–0:08) – Low-angle dramatic shot looking up: Chef tosses the flaming pizza high into the air with both hands. The camera follows the spinning fiery pizza as it arcs toward the ceiling tiles. SHOT 5 (0:08–0:10) – Extreme low-angle on ceiling: The flaming pizza spins in a perfect circle of fire against the tiled ceiling, sparks flying. SHOT 6 (0:10–0:12) – Wide dynamic shot, low angle: Chef does a full acrobatic flip in mid-air, upside-down, catching the flaming pizza behind his back while still in the air. SHOT 7 (0:12–0:14) – Wide action shot, eye-level: Chef lands in a wide stance, spins the flaming pizza on one hand like a basketball, then dramatically throws it forward toward the open doorway with full body power, flames trailing, quick push in and follow the close up of the flying pizza in slow motion SHOT 8 (0:14–0:16) – Medium shot on street, eye-level: Pizza Delivery Guy stands outside the shop holding an empty pizza box, looking down at his watch with bored expression, propeller on helmet slowly spinning. SHOT 9 (0:16–0:18) – Medium close-up, eye-level: Chef (partially visible inside doorway) throws the flaming pepperoni pizza directly toward the Delivery Guy. Delivery Guy looks up with wide-eyed shock. SHOT 10 (0:18–0:20) – Medium shot, eye-level: slow motion, close up of the flaming pizza flies straight into the open pizza box held by the Delivery Guy. Flames whoosh past his face as he catches it perfectly. SHOT 11 (0:20–0:22) – Close-up on Delivery Guy’s face: His eyes go extremely wide in surprise, mouth open, propeller spinning faster, and talk excitedly SHOT 12 (0:22–0:24) – Extreme close-up on smartphone screen held in hand: Red digital timer clearly shows “00:30” counting down. SHOT 13 (0:24–0:26) – Close-up on Delivery Guy’s face: Expression changes from shock to intense determination — eyebrows lowered, mouth set in a smirk, eyes focused. SHOT 14 (0:26–0:50 end) – Wide tracking shot from behind, fast-paced: Delivery Guy jumps on his purple scooter and speeds away down the sunny city street, pizza box secured on the back. Camera follows as he weaves between cars, jumps over red-and-white construction barriers, rides up stairs, does rooftop jumps, and finally stops smoothly in front of a house. He turns with a confident smile as the stern Customer opens the door and stares at him and says with an angry tone “you are late” cut to Tom smiling awkwardly and scratch the back of his head, he takes the pizza from his back and suddenly he slide and fall down on the ground Cinematic 3D CGI animation style, highly exaggerated comedic action, perfect continuity of the flaming pizza and characters, dynamic camera movements exactly matching the original video’s pacing, framing, and energetic tone. Photorealistic 3D render quality, 1080p, 24fps.
0:25

just copy the prompt below and paste on Utopai the PAI agent turns it into script, create storyline, generate clips and edit all by itself prompt: High-energy 3D CGI animated comedy short, Pixar quality, ultra-detailed character animation, exaggerated physics, vibrant colors, warm orange kitchen lighting with glowing flames, bright daylight city streets, dynamic camera work with fast pans, tilts and dramatic angles, subtle motion blur on fast movements, comedic timing and expressions, upbeat energetic music with whooshes and impacts. **Main Character Casting Descriptions:** - **Pizza Chef - Jack (main actor in kitchen)**: Early 50s energetic male, messy silver hair, large prominent nose, thick expressive eyebrows, sharp intense eyes, fair skin with slight blush from heat. Wears white double-breasted chef jacket, wear white chef hat with text “el.cine” in front, gree neckerchief. Highly animated face — furrowed brows, focused squint, dramatic determination turning to exhaustion. - **Pizza Delivery Guy - Tom (main actor on street/scooter)**: Late teens/early 20s lanky male, long blue hair, huge expressive brown eyes, long nose, very animated facial expressions (surprise, determination, panic, relief). Wears white helmet with spinning yellow propeller on to, light blue leather with text el.cine at back, white pants, sneakers. Fast, exaggerated movements. - **Customer (final shot)**: Large, middle-aged stern woman, brown hair, heavy eyebrows, downturned mouth, wearing beige suit jacket, white shirt, dark trousers. Standing in doorway with impatient/annoyed expression. SHOT 1 (0:00–0:02) – Cinematic fast motion, dramatic low angle with subtle Dutch tilt and intense push-in: fast push from kitchen wide shot to close up on the Pizza Chef’s face in the bustling kitchen. He grips the large pepperoni pizza on a metal tray with raw, over-the-top determination — brows dramatically furrowed into deep angry V-shapes, eyes sharply narrowed with a fierce glint and slight crazy wideness at the edges, teeth gritted in heroic effort, dramatic sweat beads flying off his forehead. Bright orange flames explode upward from the pizza in the foreground with massive sparks and heat waves licking toward his face. Dynamic camera orbits left while pushing in for maximum tension, subtle motion blur on the flames. Background shows chaotic kitchen with stacked pizza boxes, glowing ovens, and flying embers. SHOT 2 (0:02–0:04) – Medium close-up, eye-level: Chef lifts the flaming pizza higher with both hands, leans forward, eyes wide with concentration as flames lick upward toward his face. SHOT 3 (0:04–0:06) – Medium shot, eye-level, dynamic pan: Chef dramatically spins the flaming pizza on the peel in a huge fiery arc above his head, left hand on forehead in dramatic pose, right arm extended. Flames trail in a perfect circle. SHOT 4 (0:06–0:08) – Low-angle dramatic shot looking up: Chef tosses the flaming pizza high into the air with both hands. The camera follows the spinning fiery pizza as it arcs toward the ceiling tiles. SHOT 5 (0:08–0:10) – Extreme low-angle on ceiling: The flaming pizza spins in a perfect circle of fire against the tiled ceiling, sparks flying. SHOT 6 (0:10–0:12) – Wide dynamic shot, low angle: Chef does a full acrobatic flip in mid-air, upside-down, catching the flaming pizza behind his back while still in the air. SHOT 7 (0:12–0:14) – Wide action shot, eye-level: Chef lands in a wide stance, spins the flaming pizza on one hand like a basketball, then dramatically throws it forward toward the open doorway with full body power, flames trailing, quick push in and follow the close up of the flying pizza in slow motion SHOT 8 (0:14–0:16) – Medium shot on street, eye-level: Pizza Delivery Guy stands outside the shop holding an empty pizza box, looking down at his watch with bored expression, propeller on helmet slowly spinning. SHOT 9 (0:16–0:18) – Medium close-up, eye-level: Chef (partially visible inside doorway) throws the flaming pepperoni pizza directly toward the Delivery Guy. Delivery Guy looks up with wide-eyed shock. SHOT 10 (0:18–0:20) – Medium shot, eye-level: slow motion, close up of the flaming pizza flies straight into the open pizza box held by the Delivery Guy. Flames whoosh past his face as he catches it perfectly. SHOT 11 (0:20–0:22) – Close-up on Delivery Guy’s face: His eyes go extremely wide in surprise, mouth open, propeller spinning faster, and talk excitedly SHOT 12 (0:22–0:24) – Extreme close-up on smartphone screen held in hand: Red digital timer clearly shows “00:30” counting down. SHOT 13 (0:24–0:26) – Close-up on Delivery Guy’s face: Expression changes from shock to intense determination — eyebrows lowered, mouth set in a smirk, eyes focused. SHOT 14 (0:26–0:50 end) – Wide tracking shot from behind, fast-paced: Delivery Guy jumps on his purple scooter and speeds away down the sunny city street, pizza box secured on the back. Camera follows as he weaves between cars, jumps over red-and-white construction barriers, rides up stairs, does rooftop jumps, and finally stops smoothly in front of a house. He turns with a confident smile as the stern Customer opens the door and stares at him and says with an angry tone “you are late” cut to Tom smiling awkwardly and scratch the back of his head, he takes the pizza from his back and suddenly he slide and fall down on the ground Cinematic 3D CGI animation style, highly exaggerated comedic action, perfect continuity of the flaming pizza and characters, dynamic camera movements exactly matching the original video’s pacing, framing, and energetic tone. Photorealistic 3D render quality, 1080p, 24fps.

el.cine

12,990 Aufrufe • vor 3 Monaten

Used Product Commercial Skill to create this video on FlovaAI FlovaAI_Japan prom SHOT 1 [0:00–0:03] — 3s, real-time Extreme close-up: a single perfect golden-brown fried mandu (Korean dumpling), triangular fold, sitting on the railing of a 10th-floor officetel balcony in Seoul. Bright midday sun catching every crisp fried edge, steam rising gently. A small dish of soy-vinegar dipping sauce sits right beside it, close to the mandu. SHOT 2 [0:03–0:05] — 2s, real-time A pigeon lands on the railing a foot away. It looks at the mandu, tilts its head, takes one casual step closer. Its wing brushes the sauce dish. SHOT 3 [0:05–0:06] — 1s, real-time The mandu and the sauce dish both wobble from the nudge. They tip together and fall off the edge of the railing. SHOT 4 [0:06–0:10] — 4s, slow motion Wide shot from directly across the street at 10th-floor level: the mandu and sauce dish tumbling outward, rotating end over end, catching the sunlight on every turn. Behind them, the building facade — a tall Seoul apartment block, muted grey-blue exterior, laundry hanging on a few balconies. The mandu is a tiny golden triangle falling against the building. SHOT 5 [0:10–0:13] — 3s, real-time Ground level wide shot: a busy Seoul street in midday sun. Pedestrians with shopping bags, a delivery scooter idling at the curb, a tteokbokki/odeng street cart with an ajumma stirring a pot, a dog sleeping in a patch of sun, an elderly man reading a newspaper on a bench. Ordinary day, nobody aware anything is falling. SHOT 6 [0:13–0:15] — 2s, real-time Close-up on the sleeping dog: one ear twitches, then both go up. Nose starts working. One eye opens, pupils tracking something falling. The dog slowly rises, never looking away from above. SHOT 7 [0:15–0:17] — 2s, real-time Close-up on the cart ajumma: her stirring spoon slows, then stops. She looks up, eyes widening, and slowly sets the spoon down on the cart edge. SHOT 8 [0:17–0:19] — 2s, real-time Close-up on the newspaper man: a small triangular shadow crosses his page. He lowers the newspaper and looks up, his glasses catching the sunlight. SHOT 9 [0:19–0:23] — 4s, slow motion Wide shot of the full street: the mandu and sauce dish visible as tiny falling shapes above the crowd. Below, reactions ripple outward — the dog now standing, the ajumma craning her neck, the newspaper man on his feet, the delivery driver stepped off his scooter looking up, a vegetable vendor shielding her eyes with one hand. SHOT 10 [0:23–0:25] — 2s, real-time A second pigeon flying past at around the 5th-floor level narrowly dodges the falling mandu, does a startled double-take mid-flight, and veers off. SHOT 11 [0:25–0:29] — 4s, extreme slow motion Extreme close-up: the mandu now three feet from the ground, rotating slowly, every crisp fried ridge sharp in the light, a faint trail of steam still lifting off it. The sauce dish falls a foot above it, tilting but staying upright. SHOT 12 [0:29–0:31] — 2s, real-time Ground-level close-up: the dog's mouth is open, perfectly positioned. The mandu drops directly into it. The dog closes its mouth. The sauce dish lands upright on the pavement beside the dog with a small click. SHOT 13 [0:31–0:34] — 3s, real-time The dog sits down, chews twice, swallows. It licks its nose once, then glances down at the sauce dish, then up at the silent, staring crowd. SHOT 14 [0:34–0:40] — 6s, real-time Wide shot: total silence on the street for a beat. Then the dog lies back down in its sunny spot and closes its eyes. The crowd slowly breaks and goes back to what they were doing — the ajumma picks her spoon back up, the newspaper man sits and lifts his paper, the delivery driver gets back on his scooter. SHOT 15 [0:40–0:45] — 5s, real-time Overhead, back on the 10th-floor balcony: the first pigeon is now sitting exactly where the mandu used to be, looking down at the street below. Bright midday sun, crisp shadows. Hold on the pigeon as the shot settles, closing the sequence. #Flovaai #Flovacpp
0:45

Used Product Commercial Skill to create this video on FlovaAI FlovaAI_Japan prom SHOT 1 [0:00–0:03] — 3s, real-time Extreme close-up: a single perfect golden-brown fried mandu (Korean dumpling), triangular fold, sitting on the railing of a 10th-floor officetel balcony in Seoul. Bright midday sun catching every crisp fried edge, steam rising gently. A small dish of soy-vinegar dipping sauce sits right beside it, close to the mandu. SHOT 2 [0:03–0:05] — 2s, real-time A pigeon lands on the railing a foot away. It looks at the mandu, tilts its head, takes one casual step closer. Its wing brushes the sauce dish. SHOT 3 [0:05–0:06] — 1s, real-time The mandu and the sauce dish both wobble from the nudge. They tip together and fall off the edge of the railing. SHOT 4 [0:06–0:10] — 4s, slow motion Wide shot from directly across the street at 10th-floor level: the mandu and sauce dish tumbling outward, rotating end over end, catching the sunlight on every turn. Behind them, the building facade — a tall Seoul apartment block, muted grey-blue exterior, laundry hanging on a few balconies. The mandu is a tiny golden triangle falling against the building. SHOT 5 [0:10–0:13] — 3s, real-time Ground level wide shot: a busy Seoul street in midday sun. Pedestrians with shopping bags, a delivery scooter idling at the curb, a tteokbokki/odeng street cart with an ajumma stirring a pot, a dog sleeping in a patch of sun, an elderly man reading a newspaper on a bench. Ordinary day, nobody aware anything is falling. SHOT 6 [0:13–0:15] — 2s, real-time Close-up on the sleeping dog: one ear twitches, then both go up. Nose starts working. One eye opens, pupils tracking something falling. The dog slowly rises, never looking away from above. SHOT 7 [0:15–0:17] — 2s, real-time Close-up on the cart ajumma: her stirring spoon slows, then stops. She looks up, eyes widening, and slowly sets the spoon down on the cart edge. SHOT 8 [0:17–0:19] — 2s, real-time Close-up on the newspaper man: a small triangular shadow crosses his page. He lowers the newspaper and looks up, his glasses catching the sunlight. SHOT 9 [0:19–0:23] — 4s, slow motion Wide shot of the full street: the mandu and sauce dish visible as tiny falling shapes above the crowd. Below, reactions ripple outward — the dog now standing, the ajumma craning her neck, the newspaper man on his feet, the delivery driver stepped off his scooter looking up, a vegetable vendor shielding her eyes with one hand. SHOT 10 [0:23–0:25] — 2s, real-time A second pigeon flying past at around the 5th-floor level narrowly dodges the falling mandu, does a startled double-take mid-flight, and veers off. SHOT 11 [0:25–0:29] — 4s, extreme slow motion Extreme close-up: the mandu now three feet from the ground, rotating slowly, every crisp fried ridge sharp in the light, a faint trail of steam still lifting off it. The sauce dish falls a foot above it, tilting but staying upright. SHOT 12 [0:29–0:31] — 2s, real-time Ground-level close-up: the dog's mouth is open, perfectly positioned. The mandu drops directly into it. The dog closes its mouth. The sauce dish lands upright on the pavement beside the dog with a small click. SHOT 13 [0:31–0:34] — 3s, real-time The dog sits down, chews twice, swallows. It licks its nose once, then glances down at the sauce dish, then up at the silent, staring crowd. SHOT 14 [0:34–0:40] — 6s, real-time Wide shot: total silence on the street for a beat. Then the dog lies back down in its sunny spot and closes its eyes. The crowd slowly breaks and goes back to what they were doing — the ajumma picks her spoon back up, the newspaper man sits and lifts his paper, the delivery driver gets back on his scooter. SHOT 15 [0:40–0:45] — 5s, real-time Overhead, back on the 10th-floor balcony: the first pigeon is now sitting exactly where the mandu used to be, looking down at the street below. Bright midday sun, crisp shadows. Hold on the pigeon as the shot settles, closing the sequence. #Flovaai #Flovacpp

Sharon Riley

32,523 Aufrufe • vor 2 Monaten

-- What holds it together -- ✂️PAPER CUTS.- When the image is the end ⤵️ What you bring to life is the journey towards the image: how the pieces come to be as they are. The movement is the idea, and your image in Seedance is the final frame. ---------------------------------------------------- What happens to the object? 1⃣ By the time the object TRANFORMS into something else. It takes place in a continuous shot, a single camera that zooms in slowly and never cuts away. A cut would break the transformation; the hypnotic effect lies precisely in the fact that it doesn’t flicker. Template.- [@.RE IMAGE] is the LAST frame. [GLOBAL] [Technique + light + backdrop + focus]. [Real materials]. One continuous hypnotic transformation — a single take, no cuts. The same [OBJECT A] does not appear in pieces; it [VERB: melts / folds / blooms / dissolves] into [OBJECT B]. Slow surreal dreamlike drift, one unbroken slow push, slight stop-motion shimmer, no snapping. 0-1s: [state A, intact and recognizable]. 1-2.5s: [the change begins — "the same material begins to..."]. 2.5-3.5s: [the change at full — "...becomes..."]. 3.5-5s: [it settles]. The push eases to rest. Locked, exact match to the last frame. [LOGIC RULE] one continuous same-lens push, never cutting. [A] morphs into [B], [details that must not deform] stay legible, no warping. hypnotic drift. SFX: [a sound that also transforms]. no music, normal speed. 2⃣ When one thing LEADS to another, we need each step to be a link in the chain of causality. Template.- [@.RE IMAGE] is the LAST frame. [GLOBAL] [Technique + light + backdrop + focus]. [Real materials]. Hypnotic stop-motion paper cadence, slight frame-step, brisk causal montage, ~1.5s per shot, no naturalistic motion, no slow-mo. [cut] [shot + camera] / [carries on from previous cut] / [ACTION: what it DOES, not how it looks]. SFX: [beat-anchored hit]. [cut] ... (link 2 — chains from link 1) [cut] ... (link 3) [cut] ... (link 4) [cut] ... ease back to reveal / [link 5]. Locked, exact match to the last frame. SFX: ... [LOGIC RULE].- [materials], [what must NOT happen], no warping, [text legible if any]. ~1.5s per shot, no slow-mo. no music.
0:41

-- What holds it together -- ✂️PAPER CUTS.- When the image is the end ⤵️ What you bring to life is the journey towards the image: how the pieces come to be as they are. The movement is the idea, and your image in Seedance is the final frame. ---------------------------------------------------- What happens to the object? 1⃣ By the time the object TRANFORMS into something else. It takes place in a continuous shot, a single camera that zooms in slowly and never cuts away. A cut would break the transformation; the hypnotic effect lies precisely in the fact that it doesn’t flicker. Template.- [@.RE IMAGE] is the LAST frame. [GLOBAL] [Technique + light + backdrop + focus]. [Real materials]. One continuous hypnotic transformation — a single take, no cuts. The same [OBJECT A] does not appear in pieces; it [VERB: melts / folds / blooms / dissolves] into [OBJECT B]. Slow surreal dreamlike drift, one unbroken slow push, slight stop-motion shimmer, no snapping. 0-1s: [state A, intact and recognizable]. 1-2.5s: [the change begins — "the same material begins to..."]. 2.5-3.5s: [the change at full — "...becomes..."]. 3.5-5s: [it settles]. The push eases to rest. Locked, exact match to the last frame. [LOGIC RULE] one continuous same-lens push, never cutting. [A] morphs into [B], [details that must not deform] stay legible, no warping. hypnotic drift. SFX: [a sound that also transforms]. no music, normal speed. 2⃣ When one thing LEADS to another, we need each step to be a link in the chain of causality. Template.- [@.RE IMAGE] is the LAST frame. [GLOBAL] [Technique + light + backdrop + focus]. [Real materials]. Hypnotic stop-motion paper cadence, slight frame-step, brisk causal montage, ~1.5s per shot, no naturalistic motion, no slow-mo. [cut] [shot + camera] / [carries on from previous cut] / [ACTION: what it DOES, not how it looks]. SFX: [beat-anchored hit]. [cut] ... (link 2 — chains from link 1) [cut] ... (link 3) [cut] ... (link 4) [cut] ... ease back to reveal / [link 5]. Locked, exact match to the last frame. SFX: ... [LOGIC RULE].- [materials], [what must NOT happen], no warping, [text legible if any]. ~1.5s per shot, no slow-mo. no music.

AlexandrIA

41,804 Aufrufe • vor 2 Monaten

Walked past him like the backflip was the easy part of lunch. Seedance 2.5 on Fish Creative Prompt Cinematic Korean high-school drama, 22-second continuous shot sequence, photoreal live-action, 24fps, shallow-to-medium depth of field, natural fluorescent cafeteria lighting mixed with window daylight, slightly warm color grade. Crowded Korean high-school cafeteria: long wooden tables, metal benches, tiled floor with a faint sheen, white waffle-grid ceiling, hanging fluorescent lights. Dozens of students in pastel blue short-sleeve summer uniforms with purple ties (boys) and pink ribbon bows (girls) eating from stainless-steel compartment trays. Heroine: early-20s Korean woman @[Image 1](image_1) styled as a high-school senior — long straight pastel pink hair with center part and face-framing layers, pale makeup, glossy lips, pastel pink short-sleeve school blouse, navy ribbon bow, pastel pink mini skirt, white crew socks, chunky white sneakers, small blue name tag on her chest. She walks the center aisle carrying a stainless 5-compartment lunch tray in both hands. Tray contents: mound of white rice, spicy red tteokbokki cylinders, a pile of kimchi, seasoned green namul, and a small metal soup bowl of red stew. Spoon and chopsticks rest on the tray. Shot 1 (0–1s): Medium-wide tracking shot. She walks straight toward camera down the aisle, calm expression, tray held level at waist height. Background students laugh and eat. Shot 2 (1s): Tight low insert of her feet. She scuffs the heel of her left white sneaker against the polished floor, then plants both feet. Shot 3 (2s): Medium close-up of her face as she looks up, slightly startled, hair swinging. Shot 4–6 (3–6s): Slow-motion VFX food sequence. She tosses the tray upward. The tray and utensils hang in mid-air. Tteokbokki pieces, kimchi, and namul lift off the compartments and float in a neat horizontal line above the tray, as if gravity paused. Cut to overhead: food settles perfectly back into each compartment; soup bowl stays upright, nothing spills. Shot 7 (7s): Wide. She drops into a fast back handspring / cartwheel on the cafeteria floor, skirt flipping, one sneaker kicking high. Students at nearby tables freeze and stare. Shot 8 (8s): She lands spinning, hair whipping, and catches the falling tray and utensils in one fluid motion without dropping food. Shot 9–11 (9–11s): Close-ups of hands catching chopsticks and spoon, then a hero beauty shot of the completed tray held out toward camera — rice, tteokbokki, kimchi, namul, and stew all perfectly arranged. Shot 12 (12s): Cut to a table of boys. Handsome dark-haired boy in white shirt and navy tie turns, mouth open in shock; friends around him gape. Shot 13–14 (13–14s): Tight beauty close-up of the heroine’s face, staring into camera, then a tiny knowing smirk. Shot 15–20 (15–20s): She walks past the shocked boy’s table, tray in her left hand, glancing down at him. Soft line of dialogue in Korean, subtitled: “Let’s eat and see.” He looks down, embarrassed. She keeps walking. Shot 21 (21s): Rear tracking shot as she walks away down the aisle, long hair and navy skirt, cafeteria buzzing again behind her. Style notes: high-end K-drama cinematography (something like a glossy teen romance / school fantasy), practical cafeteria set, subtle slow-motion only on the floating-food and flip beats, clean VFX so the food never smears or looks cartoonish, no logos, no on-screen text except optional Korean subtitle on the one line. Negative: messy spills, broken tray, Western cafeteria, adult office clothes, exaggerated anime faces, shaky phone footage, watermarks.
0:22

Walked past him like the backflip was the easy part of lunch. Seedance 2.5 on Fish Creative Prompt Cinematic Korean high-school drama, 22-second continuous shot sequence, photoreal live-action, 24fps, shallow-to-medium depth of field, natural fluorescent cafeteria lighting mixed with window daylight, slightly warm color grade. Crowded Korean high-school cafeteria: long wooden tables, metal benches, tiled floor with a faint sheen, white waffle-grid ceiling, hanging fluorescent lights. Dozens of students in pastel blue short-sleeve summer uniforms with purple ties (boys) and pink ribbon bows (girls) eating from stainless-steel compartment trays. Heroine: early-20s Korean woman @[Image 1](image_1) styled as a high-school senior — long straight pastel pink hair with center part and face-framing layers, pale makeup, glossy lips, pastel pink short-sleeve school blouse, navy ribbon bow, pastel pink mini skirt, white crew socks, chunky white sneakers, small blue name tag on her chest. She walks the center aisle carrying a stainless 5-compartment lunch tray in both hands. Tray contents: mound of white rice, spicy red tteokbokki cylinders, a pile of kimchi, seasoned green namul, and a small metal soup bowl of red stew. Spoon and chopsticks rest on the tray. Shot 1 (0–1s): Medium-wide tracking shot. She walks straight toward camera down the aisle, calm expression, tray held level at waist height. Background students laugh and eat. Shot 2 (1s): Tight low insert of her feet. She scuffs the heel of her left white sneaker against the polished floor, then plants both feet. Shot 3 (2s): Medium close-up of her face as she looks up, slightly startled, hair swinging. Shot 4–6 (3–6s): Slow-motion VFX food sequence. She tosses the tray upward. The tray and utensils hang in mid-air. Tteokbokki pieces, kimchi, and namul lift off the compartments and float in a neat horizontal line above the tray, as if gravity paused. Cut to overhead: food settles perfectly back into each compartment; soup bowl stays upright, nothing spills. Shot 7 (7s): Wide. She drops into a fast back handspring / cartwheel on the cafeteria floor, skirt flipping, one sneaker kicking high. Students at nearby tables freeze and stare. Shot 8 (8s): She lands spinning, hair whipping, and catches the falling tray and utensils in one fluid motion without dropping food. Shot 9–11 (9–11s): Close-ups of hands catching chopsticks and spoon, then a hero beauty shot of the completed tray held out toward camera — rice, tteokbokki, kimchi, namul, and stew all perfectly arranged. Shot 12 (12s): Cut to a table of boys. Handsome dark-haired boy in white shirt and navy tie turns, mouth open in shock; friends around him gape. Shot 13–14 (13–14s): Tight beauty close-up of the heroine’s face, staring into camera, then a tiny knowing smirk. Shot 15–20 (15–20s): She walks past the shocked boy’s table, tray in her left hand, glancing down at him. Soft line of dialogue in Korean, subtitled: “Let’s eat and see.” He looks down, embarrassed. She keeps walking. Shot 21 (21s): Rear tracking shot as she walks away down the aisle, long hair and navy skirt, cafeteria buzzing again behind her. Style notes: high-end K-drama cinematography (something like a glossy teen romance / school fantasy), practical cafeteria set, subtle slow-motion only on the floating-food and flip beats, clean VFX so the food never smears or looks cartoonish, no logos, no on-screen text except optional Korean subtitle on the one line. Negative: messy spills, broken tray, Western cafeteria, adult office clothes, exaggerated anime faces, shaky phone footage, watermarks.

Sharon Riley

39,318 Aufrufe • vor 8 Tagen

So Runway Gen 4.5 finally adds image-to-video, the workflow most pros rely on for consistency. We put it head to head with Kling AI and Google Flow VEO using the same reference images and prompts (below) to evaluate motion quality, stability, and cinematic realism. 1. Action/WaterPhysics Test Prompt: Cinematic, wide-shot of a man running in a shallow river. The camera is tracking the man from behind as he runs up the river. Handheld camera shake as the camera follows the man. 2. Fire Physics Test Prompt: Cinematic, wide-shot of terrified woman running towards her burning barn. She abruptly stops, and puts in hands on her head as she watches her barn burn down. 3. VFX test prompt: Cinematic, wide-shot of a hooded figure. Flashes of purple magic and smoke whirl around the figure. The figure lifts its arms as the purple magic and smoke intensifies. 4. 2D Animation Test Prompt: 2D animated shot of a waiting at a bus stop in a thunderstorm. The man turns, walks to the bench, and sits down. 5. 3D Animation Test Prompt: 3D animated shot of an octopus. The octopus reaches into a coral and picks up a glowing white gem. 6. Conversation Test Prompt: slow camera push-in as two friends are having a conversation at a coffee shop Overall verdict: Despite the “world’s best” claim, Runway Gen 4.5 is not there yet. Prompt adherence is solid, but motion, physics, and cinematic realism still lag behind tools like Kling and VEO. Great platform, mid-tier model for now.
0:47

So Runway Gen 4.5 finally adds image-to-video, the workflow most pros rely on for consistency. We put it head to head with Kling AI and Google Flow VEO using the same reference images and prompts (below) to evaluate motion quality, stability, and cinematic realism. 1. Action/WaterPhysics Test Prompt: Cinematic, wide-shot of a man running in a shallow river. The camera is tracking the man from behind as he runs up the river. Handheld camera shake as the camera follows the man. 2. Fire Physics Test Prompt: Cinematic, wide-shot of terrified woman running towards her burning barn. She abruptly stops, and puts in hands on her head as she watches her barn burn down. 3. VFX test prompt: Cinematic, wide-shot of a hooded figure. Flashes of purple magic and smoke whirl around the figure. The figure lifts its arms as the purple magic and smoke intensifies. 4. 2D Animation Test Prompt: 2D animated shot of a waiting at a bus stop in a thunderstorm. The man turns, walks to the bench, and sits down. 5. 3D Animation Test Prompt: 3D animated shot of an octopus. The octopus reaches into a coral and picks up a glowing white gem. 6. Conversation Test Prompt: slow camera push-in as two friends are having a conversation at a coffee shop Overall verdict: Despite the “world’s best” claim, Runway Gen 4.5 is not there yet. Prompt adherence is solid, but motion, physics, and cinematic realism still lag behind tools like Kling and VEO. Great platform, mid-tier model for now.

Curious Refuge

25,712 Aufrufe • vor 8 Monaten

卧槽，牛逼了。 同样的提示词效果居然不一般。💪💪 工具：MiniMax H3，也可以使用在线工具如： 不知火舞第一弹V2👇 第一弹提示词： --- For the target video, at 0.00 seconds into the target video, (from [Shot 1]) is fully referenced. integrated_multimodal_description: [Shot 1] 2D-animated, retro arcade fighting-game character art style blended with a clean macOS desktop scene, exactly as established in : an arc-shaped light-band wallpaper sweeps from deep blue-violet at the lower left to orange-red and magenta at the upper right over a mirror-like reflective ground; two vertical columns of glossy rounded-square application icons stand on the left half — each icon is a clean pictogram with NO text label beneath it: the first column shows from top to bottom a blue smiling face, a red-yellow-green ring around a blue center dot, a white "N" block in a dark frame, a light-blue infinity-style ribbon, a dark tile with blue letters, an amber tile with yellow script, a purple tile with white letters, and green arcs inside a circle; the second column shows two white chat bubbles on green, a penguin on white, a white paper plane on blue gradient, four colored squares in a grid, a blue-green spiral ring, a red play triangle, colorful pinwheel petals, and a white "A" brushstroke on blue — on the right stands the brown high-ponytail young woman with white horn-like hair ornaments, wearing a red high-slit qipao-style fighting outfit with a large white waist knot trailing red-floral ribbons and white-tassel beads in her hair, black fingerless gloves and red-black heeled sandals; she holds an open white fan with red trim hanging behind her hip while one hand rests on her waist, gazing back over her shoulder. The camera pushes in with small amplitude at slow speed as she pivots from the回眸 stance into a low crouch, orange-yellow fire ribbons beginning to swirl around her feet and embers spiraling upward past her shoulders. [Shot 2] At 00:04.500, the camera cuts to a wider shot of the full desktop as she explodes out of the crouch into a dramatic backbend spin — one leg planted, the other extended far to the side-rear, torso twisted and arched backward, ponytail flaring wide in the motion — and roars [Japanese] 超必殺・忍蜂！ A ring of glowing shuriken erupts from her spinning body and orbits outward like a whirlpool across the center of the screen; as the blades sweep through the icon columns, open fans launch from her wrist in rapid succession and strike the icons one by one — each struck icon wobbles violently, peels off its grid position, and tumbles downward with motion blur past the reflective ground out of frame, trailing orange-yellow sparks. The final shuriken detonates at the center of the grid as a white-blue light bloom, shaking the whole desktop loose; every remaining icon rains down in a cascade while her spin finishes in a low landing, one hand extended forward, palm up. [Shot 3] At 00:10.500, the camera cuts to a medium close-up of the young woman across the now-empty center of the screen; her expression stays calm and unbothered, lips pressed into a confident smirk while embers drift past her shoulder. She slowly raises her open fan beside her face and says [Japanese] 花蝶扇。 Orange-yellow flame begins to gather along the fan's ribs like liquid fire pooling on silk, the light reflecting off her white waist knot and red-floral ribbons as tiny sparks orbit her wrist. [Shot 4] At 00:13.500, the shot cuts back to the full desktop as she sweeps the burning fan in a wide graceful arc through another spin; ribbons of orange-yellow flame unfurl from the fan like butterfly wings trailing behind her, and each ribbon's tip hooks one falling icon from below the frame, reeling it smoothly up into its exact original grid position — every lock-in flashing a small white-blue light bloom with a sharp click as the icons seat crisply back into place, restoring both columns perfectly. The last ribbon curls around the final icon and dissolves into sparks that spiral back into her fan as she closes it with a snap at her hip. [Shot 5] At 00:17.000, the camera cuts to a low-angle hero shot as she settles into her classic pose from : side-turned stance with weight on the rear leg, one hand on her waist, the closed fan held elegantly beside her face, chin tilted down in a cold confident glare while her ribbons and hair flare outward in the residual wind. The camera pulls out with small amplitude at slow speed, revealing the fully restored desktop around her; drifting orange sparks fade to black as she holds the pose until the end of the video. overall_soundscape: Low flame crackle builds under a rumbling charge, then an explosive whoosh on the backbend spin — rapid shuriken whistles and fan-snap cracks striking icons one after another — followed by cascading rattling clatters as icons tumble out of frame and a sharp white-blue burst pop. A crisp fan snap and a soft confident breath carry across the empty desktop during the calm close-up. Rising flame hiss gathers along the fan's ribs, then graceful silk-ribbon whooshes sweep through the spin while crisp snap-back clicks land one after another as each icon locks into place with tiny light-bloom pops, ending with a low resonant boom under guttering ember crackle. non_diegetic_music: Driving taiko drums with fast electronic percussion at a high tempo building to a hard hit on the shuriken barrage, dropping out to sparse sustained synth and a single koto pluck during the calm close-up, then returning for one final strong downbeat as she locks her classic pose. ---
0:20

卧槽，牛逼了。 同样的提示词效果居然不一般。💪💪 工具：MiniMax H3，也可以使用在线工具如： 不知火舞第一弹V2👇 第一弹提示词： --- For the target video, at 0.00 seconds into the target video, (from [Shot 1]) is fully referenced. integrated_multimodal_description: [Shot 1] 2D-animated, retro arcade fighting-game character art style blended with a clean macOS desktop scene, exactly as established in : an arc-shaped light-band wallpaper sweeps from deep blue-violet at the lower left to orange-red and magenta at the upper right over a mirror-like reflective ground; two vertical columns of glossy rounded-square application icons stand on the left half — each icon is a clean pictogram with NO text label beneath it: the first column shows from top to bottom a blue smiling face, a red-yellow-green ring around a blue center dot, a white "N" block in a dark frame, a light-blue infinity-style ribbon, a dark tile with blue letters, an amber tile with yellow script, a purple tile with white letters, and green arcs inside a circle; the second column shows two white chat bubbles on green, a penguin on white, a white paper plane on blue gradient, four colored squares in a grid, a blue-green spiral ring, a red play triangle, colorful pinwheel petals, and a white "A" brushstroke on blue — on the right stands the brown high-ponytail young woman with white horn-like hair ornaments, wearing a red high-slit qipao-style fighting outfit with a large white waist knot trailing red-floral ribbons and white-tassel beads in her hair, black fingerless gloves and red-black heeled sandals; she holds an open white fan with red trim hanging behind her hip while one hand rests on her waist, gazing back over her shoulder. The camera pushes in with small amplitude at slow speed as she pivots from the回眸 stance into a low crouch, orange-yellow fire ribbons beginning to swirl around her feet and embers spiraling upward past her shoulders. [Shot 2] At 00:04.500, the camera cuts to a wider shot of the full desktop as she explodes out of the crouch into a dramatic backbend spin — one leg planted, the other extended far to the side-rear, torso twisted and arched backward, ponytail flaring wide in the motion — and roars [Japanese] 超必殺・忍蜂！ A ring of glowing shuriken erupts from her spinning body and orbits outward like a whirlpool across the center of the screen; as the blades sweep through the icon columns, open fans launch from her wrist in rapid succession and strike the icons one by one — each struck icon wobbles violently, peels off its grid position, and tumbles downward with motion blur past the reflective ground out of frame, trailing orange-yellow sparks. The final shuriken detonates at the center of the grid as a white-blue light bloom, shaking the whole desktop loose; every remaining icon rains down in a cascade while her spin finishes in a low landing, one hand extended forward, palm up. [Shot 3] At 00:10.500, the camera cuts to a medium close-up of the young woman across the now-empty center of the screen; her expression stays calm and unbothered, lips pressed into a confident smirk while embers drift past her shoulder. She slowly raises her open fan beside her face and says [Japanese] 花蝶扇。 Orange-yellow flame begins to gather along the fan's ribs like liquid fire pooling on silk, the light reflecting off her white waist knot and red-floral ribbons as tiny sparks orbit her wrist. [Shot 4] At 00:13.500, the shot cuts back to the full desktop as she sweeps the burning fan in a wide graceful arc through another spin; ribbons of orange-yellow flame unfurl from the fan like butterfly wings trailing behind her, and each ribbon's tip hooks one falling icon from below the frame, reeling it smoothly up into its exact original grid position — every lock-in flashing a small white-blue light bloom with a sharp click as the icons seat crisply back into place, restoring both columns perfectly. The last ribbon curls around the final icon and dissolves into sparks that spiral back into her fan as she closes it with a snap at her hip. [Shot 5] At 00:17.000, the camera cuts to a low-angle hero shot as she settles into her classic pose from : side-turned stance with weight on the rear leg, one hand on her waist, the closed fan held elegantly beside her face, chin tilted down in a cold confident glare while her ribbons and hair flare outward in the residual wind. The camera pulls out with small amplitude at slow speed, revealing the fully restored desktop around her; drifting orange sparks fade to black as she holds the pose until the end of the video. overall_soundscape: Low flame crackle builds under a rumbling charge, then an explosive whoosh on the backbend spin — rapid shuriken whistles and fan-snap cracks striking icons one after another — followed by cascading rattling clatters as icons tumble out of frame and a sharp white-blue burst pop. A crisp fan snap and a soft confident breath carry across the empty desktop during the calm close-up. Rising flame hiss gathers along the fan's ribs, then graceful silk-ribbon whooshes sweep through the spin while crisp snap-back clicks land one after another as each icon locks into place with tiny light-bloom pops, ending with a low resonant boom under guttering ember crackle. non_diegetic_music: Driving taiko drums with fast electronic percussion at a high tempo building to a hard hit on the shuriken barrage, dropping out to sparse sustained synth and a single koto pluck during the calm close-up, then returning for one final strong downbeat as she locks her classic pose. ---

大卫叔的AI旅程

42,883 Aufrufe • vor 3 Tagen

What would you do if this mirror pulled you underwater? Nano Banana 2 + Seedance 2.5 on TapNow prompt SCENE CONTEXT A girl Image flees something unseen through a glowing forest, trips, falls — and finds an antique mirror that yanks her through into an underwater city. There, mid-float before the great shell palace, she turns her head — a flash of POV shows a colossal mouth opening onto her — and back in the wide frame the whale is already closing its jaw and gliding calmly away. 24 seconds, full realism. ACTIVE REFERENCES — STRICT ROLE HIERARCHY Image HER EXACT FACE — sole source of her identity and features, 100% match, zero drift: a 20-year-old , 163 cm, slim and lightly built. Soft rounded oval face; warm light-beige skin with a golden undertone and real photographic texture — visible pores, small freckles and tiny beauty marks across the cheeks and nose bridge; dark blue almond eyes with a shallow partially hidden upper-lid crease and soft under-eye fullness; thick dark straight brows with individual hairs brushed upward; a small neat nose with narrow straight bridge and softly rounded tip; full lips with a defined cupid's bow, the lower lip fuller, natural rosy tone; softly rounded jaw tapering to a small chin; small silver hoop earrings. Ignore this reference's hair, clothing, car interior and lighting. Face identity comes from this reference in every single frame. Image : CHARACTER SHEET — controls everything: long voluminous wavy blonde hair past the shoulders; neat elven ears with slender pointed tips; a white billowy medieval linen shirt deep plunging scoop neckline that reveals significant cleavage., with puffed sleeves; a brown leather underbust corset; fitted sage-green trousers; tall brown leather boots; brown leather gloves; a forest-green wool hooded cloak clasped at the collar. Does NOT control the face. Image FOREST LOCATION — a misty magical forest: narrow dirt path, giant glowing red mushrooms casting warm orange light, pink flowers, mossy trunks, drifting fog. 100% matches the reference. Image : UNDERWATER CITY LOCATION — the plaza: a colossal ribbed nautilus-shell palace with glowing golden seams, pearl shell houses with warm windows, god rays from above, jellyfish and drifting sea life. 100% matches the reference. FORMAT MODE One continuous shot from 0:00 to 0:19, then TWO HARD CUTS in the finale: a fast POV insert and a return to the previous framing. No fades, no dissolves. Full realism. HER BACKWARD GLANCE — HOW IT MUST LOOK, STRICT Whenever she checks behind her, she does NOT turn toward the camera and does NOT look into the lens. She rotates her head roughly 45° to ONE SIDE and her EYES GO THE SAME WAY her head goes — looking off toward that side of frame, into the fog, then snapping forward again. BANS: no over-the-shoulder look at the lens, no eye contact with the camera, no 180° head turn. SHOT 1 — 0:00–0:01.5 — HER FEET, LOW AND CANTED LOW, near ground level, canted hard — Dutch tilt ~20–25° — framing her BOOTS and lower legs sprinting along the path: soil bursting, cloak hem cracking, mushroom stalks brushing aside, path streaking in motion blur. Handheld, jolting with her rhythm; the pursuer heard far behind in the fog. SHOT 2 — 0:01.5–0:03 — HER FACE, FRIGHTENED Unbroken move: the frame rises and pushes in to her FACE — a tight running close-up travelling with her, still canted, hair whipping. Raw fear: wide eyes, brows drawn, mouth gasping, dirt on her cheek. Twice she performs the 45° glance as specified, eyes going the same way as her head, searching the fog off to that side; then forward again. SHOT 3 — 0:03–0:05 — THE TRIP, WIDE Unbroken: the frame swings out to a WIDE shot of the path — full figure, mushrooms towering, fog closing the depth. Mid-glance her leading boot CATCHES a root — the foot stops dead, momentum throws her forward, and she goes down hard in full view: knees, then hands and shoulder into the dirt, dust and leaf litter bursting up, cloak flying over her. She lands sprawled, chest heaving. SHOT 4 — 0:05–0:09 — THE MIRROR SHE ALMOST IGNORES Unbroken: the camera drifts in from the front, then around to her side, settling into profile with her and the mirror in frame. Fear first, curiosity second: sprawled, she checks behind with the 45° head-and-eyes turn; the crashing is closer. She scrambles up, barely looking ahead — then registers an ornate antique MIRROR against a mossy trunk, filled with cold blue glow unlike the warm mushroom light. Brushing dirt off her sleeve with ONE hand, her eyes stay on the glass. THE MIRROR DOES NOT REFLECT: her reflection NEVER appears, no mirror image of her, no reflection of the forest — the glass is a window filled with its own inner light: fog thinning into deep watery blue, faint caustics, vague luminous silhouettes far in the depth, no sharp image. The blue washes her face. ACTING TASK — HER CHOICE (the work happens in her eyes): glass → a 45° glance into the fog behind → glass again; she registers that nothing of HER answers her movement in it; no time to solve it. She extends ONE FINGER toward the surface. (Safety: gaze always engaged; natural blink cadence.) SHOT 5 — 0:09–0:11 — THE YANK: UNDER A SECOND Her fingertip nears the glass. The light FLARES — the surface SNAPS outward like a whip and SEIZES her hand. INSTANT: she is RIPPED off her feet, jerked forward along her outstretched arm, body whipping horizontal in a single frame, head-first through the glass, boots torn off the ground last, cloak cracking behind her. No build-up, no float — limp as a ragdoll, the mirror doing ALL of it, vector purely FORWARD through the glass plane. Camera: caught off guard WITH her — it WHIPS sideways-and-forward, slings around behind her flying body and punches through the rippling surface on her heels; water and bubbles SLAM across the lens, forest colors ripped into deep blue. NOT her POV. SHOT 6 — 0:11–0:16 — ARRIVAL IN THE PLAZA Same shot, no cut — camera behind her. THE FIRST UNDERWATER FRAME IS THE ARRIVAL FRAME: the portal exits DIRECTLY INTO the plaza of >>; the colossal nautilus palace is ALREADY in frame, its ribbed pearl wall with glowing golden seams filling the background, sharp and close; shell houses with warm windows border both sides. NO TRAVEL, no approach — the water BRAKES her within a meter or two. HER BODY: horizontal, HEAD-FIRST, back toward the surface, fully passive — arms loose, LEGS STILL AND MOTIONLESS, no kicking, no strokes; thrown cargo, not a swimmer. UNDERWATER PHYSICS, HIGHEST PRIORITY: hair streaming backward in rippling seaweed-like strands, cloak dragging in a heavy water-loaded wave; on stopping, hair and cloak drift forward past her shoulders by inertia. She pivots from horizontal to upright — feet swinging down, legs hanging relaxed — settling into weightless float facing the palace wall. HER HAIR AT REST, STRICT: no parting, no combed order — a loose free-floating mass fanning outward and upward from her whole head, strands crossing over her crown in constant slow chaotic motion, never symmetrical, never still. The cloak billows wide, breathing with the water. SHE CANNOT BREATHE UNDERWATER: cheeks slightly puffed, lips pressed, holding her breath. Bubbles rise from her mouth in small silver clusters climbing upward past her face. ACTING TASK: to ORIENT beneath something impossibly huge — her attention pulls UPWARD: head climbing the glowing houses, up the palace wall, chin lifting, trying to find where the spiral ends. Jellyfish pulse between the houses. SHOT 7 — 0:16–0:19 — SETTLE INTO THE MEDIUM PROFILE FRAME Same shot, no cut. The camera drifts smoothly from behind her around to her side and settles into the framing that holds for the rest of the film: FRAMING LOCK — MEDIUM PROFILE: she is seen from her LEFT SIDE in a medium shot, CHEST-UP ONLY — never full-body, never small in frame; her head and shoulders occupy the lower-left third, elven ear tip clear, hair a floating dark halo, white puffed sleeve and green cloak reading in the frame's bottom, one gloved hand extended forward. Behind and above her, filling the whole background, the giant glowing spiral nautilus palace; pearl shell houses along the lower edge; god rays raking down from the surface; a jellyfish drifting at frame-left; her bubbles rising past her face. She hangs weightless with the faintest sway. SHOT 8 — 0:19–0:21 — SHE TURNS HER HEAD (SAME FRAME) No cut, camera locked in the FRAMING LOCK. She turns her head sharply to look off toward frame-LEFT — a fast, alarmed head turn, eyes going the same direction, brows snapping up, a startled burst of bubbles ripping from her mouth. Her shoulder tenses; nothing else of her moves. She is still only chest-up in frame; the whale is NOT visible yet. HARD CUT. SHOT 9 — 0:21–0:22.5 — POV: THE MOUTH OPENS ON US FIRST-PERSON POV FROM HER EYES — fast and brutal: filling the entire frame, the colossal whale's head rushes in from the left, and the vast baleen MOUTH OPENS WIDE — grooved pale throat pleats stretching, a dark glowing cavern spreading until it swallows the frame edge to edge; water and bubbles ripping past the lens; the scale absolute, the opening several times larger than a human body. Quick — a second and a half, no lingering. The frame goes to the mouth's darkness. HARD CUT. SHOT 10 — 0:22.5–0:24 — BACK TO THE SAME FRAME: THE WHALE MOVES ON Return to the EXACT FRAMING LOCK of Shot 7–8 — same camera position, same background: the glowing spiral palace, the shell houses, the god rays. The girl is no longer there; only her last scattered bubbles rising where she floated. The colossal whale is already in frame with its JAW CLOSED, gliding calmly from LEFT to RIGHT across the plaza — placid, unhurried, indifferent, as if it simply fed on the way past. Its enormous flank sweeps close past the lens: dark iridescent mother-of-pearl skin shifting purple-green-blue like oil on water, scattered glowing teal rings and dotted bioluminescent lines, a tall webbed translucent dorsal fin with visible veining, pectoral and tail fins extending into long flowing translucent ribbon-streamers rippling like silk. TRUE WHALE LOCOMOTION: all thrust from the TAIL — deep lateral sweeps bending the rear third of the body, an S-wave of muscle rolling down the flanks head-to-tail on every beat, mass shifting under the skin, head steady on course, ribbon-fins streaming back like wings. Living muscle, never a rigid sculpture on rails. Its wake rocks the jellyfish and scatters her bubbles. It exits frame-RIGHT. Final beat: the empty plaza, the palace glowing, bubbles dispersing, water settling. END. Exactly ONE creature in the finale, the same individual in the POV and in the return frame — no second creature, no duplicate. No grabbing, no chewing, no thrashing, no blood, no gore — the horror is entirely scale. PHYSICS Forest: real running biomechanics, the head-turns costing her balance, the trip stopping the foot dead while momentum carries her over, a genuine three-point fall, real bodyweight in the scramble up. The yank: whip-crack acceleration, body limp, purely forward. Underwater: everything obeys water — drag on limbs and fabric, slow rebound, no dry-hair or dry-cloth behavior in any frame; the whale moves with true mass and inertia, its bow wave visibly displacing water, bubbles and jellyfish; the jaw opens and closes with weight, not like a trap. LIGHTING Forest: warm orange mushroom glow against cool misty air; the mirror's cold blue the only competing source. Underwater: cool blue depth light with god rays, warm golden light from the shell houses and the palace's glowing seams; caustic ripples crawling over her skin, the white sleeve and the whale's flank; the open mouth in the POV reading as a deep shadowed cavern with faint light only on the throat pleats. Natural exposure, no stylization. MATERIALS Real skin with pores and freckles; individual hair strands, dry and flying in the forest, water-loaded and undulating below; real linen weave, leather grain, heavy wool cloak with true water weight; real soil, moss and mushroom flesh; pearl shell with subsurface glow; the whale's iridescent hide with subsurface shift, skin folds and grooved throat pleats, translucent fin membranes. No plastic skin, no CG sheen. AUDIO — SFX ONLY, NO MUSIC 0:00–0:05: pounding footsteps, ragged breathing, cloak snapping, DISTANT crashing branches and a low guttural monster call rolling through the fog; the trip — scuff, body impact, gasp. 0:05–0:09: panicked breathing, scrambling in dirt, forest ambience, a rising crystalline hum near the glass. 0:09–0:11: a sharp liquid CRACK, one violent water-rush WHOOSH, bubbles slamming the lens; forest sound cutting off dead. 0:11–0:19: muffled underwater ambience, soft bubble streams, distant whale-like calls, faint clicks, a deep resonant hum from the palace. 0:19–0:22.5: a startled bubble burst; a deep swelling RUMBLE from the left; in the POV a roaring water-rush and the wet groan of the opening jaw. 0:22.5–0:24: one soft heavy WHOMP settling, then calm rhythmic tail SWISH, the flank's water-rush passing the lens, fading right into churning wake and settling ambience. No score, no melody anywhere. POSITIVE CONSTRAINTS Continuous shot 0:00–0:19; then exactly TWO HARD CUTS: into the POV insert and back out to the identical framing. No other cuts anywhere. FRAMING LOCK: from 0:16 to the end (except the POV insert) the camera holds the same medium profile framing — she is CHEST-UP, seen from her left side, lower-left of frame, with the glowing spiral palace filling the background. She is never shown full-body in this section, never small in frame, and the camera never moves. The finale order is exact: she turns her head left (chest-up, whale not visible) → HARD CUT to her POV of the mouth opening wide, fast → HARD CUT back to the same framing where the jaw is already closed and the whale glides calmly left to right and exits. Her glances in the forest: ~45° head turns with eyes going the same direction; never toward the lens. The forest pursuer is NEVER shown — distant sound only. The mirror NEVER reflects her or the forest — a lit window, not a reflective surface. Underwater she never swims — legs still and motionless throughout; the palace fills the background from the first underwater frame, no travel. Her hair underwater is a chaotic free-floating mass — never parted, never neat, never still. Face 100% >> every frame, zero drift; hair, elven ears, wardrobe 100% >>; forest 100% >>; plaza and palace 100% >>. No grabbing, chewing, blood or gore; exactly ONE creature; she is not visible after the POV cut, only her bubbles. Full realism — no animated look, no illustration, no CG gloss, no plastic surfaces. Clean image: no grain, no vignette. She is the only person. No text, no logos, no watermarks. OPTICS STRONG anamorphic lens character: horizontal squeeze and compression, oval elliptical bokeh, horizontally stretched highlights, curved barrel edge distortion, chromatic aberration toward the edges. NO lens flares, NO light streaks, NO floating bokeh circles. Shot 1: canted 20–25°, low on boots. Shot 2: focus locked on her face. Shot 3: wide, deep focus. Shots 4–5: her face and the mirror's glow. Shots 6–8: her in medium profile against the palace, caustics softening the depth. Shot 9 (POV): ultra-wide immersive perspective, the mouth filling the frame. Shot 10: the flank sharp as it sweeps past the lens.
0:27

What would you do if this mirror pulled you underwater? Nano Banana 2 + Seedance 2.5 on TapNow prompt SCENE CONTEXT A girl Image flees something unseen through a glowing forest, trips, falls — and finds an antique mirror that yanks her through into an underwater city. There, mid-float before the great shell palace, she turns her head — a flash of POV shows a colossal mouth opening onto her — and back in the wide frame the whale is already closing its jaw and gliding calmly away. 24 seconds, full realism. ACTIVE REFERENCES — STRICT ROLE HIERARCHY Image HER EXACT FACE — sole source of her identity and features, 100% match, zero drift: a 20-year-old , 163 cm, slim and lightly built. Soft rounded oval face; warm light-beige skin with a golden undertone and real photographic texture — visible pores, small freckles and tiny beauty marks across the cheeks and nose bridge; dark blue almond eyes with a shallow partially hidden upper-lid crease and soft under-eye fullness; thick dark straight brows with individual hairs brushed upward; a small neat nose with narrow straight bridge and softly rounded tip; full lips with a defined cupid's bow, the lower lip fuller, natural rosy tone; softly rounded jaw tapering to a small chin; small silver hoop earrings. Ignore this reference's hair, clothing, car interior and lighting. Face identity comes from this reference in every single frame. Image : CHARACTER SHEET — controls everything: long voluminous wavy blonde hair past the shoulders; neat elven ears with slender pointed tips; a white billowy medieval linen shirt deep plunging scoop neckline that reveals significant cleavage., with puffed sleeves; a brown leather underbust corset; fitted sage-green trousers; tall brown leather boots; brown leather gloves; a forest-green wool hooded cloak clasped at the collar. Does NOT control the face. Image FOREST LOCATION — a misty magical forest: narrow dirt path, giant glowing red mushrooms casting warm orange light, pink flowers, mossy trunks, drifting fog. 100% matches the reference. Image : UNDERWATER CITY LOCATION — the plaza: a colossal ribbed nautilus-shell palace with glowing golden seams, pearl shell houses with warm windows, god rays from above, jellyfish and drifting sea life. 100% matches the reference. FORMAT MODE One continuous shot from 0:00 to 0:19, then TWO HARD CUTS in the finale: a fast POV insert and a return to the previous framing. No fades, no dissolves. Full realism. HER BACKWARD GLANCE — HOW IT MUST LOOK, STRICT Whenever she checks behind her, she does NOT turn toward the camera and does NOT look into the lens. She rotates her head roughly 45° to ONE SIDE and her EYES GO THE SAME WAY her head goes — looking off toward that side of frame, into the fog, then snapping forward again. BANS: no over-the-shoulder look at the lens, no eye contact with the camera, no 180° head turn. SHOT 1 — 0:00–0:01.5 — HER FEET, LOW AND CANTED LOW, near ground level, canted hard — Dutch tilt ~20–25° — framing her BOOTS and lower legs sprinting along the path: soil bursting, cloak hem cracking, mushroom stalks brushing aside, path streaking in motion blur. Handheld, jolting with her rhythm; the pursuer heard far behind in the fog. SHOT 2 — 0:01.5–0:03 — HER FACE, FRIGHTENED Unbroken move: the frame rises and pushes in to her FACE — a tight running close-up travelling with her, still canted, hair whipping. Raw fear: wide eyes, brows drawn, mouth gasping, dirt on her cheek. Twice she performs the 45° glance as specified, eyes going the same way as her head, searching the fog off to that side; then forward again. SHOT 3 — 0:03–0:05 — THE TRIP, WIDE Unbroken: the frame swings out to a WIDE shot of the path — full figure, mushrooms towering, fog closing the depth. Mid-glance her leading boot CATCHES a root — the foot stops dead, momentum throws her forward, and she goes down hard in full view: knees, then hands and shoulder into the dirt, dust and leaf litter bursting up, cloak flying over her. She lands sprawled, chest heaving. SHOT 4 — 0:05–0:09 — THE MIRROR SHE ALMOST IGNORES Unbroken: the camera drifts in from the front, then around to her side, settling into profile with her and the mirror in frame. Fear first, curiosity second: sprawled, she checks behind with the 45° head-and-eyes turn; the crashing is closer. She scrambles up, barely looking ahead — then registers an ornate antique MIRROR against a mossy trunk, filled with cold blue glow unlike the warm mushroom light. Brushing dirt off her sleeve with ONE hand, her eyes stay on the glass. THE MIRROR DOES NOT REFLECT: her reflection NEVER appears, no mirror image of her, no reflection of the forest — the glass is a window filled with its own inner light: fog thinning into deep watery blue, faint caustics, vague luminous silhouettes far in the depth, no sharp image. The blue washes her face. ACTING TASK — HER CHOICE (the work happens in her eyes): glass → a 45° glance into the fog behind → glass again; she registers that nothing of HER answers her movement in it; no time to solve it. She extends ONE FINGER toward the surface. (Safety: gaze always engaged; natural blink cadence.) SHOT 5 — 0:09–0:11 — THE YANK: UNDER A SECOND Her fingertip nears the glass. The light FLARES — the surface SNAPS outward like a whip and SEIZES her hand. INSTANT: she is RIPPED off her feet, jerked forward along her outstretched arm, body whipping horizontal in a single frame, head-first through the glass, boots torn off the ground last, cloak cracking behind her. No build-up, no float — limp as a ragdoll, the mirror doing ALL of it, vector purely FORWARD through the glass plane. Camera: caught off guard WITH her — it WHIPS sideways-and-forward, slings around behind her flying body and punches through the rippling surface on her heels; water and bubbles SLAM across the lens, forest colors ripped into deep blue. NOT her POV. SHOT 6 — 0:11–0:16 — ARRIVAL IN THE PLAZA Same shot, no cut — camera behind her. THE FIRST UNDERWATER FRAME IS THE ARRIVAL FRAME: the portal exits DIRECTLY INTO the plaza of >>; the colossal nautilus palace is ALREADY in frame, its ribbed pearl wall with glowing golden seams filling the background, sharp and close; shell houses with warm windows border both sides. NO TRAVEL, no approach — the water BRAKES her within a meter or two. HER BODY: horizontal, HEAD-FIRST, back toward the surface, fully passive — arms loose, LEGS STILL AND MOTIONLESS, no kicking, no strokes; thrown cargo, not a swimmer. UNDERWATER PHYSICS, HIGHEST PRIORITY: hair streaming backward in rippling seaweed-like strands, cloak dragging in a heavy water-loaded wave; on stopping, hair and cloak drift forward past her shoulders by inertia. She pivots from horizontal to upright — feet swinging down, legs hanging relaxed — settling into weightless float facing the palace wall. HER HAIR AT REST, STRICT: no parting, no combed order — a loose free-floating mass fanning outward and upward from her whole head, strands crossing over her crown in constant slow chaotic motion, never symmetrical, never still. The cloak billows wide, breathing with the water. SHE CANNOT BREATHE UNDERWATER: cheeks slightly puffed, lips pressed, holding her breath. Bubbles rise from her mouth in small silver clusters climbing upward past her face. ACTING TASK: to ORIENT beneath something impossibly huge — her attention pulls UPWARD: head climbing the glowing houses, up the palace wall, chin lifting, trying to find where the spiral ends. Jellyfish pulse between the houses. SHOT 7 — 0:16–0:19 — SETTLE INTO THE MEDIUM PROFILE FRAME Same shot, no cut. The camera drifts smoothly from behind her around to her side and settles into the framing that holds for the rest of the film: FRAMING LOCK — MEDIUM PROFILE: she is seen from her LEFT SIDE in a medium shot, CHEST-UP ONLY — never full-body, never small in frame; her head and shoulders occupy the lower-left third, elven ear tip clear, hair a floating dark halo, white puffed sleeve and green cloak reading in the frame's bottom, one gloved hand extended forward. Behind and above her, filling the whole background, the giant glowing spiral nautilus palace; pearl shell houses along the lower edge; god rays raking down from the surface; a jellyfish drifting at frame-left; her bubbles rising past her face. She hangs weightless with the faintest sway. SHOT 8 — 0:19–0:21 — SHE TURNS HER HEAD (SAME FRAME) No cut, camera locked in the FRAMING LOCK. She turns her head sharply to look off toward frame-LEFT — a fast, alarmed head turn, eyes going the same direction, brows snapping up, a startled burst of bubbles ripping from her mouth. Her shoulder tenses; nothing else of her moves. She is still only chest-up in frame; the whale is NOT visible yet. HARD CUT. SHOT 9 — 0:21–0:22.5 — POV: THE MOUTH OPENS ON US FIRST-PERSON POV FROM HER EYES — fast and brutal: filling the entire frame, the colossal whale's head rushes in from the left, and the vast baleen MOUTH OPENS WIDE — grooved pale throat pleats stretching, a dark glowing cavern spreading until it swallows the frame edge to edge; water and bubbles ripping past the lens; the scale absolute, the opening several times larger than a human body. Quick — a second and a half, no lingering. The frame goes to the mouth's darkness. HARD CUT. SHOT 10 — 0:22.5–0:24 — BACK TO THE SAME FRAME: THE WHALE MOVES ON Return to the EXACT FRAMING LOCK of Shot 7–8 — same camera position, same background: the glowing spiral palace, the shell houses, the god rays. The girl is no longer there; only her last scattered bubbles rising where she floated. The colossal whale is already in frame with its JAW CLOSED, gliding calmly from LEFT to RIGHT across the plaza — placid, unhurried, indifferent, as if it simply fed on the way past. Its enormous flank sweeps close past the lens: dark iridescent mother-of-pearl skin shifting purple-green-blue like oil on water, scattered glowing teal rings and dotted bioluminescent lines, a tall webbed translucent dorsal fin with visible veining, pectoral and tail fins extending into long flowing translucent ribbon-streamers rippling like silk. TRUE WHALE LOCOMOTION: all thrust from the TAIL — deep lateral sweeps bending the rear third of the body, an S-wave of muscle rolling down the flanks head-to-tail on every beat, mass shifting under the skin, head steady on course, ribbon-fins streaming back like wings. Living muscle, never a rigid sculpture on rails. Its wake rocks the jellyfish and scatters her bubbles. It exits frame-RIGHT. Final beat: the empty plaza, the palace glowing, bubbles dispersing, water settling. END. Exactly ONE creature in the finale, the same individual in the POV and in the return frame — no second creature, no duplicate. No grabbing, no chewing, no thrashing, no blood, no gore — the horror is entirely scale. PHYSICS Forest: real running biomechanics, the head-turns costing her balance, the trip stopping the foot dead while momentum carries her over, a genuine three-point fall, real bodyweight in the scramble up. The yank: whip-crack acceleration, body limp, purely forward. Underwater: everything obeys water — drag on limbs and fabric, slow rebound, no dry-hair or dry-cloth behavior in any frame; the whale moves with true mass and inertia, its bow wave visibly displacing water, bubbles and jellyfish; the jaw opens and closes with weight, not like a trap. LIGHTING Forest: warm orange mushroom glow against cool misty air; the mirror's cold blue the only competing source. Underwater: cool blue depth light with god rays, warm golden light from the shell houses and the palace's glowing seams; caustic ripples crawling over her skin, the white sleeve and the whale's flank; the open mouth in the POV reading as a deep shadowed cavern with faint light only on the throat pleats. Natural exposure, no stylization. MATERIALS Real skin with pores and freckles; individual hair strands, dry and flying in the forest, water-loaded and undulating below; real linen weave, leather grain, heavy wool cloak with true water weight; real soil, moss and mushroom flesh; pearl shell with subsurface glow; the whale's iridescent hide with subsurface shift, skin folds and grooved throat pleats, translucent fin membranes. No plastic skin, no CG sheen. AUDIO — SFX ONLY, NO MUSIC 0:00–0:05: pounding footsteps, ragged breathing, cloak snapping, DISTANT crashing branches and a low guttural monster call rolling through the fog; the trip — scuff, body impact, gasp. 0:05–0:09: panicked breathing, scrambling in dirt, forest ambience, a rising crystalline hum near the glass. 0:09–0:11: a sharp liquid CRACK, one violent water-rush WHOOSH, bubbles slamming the lens; forest sound cutting off dead. 0:11–0:19: muffled underwater ambience, soft bubble streams, distant whale-like calls, faint clicks, a deep resonant hum from the palace. 0:19–0:22.5: a startled bubble burst; a deep swelling RUMBLE from the left; in the POV a roaring water-rush and the wet groan of the opening jaw. 0:22.5–0:24: one soft heavy WHOMP settling, then calm rhythmic tail SWISH, the flank's water-rush passing the lens, fading right into churning wake and settling ambience. No score, no melody anywhere. POSITIVE CONSTRAINTS Continuous shot 0:00–0:19; then exactly TWO HARD CUTS: into the POV insert and back out to the identical framing. No other cuts anywhere. FRAMING LOCK: from 0:16 to the end (except the POV insert) the camera holds the same medium profile framing — she is CHEST-UP, seen from her left side, lower-left of frame, with the glowing spiral palace filling the background. She is never shown full-body in this section, never small in frame, and the camera never moves. The finale order is exact: she turns her head left (chest-up, whale not visible) → HARD CUT to her POV of the mouth opening wide, fast → HARD CUT back to the same framing where the jaw is already closed and the whale glides calmly left to right and exits. Her glances in the forest: ~45° head turns with eyes going the same direction; never toward the lens. The forest pursuer is NEVER shown — distant sound only. The mirror NEVER reflects her or the forest — a lit window, not a reflective surface. Underwater she never swims — legs still and motionless throughout; the palace fills the background from the first underwater frame, no travel. Her hair underwater is a chaotic free-floating mass — never parted, never neat, never still. Face 100% >> every frame, zero drift; hair, elven ears, wardrobe 100% >>; forest 100% >>; plaza and palace 100% >>. No grabbing, chewing, blood or gore; exactly ONE creature; she is not visible after the POV cut, only her bubbles. Full realism — no animated look, no illustration, no CG gloss, no plastic surfaces. Clean image: no grain, no vignette. She is the only person. No text, no logos, no watermarks. OPTICS STRONG anamorphic lens character: horizontal squeeze and compression, oval elliptical bokeh, horizontally stretched highlights, curved barrel edge distortion, chromatic aberration toward the edges. NO lens flares, NO light streaks, NO floating bokeh circles. Shot 1: canted 20–25°, low on boots. Shot 2: focus locked on her face. Shot 3: wide, deep focus. Shots 4–5: her face and the mirror's glow. Shots 6–8: her in medium profile against the palace, caustics softening the depth. Shot 9 (POV): ultra-wide immersive perspective, the mouth filling the frame. Shot 10: the flank sharp as it sweeps past the lens.

Sharon Riley

28,464 Aufrufe • vor 1 Monat

EPISODE 1- FINAL REPLAY Was their love story built on a lie? The championship was over, but the biggest betrayal was just beginning. Made with Nano Banana 2 + Seedance 2.0 on RoboNeo prompt Style: Ultra-cinematic drama, premium streaming-series aesthetics, photorealistic visuals, anamorphic framing, shallow depth of field, luxurious golden ballroom lighting with dramatic shadows, subtle facial acting, slow deliberate camera moves, emotional orchestral score swelling with tension. GRAND GALA BALLROOM – NIGHT 0–5s | Recall & Re-hook Freeze frame from Episode Zero lingers on the brunette’s @[Image 2](image_2) knowing smile as she lowers her wine glass. The giant replay screen behind her flashes blinding white. Hard cut to black. A single heartbeat sound. The replay screen bursts to life — but instead of football highlights, it shows intimate, hidden footage: the football champion @[Image 4](image_4) and the elegant dark-haired brunette @[Image 2](image_2) in a passionate embrace in a private locker room, his winner’s medal still around his neck. The crowd in the ballroom gasps audibly. 5–12s | Consequence Cut to the blonde woman @[Image 3](image_3) at the elegant table. Her face drains of color as she stares at the massive screen. Tears well up again. She picks up her engagement ring from the table in her bare hand and clutches it so tightly it digs into her right hand. The football champion @[Image 4](image_4)(still in black suit, medal now missing from his neck) stands frozen a few feet away, horror dawning on his face. He (medal now missing from his neck) turns toward the screen, then desperately toward the blonde. Blonde woman (whispering, broken): “You said it was only the match that changed everything…” The blonde @[Image 2](image_2) walks away abruptly, knocking over a champagne flute. It shatters loudly on the marble floor — the sound cutting through the now-hushed ballroom. She looks between the champion @[Image 3](image_3) and the brunette @[Image 1](image_1), betrayal turning to cold fury. Blonde woman @[Image 2](image_2)(voice cracking but gaining strength): “Then why does the final replay show you celebrating with her… while I waited for you?” The replay screen loops the damning embrace in slow motion. Guests murmur and film with their phones. 27–30s | Next Cliffhanger The brunette @[Image 1](image_1) smiles wider, turns, and begins walking away through the crowd as the replay screen suddenly cuts to new unseen footage — a close-up of the brunette @[Image 1](image_1) slipping something into the champion’s drink earlier that night, followed by a quick flash of a mysterious document with official-looking seals. The champion’s face twists in shock and realization. The blonde’s eyes widen in horror as she sees it too. Freeze frame on the three of them — triangle of tension. Text on screen fades in: EPISODE TWO Fade to black. Distant crowd applause mixes with a rising, ominous orchestral sting.
0:36

EPISODE 1- FINAL REPLAY Was their love story built on a lie? The championship was over, but the biggest betrayal was just beginning. Made with Nano Banana 2 + Seedance 2.0 on RoboNeo prompt Style: Ultra-cinematic drama, premium streaming-series aesthetics, photorealistic visuals, anamorphic framing, shallow depth of field, luxurious golden ballroom lighting with dramatic shadows, subtle facial acting, slow deliberate camera moves, emotional orchestral score swelling with tension. GRAND GALA BALLROOM – NIGHT 0–5s | Recall & Re-hook Freeze frame from Episode Zero lingers on the brunette’s @[Image 2](image_2) knowing smile as she lowers her wine glass. The giant replay screen behind her flashes blinding white. Hard cut to black. A single heartbeat sound. The replay screen bursts to life — but instead of football highlights, it shows intimate, hidden footage: the football champion @[Image 4](image_4) and the elegant dark-haired brunette @[Image 2](image_2) in a passionate embrace in a private locker room, his winner’s medal still around his neck. The crowd in the ballroom gasps audibly. 5–12s | Consequence Cut to the blonde woman @[Image 3](image_3) at the elegant table. Her face drains of color as she stares at the massive screen. Tears well up again. She picks up her engagement ring from the table in her bare hand and clutches it so tightly it digs into her right hand. The football champion @[Image 4](image_4)(still in black suit, medal now missing from his neck) stands frozen a few feet away, horror dawning on his face. He (medal now missing from his neck) turns toward the screen, then desperately toward the blonde. Blonde woman (whispering, broken): “You said it was only the match that changed everything…” The blonde @[Image 2](image_2) walks away abruptly, knocking over a champagne flute. It shatters loudly on the marble floor — the sound cutting through the now-hushed ballroom. She looks between the champion @[Image 3](image_3) and the brunette @[Image 1](image_1), betrayal turning to cold fury. Blonde woman @[Image 2](image_2)(voice cracking but gaining strength): “Then why does the final replay show you celebrating with her… while I waited for you?” The replay screen loops the damning embrace in slow motion. Guests murmur and film with their phones. 27–30s | Next Cliffhanger The brunette @[Image 1](image_1) smiles wider, turns, and begins walking away through the crowd as the replay screen suddenly cuts to new unseen footage — a close-up of the brunette @[Image 1](image_1) slipping something into the champion’s drink earlier that night, followed by a quick flash of a mysterious document with official-looking seals. The champion’s face twists in shock and realization. The blonde’s eyes widen in horror as she sees it too. Freeze frame on the three of them — triangle of tension. Text on screen fades in: EPISODE TWO Fade to black. Distant crowd applause mixes with a rising, ominous orchestral sting.

Sharon Riley

68,710 Aufrufe • vor 2 Monaten

In Heat, the scene with Robert De Niro and Amy Brenneman looking out over the Los Angeles skyline, is one of the most beautiful shots in all of crime cinema. However, it was also incredibly difficult to pull off in 1995, before the introduction of digital cinematography Heat was shot on Kodak EXR 500T 5298, a fast tungsten-balanced film stock designed for low-light photography. This allowed cinematographer Dante Spinotti to shoot night scenes without blasting the actors with harsh movie lights. Instead, he could rely on softer, more naturalistic light sources, while still allowing the audience to see deep into the darkness of nighttime Los Angeles. That stock was ideal for the terrace scene between De Niro and Brenneman. It could capture the soft light spilling from De Niro’s house onto their faces, keeping the scene intimate and natural. But there was still a problem: they were working on film. Once they exposed correctly for the actors, the background of Los Angeles’ skyline disappeared into darkness. Michael Mann wanted to preserve the brilliance of the cityscape, and the way it reflected off the night clouds, while still maintaining that soft, romantic glow on the actors. So Spinotti came up with a clever solution. He shot the background separately using Panavision Primo lenses opened all the way to T2, meaning the aperture was set extremely wide so the lens could take in as much light as possible. First, he shot the night sky at 4 frames per second. Because the camera was running much slower than normal, each frame was exposed for longer, giving the film more time to absorb the faint light in the sky. Then he shot the skyline separately at 12 frames per second. This gave the lights more brightness and clarity. He also pushed the film one stop. In simple terms, he shot the film as if it needed less light than it actually did, then had the lab develop it longer to bring the brightness back up. This made the city lights register far more strongly, while the darker parts of the image fell deeper into black - creating what Spinotti described as a glowing “ocean of lights.” They then shot the scene on location with a greenscreen placed behind or, in some setups, in front of the actors. What you’re seeing in the final shot is three separate film elements - the sky, the city lights, and the actors - all exposed differently, at different frame rates, then combined through digital compositing into a single image. The result is strangely beautiful. De Niro and Brenneman seem almost suspended in mid-air, floating above the city lights, giving the moment an almost abstract, dreamlike quality - one that perfectly complements the overall tone of the scene.
2:25

In Heat, the scene with Robert De Niro and Amy Brenneman looking out over the Los Angeles skyline, is one of the most beautiful shots in all of crime cinema. However, it was also incredibly difficult to pull off in 1995, before the introduction of digital cinematography Heat was shot on Kodak EXR 500T 5298, a fast tungsten-balanced film stock designed for low-light photography. This allowed cinematographer Dante Spinotti to shoot night scenes without blasting the actors with harsh movie lights. Instead, he could rely on softer, more naturalistic light sources, while still allowing the audience to see deep into the darkness of nighttime Los Angeles. That stock was ideal for the terrace scene between De Niro and Brenneman. It could capture the soft light spilling from De Niro’s house onto their faces, keeping the scene intimate and natural. But there was still a problem: they were working on film. Once they exposed correctly for the actors, the background of Los Angeles’ skyline disappeared into darkness. Michael Mann wanted to preserve the brilliance of the cityscape, and the way it reflected off the night clouds, while still maintaining that soft, romantic glow on the actors. So Spinotti came up with a clever solution. He shot the background separately using Panavision Primo lenses opened all the way to T2, meaning the aperture was set extremely wide so the lens could take in as much light as possible. First, he shot the night sky at 4 frames per second. Because the camera was running much slower than normal, each frame was exposed for longer, giving the film more time to absorb the faint light in the sky. Then he shot the skyline separately at 12 frames per second. This gave the lights more brightness and clarity. He also pushed the film one stop. In simple terms, he shot the film as if it needed less light than it actually did, then had the lab develop it longer to bring the brightness back up. This made the city lights register far more strongly, while the darker parts of the image fell deeper into black - creating what Spinotti described as a glowing “ocean of lights.” They then shot the scene on location with a greenscreen placed behind or, in some setups, in front of the actors. What you’re seeing in the final shot is three separate film elements - the sky, the city lights, and the actors - all exposed differently, at different frame rates, then combined through digital compositing into a single image. The result is strangely beautiful. De Niro and Brenneman seem almost suspended in mid-air, floating above the city lights, giving the moment an almost abstract, dreamlike quality - one that perfectly complements the overall tone of the scene.

Gangster Cinema Central

122,996 Aufrufe • vor 3 Monaten

Seedance 2.5 POV video. The best AI video model is live. Full prompt: POV — Morning Commute in Coastal Japan | Ultra-Realistic, One Continuous Take First-person POV, no cuts, one unbroken handheld-feeling shot from our own eyes on the way through a small seaside town. Ultra-photorealistic, phone-in-hand realism — natural camera micro-shake, subtle head bob with each step, occasional glance down at our own hands and shoes. 4K, shallow but natural depth of field, real morning light, no color-grading fantasy, no neon. Beat 1 — Descending into the station (0–4s): We walk down worn concrete station stairs into a small coastal-town metro entrance, one hand loosely gripping a canvas bag strap that swings into the lower frame. Fluorescent tint mixes with daylight bleeding from the entrance behind us. Commuters pass in soft focus; we hear muffled announcements and the shuffle of footsteps. Beat 2 — The orange cat (4–9s): We slow and crouch — the horizon dips as our POV lowers toward the ground. An orange tabby sits by a ticket-gate pillar, tail curled. Our hand (natural skin texture, slightly bitten nails, cuff of a sleeve) reaches into frame and gently strokes its head. The cat leans into the touch, eyes half-closing, ears flicking. We hold there a beat, warm and quiet. Beat 3 — Boarding, settling by the window (9–14s): We rise, the horizon lifts, and we step through the train doors just as the chime sounds. POV turns and moves toward a window seat; we sit, and the frame settles against the glass. A faint silhouette of us ghosts over the view. The train pulls away with a gentle lurch. Beat 4 — The shimmering sea (14–20s): Through the window, the town gives way to open coastline. Sunlight scatters across the water in thousands of moving sparkles — real specular glitter, not CGI bloom. Utility poles and wires strobe past in the foreground. We rest our chin lightly (subtle downward frame tilt), just watching. Beat 5 — Rails into the sea (20–25s): The track curves and runs so close to the shore that the rails seem to vanish straight into the water — the sea fills nearly the whole frame, waves lapping right up to the ballast. Foam catches the light. We're gliding along the edge of the ocean, the horizon line steady, gulls crossing in the distance. Hold on this until the shot ends. Technical spec: continuous POV, first-person, no cuts or transitions, natural handheld micro-motion, realistic morning ambient audio (station hum, cat, train chime, rail clatter, distant surf), authentic Japanese coastal-railway setting (Shimonada / Enoden-style seaside line), overcast-to-clear soft daylight, photoreal skin and fabric texture, 2.39:1 or 16:9, ultra-realistic. Coming soon to Higgsfield.
0:28

Seedance 2.5 POV video. The best AI video model is live. Full prompt: POV — Morning Commute in Coastal Japan | Ultra-Realistic, One Continuous Take First-person POV, no cuts, one unbroken handheld-feeling shot from our own eyes on the way through a small seaside town. Ultra-photorealistic, phone-in-hand realism — natural camera micro-shake, subtle head bob with each step, occasional glance down at our own hands and shoes. 4K, shallow but natural depth of field, real morning light, no color-grading fantasy, no neon. Beat 1 — Descending into the station (0–4s): We walk down worn concrete station stairs into a small coastal-town metro entrance, one hand loosely gripping a canvas bag strap that swings into the lower frame. Fluorescent tint mixes with daylight bleeding from the entrance behind us. Commuters pass in soft focus; we hear muffled announcements and the shuffle of footsteps. Beat 2 — The orange cat (4–9s): We slow and crouch — the horizon dips as our POV lowers toward the ground. An orange tabby sits by a ticket-gate pillar, tail curled. Our hand (natural skin texture, slightly bitten nails, cuff of a sleeve) reaches into frame and gently strokes its head. The cat leans into the touch, eyes half-closing, ears flicking. We hold there a beat, warm and quiet. Beat 3 — Boarding, settling by the window (9–14s): We rise, the horizon lifts, and we step through the train doors just as the chime sounds. POV turns and moves toward a window seat; we sit, and the frame settles against the glass. A faint silhouette of us ghosts over the view. The train pulls away with a gentle lurch. Beat 4 — The shimmering sea (14–20s): Through the window, the town gives way to open coastline. Sunlight scatters across the water in thousands of moving sparkles — real specular glitter, not CGI bloom. Utility poles and wires strobe past in the foreground. We rest our chin lightly (subtle downward frame tilt), just watching. Beat 5 — Rails into the sea (20–25s): The track curves and runs so close to the shore that the rails seem to vanish straight into the water — the sea fills nearly the whole frame, waves lapping right up to the ballast. Foam catches the light. We're gliding along the edge of the ocean, the horizon line steady, gulls crossing in the distance. Hold on this until the shot ends. Technical spec: continuous POV, first-person, no cuts or transitions, natural handheld micro-motion, realistic morning ambient audio (station hum, cat, train chime, rail clatter, distant surf), authentic Japanese coastal-railway setting (Shimonada / Enoden-style seaside line), overcast-to-clear soft daylight, photoreal skin and fabric texture, 2.39:1 or 16:9, ultra-realistic. Coming soon to Higgsfield.

Higgsfield AI 🧩

37,368 Aufrufe • vor 1 Monat

The world's highest DJ party. 🚀🎧☁️ Thousands of festival lovers dancing on floating islands while music lights up the sky. Made with GPT Image 2 + Seedance on Pollo AI #PolloAI #PolloPeakMoment Part 1 Scene 1 (0–5s): An ultra-smooth FPV drone flies through bright clouds toward the floating festival island. The massive stage slowly emerges above the clouds while thousands of people dance. The camera passes beneath transparent sky bridges, floating holograms, and hovering drones before revealing the enormous DJ stage glowing in warm sunset light. Scene 2 (5–10s): Low-angle hero shot. The female DJ confidently walks to the center of the stage as the audience erupts with excitement. Giant LED walls ignite, laser towers activate one after another, synchronized drones rise into the sky, and glowing wristbands illuminate across the crowd. Slow cinematic orbit around the DJ before pushing into a close-up of her determined expression. Scene 3 (10–15s): The DJ places both hands on the mixer and starts the performance. Powerful bass begins. Cyan, magenta, and violet laser beams sweep across the clouds. Smoke cannons erupt, holographic equalizers appear behind the stage, and shimmering confetti fills the air. A cinematic crane shot rises above the crowd as everyone jumps together. Part 2 Scene 4 (15–20s): Motion resumes from the frozen frame. The beat drops. The DJ lowers her raised hand and begins an energetic performance while operating the mixer. Massive holographic wings unfold behind the stage. Thousands of synchronized drones form giant stars and rotating circles above the crowd. Neon lasers sweep through the clouds as lightning flashes in perfect sync with the music. Dynamic orbit shot around the DJ transitions into a wide hero view. Scene 5 (20–25s): The festival reaches maximum energy. Fireworks explode across the sky. Crystal balloons release sparkling confetti. The audience jumps in perfect rhythm, waving glowing light sticks. The camera flies through the cheering crowd before circling the DJ booth. Giant holographic equalizers pulse with every bass hit while colorful energy waves ripple across the clouds. Scene 6 (25–30s): A breathtaking aerial drone pullback reveals the entire floating festival glowing above endless clouds. Drones assemble into a gigantic luminous phoenix soaring above the stage while fireworks illuminate every floating island. The DJ raises both hands in celebration as the audience erupts with excitement. The camera climbs higher and higher, revealing the immense floating festival stretching toward the horizon under a star-filled blue-hour sky, ending with a slow cinematic fade to black.
0:34

The world's highest DJ party. 🚀🎧☁️ Thousands of festival lovers dancing on floating islands while music lights up the sky. Made with GPT Image 2 + Seedance on Pollo AI #PolloAI #PolloPeakMoment Part 1 Scene 1 (0–5s): An ultra-smooth FPV drone flies through bright clouds toward the floating festival island. The massive stage slowly emerges above the clouds while thousands of people dance. The camera passes beneath transparent sky bridges, floating holograms, and hovering drones before revealing the enormous DJ stage glowing in warm sunset light. Scene 2 (5–10s): Low-angle hero shot. The female DJ confidently walks to the center of the stage as the audience erupts with excitement. Giant LED walls ignite, laser towers activate one after another, synchronized drones rise into the sky, and glowing wristbands illuminate across the crowd. Slow cinematic orbit around the DJ before pushing into a close-up of her determined expression. Scene 3 (10–15s): The DJ places both hands on the mixer and starts the performance. Powerful bass begins. Cyan, magenta, and violet laser beams sweep across the clouds. Smoke cannons erupt, holographic equalizers appear behind the stage, and shimmering confetti fills the air. A cinematic crane shot rises above the crowd as everyone jumps together. Part 2 Scene 4 (15–20s): Motion resumes from the frozen frame. The beat drops. The DJ lowers her raised hand and begins an energetic performance while operating the mixer. Massive holographic wings unfold behind the stage. Thousands of synchronized drones form giant stars and rotating circles above the crowd. Neon lasers sweep through the clouds as lightning flashes in perfect sync with the music. Dynamic orbit shot around the DJ transitions into a wide hero view. Scene 5 (20–25s): The festival reaches maximum energy. Fireworks explode across the sky. Crystal balloons release sparkling confetti. The audience jumps in perfect rhythm, waving glowing light sticks. The camera flies through the cheering crowd before circling the DJ booth. Giant holographic equalizers pulse with every bass hit while colorful energy waves ripple across the clouds. Scene 6 (25–30s): A breathtaking aerial drone pullback reveals the entire floating festival glowing above endless clouds. Drones assemble into a gigantic luminous phoenix soaring above the stage while fireworks illuminate every floating island. The DJ raises both hands in celebration as the audience erupts with excitement. The camera climbs higher and higher, revealing the immense floating festival stretching toward the horizon under a star-filled blue-hour sky, ending with a slow cinematic fade to black.

Stonic AI

89,079 Aufrufe • vor 2 Monaten

POV: The kiss that broke the internet, recreated with AI on the tip of Tokyo Tower. A viral cinematic moment, reimagined with seamless camera movement, perfect character consistency, and a breathtaking skyline that never leaves the frame. Every shot stays locked to the very top of Tokyo Tower for a romance that feels straight out of a blockbuster. Made with GPT Image 2 and Seedance on Pollo AI for the Peak Moment Challenge. Prompt: PART 1 • 0:00–0:15 — THE REVEAL & THE KISS (9:16) 0:00–0:03 — Arrival Continuous crane arc already in motion around the couple on the tip of Tokyo Tower's antenna mast. Only one Tokyo Tower visible. Wind moves Jessy's hair and trench dress. He wears the yellow kawaii mascot helmet. Jessy: "You're seriously wearing that up here?" Man: "Only for you." 0:03–0:06 — Reveal Camera continues the same arc. He removes the helmet, revealing tousled brown hair and blue eyes. 0:06–0:09 — Pull Continuous crane widens. He pulls Jessy close by the waist, she grabs his jacket collar. The Polloai flag becomes visible above. 0:09–0:12 — Kiss Camera keeps pulling back with a subtle Dutch roll. They kiss on the tip of Tokyo Tower as the grade transitions from hazy news footage to warm cinematic. 0:12–0:15 — Sway Wide shot. They slowly turn while kissing. Tokyo Tower and the Polloai flag remain clearly visible. PART 2 • 0:15–0:25 — THE SPIN & THE VIEW (9:16) Continuity: First frame must exactly match the last frame of Part 1. 0:15–0:18 — Spin Continue the identical crane arc and orbit. He spins Jessy once on the tower tip. Dress, jewelry and blue-streaked hair flow naturally. Jessy: "Don't drop me from up here!" 0:18–0:21 — Second Kiss Orbit tightens into a close two-shot. They share another soft kiss, foreheads touching between kisses. 0:21–0:23 — View Camera cranes upward and pulls back. They face the glowing Tokyo skyline together with the Polloai flag above. 0:23–0:25 — Hold Slow push-in. They remain embracing on the tip of Tokyo Tower until fade to black. Strict: Maintain the exact reference camera movement throughout. All actions happen only on the tip of Tokyo Tower, with only one Tokyo Tower visible in every shot. #PolloAI #PolloPeakMoment
0:32

POV: The kiss that broke the internet, recreated with AI on the tip of Tokyo Tower. A viral cinematic moment, reimagined with seamless camera movement, perfect character consistency, and a breathtaking skyline that never leaves the frame. Every shot stays locked to the very top of Tokyo Tower for a romance that feels straight out of a blockbuster. Made with GPT Image 2 and Seedance on Pollo AI for the Peak Moment Challenge. Prompt: PART 1 • 0:00–0:15 — THE REVEAL & THE KISS (9:16) 0:00–0:03 — Arrival Continuous crane arc already in motion around the couple on the tip of Tokyo Tower's antenna mast. Only one Tokyo Tower visible. Wind moves Jessy's hair and trench dress. He wears the yellow kawaii mascot helmet. Jessy: "You're seriously wearing that up here?" Man: "Only for you." 0:03–0:06 — Reveal Camera continues the same arc. He removes the helmet, revealing tousled brown hair and blue eyes. 0:06–0:09 — Pull Continuous crane widens. He pulls Jessy close by the waist, she grabs his jacket collar. The Polloai flag becomes visible above. 0:09–0:12 — Kiss Camera keeps pulling back with a subtle Dutch roll. They kiss on the tip of Tokyo Tower as the grade transitions from hazy news footage to warm cinematic. 0:12–0:15 — Sway Wide shot. They slowly turn while kissing. Tokyo Tower and the Polloai flag remain clearly visible. PART 2 • 0:15–0:25 — THE SPIN & THE VIEW (9:16) Continuity: First frame must exactly match the last frame of Part 1. 0:15–0:18 — Spin Continue the identical crane arc and orbit. He spins Jessy once on the tower tip. Dress, jewelry and blue-streaked hair flow naturally. Jessy: "Don't drop me from up here!" 0:18–0:21 — Second Kiss Orbit tightens into a close two-shot. They share another soft kiss, foreheads touching between kisses. 0:21–0:23 — View Camera cranes upward and pulls back. They face the glowing Tokyo skyline together with the Polloai flag above. 0:23–0:25 — Hold Slow push-in. They remain embracing on the tip of Tokyo Tower until fade to black. Strict: Maintain the exact reference camera movement throughout. All actions happen only on the tip of Tokyo Tower, with only one Tokyo Tower visible in every shot. #PolloAI #PolloPeakMoment

Jessica Collins

35,777 Aufrufe • vor 2 Monaten

Seedance 2.5 is incredible It can take you to any city in the world. Xin chào Việt Nam 🇻🇳 It feels like I actually traveled to Hanoi, Vietnam! 👇Feel free to add any city you’d like to visit to this prompt. HANOI TRAVEL VLOG — 30 SEC No reference image. The woman below is described in words and must be built from the text alone. SUBJECT: one Korean woman, early 20s, the only person the film follows. Small oval face with a soft jawline, large round eyes with double lids, a small straight nose, full coral-red lips, fair skin. Black wavy hair tied low at the nape and pulled forward over one shoulder, with loose strands left at the temples. A small gold hoop in each ear. Real Korean skin texture with visible pores — no doll-like AI smoothness, no beauty filter. The face established in the first shot is repeated exactly in every following shot: same features, same hair, same colour. She never morphs into a different person and no lookalike appears. OUTFIT (identical throughout): burgundy ribbed knit halter top, cream high-waist flared trousers, tan leather belt with a gold buckle, burgundy platform heeled sandals, a thin gold bracelet on one wrist. There is no changing shot. CAMERA: she is filming herself on her own phone. Most shots are selfies with her arm extended; objects and food are shot by turning the phone toward them. 16:9 landscape throughout, no black bars. 26mm phone lens, deep focus, neutral iPhone colour, handheld jolt on every step, autofocus landing a beat late, exposure lagging when she moves from bright to dark, a fingerprint smudge bleeding beside strong lights. No cinematic grading, no studio lighting, no glow fx. Background people stay out of focus and nobody looks at the camera for long. DIALOGUE: lines are short and land in one breath. An interjection plus one short sentence is fine, but never two complete sentences strung together. There is breath between them and they are never rushed into each other. Punctuation is used once — no doubled question marks or exclamation marks. The two Vietnamese greetings are not fluent — just phrases she has picked up. (0:00–0:02) — Hotel window, Hanoi morning reveal. Selfie, low angle. She shoves the curtain sideways and narrow tube houses under bundled cables open up behind her. The window blows out white, then the exposure catches up. Bright grin. Dialogue: "Xin chào~ 하노이 왔다!" Transition: Hard cut on beat (0:02–0:04) — Old Quarter junction, a river of motorbikes. Selfie, stepping out between the bikes. She swings the phone to her face while a stream of helmets and conical hats flows behind her, horns overlapping. Overcast daylight, deep focus. Dialogue: "이걸 어떻게 건너?" Transition: Fast cut on beat (0:04–0:06) — Street café. Selfie, arm short. She pushes a glass with condensed milk settled at the bottom toward the lens until it fills half the frame, eyebrows raised. Low backless stools, a stained yellow French wall behind. Transition: Snap cut (0:06–0:08) — Alley bánh mì cart. Insert, phone pointed down at her hands. A baguette split over the charcoal is handed to her in newspaper and she peels the paper down with her fingertips. Steam rises and a few sprigs of coriander stick out of the split. White tube light on the cart, a parked motorbike beside it. Transition: Cut on natural movement (0:08–0:09.75) — Huc Bridge reveal. She raises the phone from her face and tilts it up until the red wooden bridge crossing the lake fills the frame. Natural daylight, sky blown out behind a banyan tree. Her mouth opens slightly. Transition: Soft cut mid-upward motion (0:09.75–0:12) — Train Street café. Selfie. On a low stool beside the track she is holding a coffee glass in both hands; hearing it come she sets the glass down and pulls her stool back against the wall. She looks at the lens, then sideways, and her face collapses into a laugh as a train comes out of the far end of the lane and passes an arm's length away. Dialogue: "헐 진짜 온닷ㅋㅋㅋㅋ" Transition: Cut on the end of the laugh (0:12–0:13.75) — Old Quarter, the 36 streets. Follow from behind, phone low. She shoulders through the packed lane with the bánh mì, finishes the last piece and folds the newspaper away. Unlit lanterns and signs stacked tight overhead, people pushing past. Overcast afternoon light. Transition: Cut on forward movement (0:13.75–0:15.5) — Back seat of a cyclo. Her hands are empty now — the phone low at knee height in one hand, the rail in the other. The street slides past under the folded canopy, the driver's back swaying in front. She looks out, not at the lens. The music drops a beat, leaving only wheels and horns. Transition: Snap cut (0:15.5–0:18) — Phở shop. From here the image is camcorder: blooming tape, light noise, late focus. The camera is fixed at eye level across the counter, no phone or camera visible in frame. Medium. She sits down on a low blue stool under a hand-painted Phở sign. The owner sets a steaming bowl of beef phở down — thin-sliced beef, rice noodles, spring onion, a side plate of sprouts and basil. Dialogue: "쌀국수! 이거 먹으러 왔어~" Transition: Cut on the bowl landing (0:18–0:20) — Lifting the noodles. Macro, phone lowered to the bowl, shallow focus. She draws rice noodles up out of the clear broth with her chopsticks, steam climbing. The steam crosses the lens and one side of the frame hazes over and clears. Only the broth and the slurping at the next stool. Transition: Cut with the noodles still raised (0:20–0:22) — First mouthful. Selfie, handheld. She pulls in a big mouthful, closes her eyes and opens them. Her shoulders drop and she nods once at the lens. Just after sundown, the white fluorescent light of the shop. Dialogue: "미쳤다 진짜." Transition: Cut where her face softens (0:22–0:23.5) — The broth. Selfie, close. She lifts the bowl in both hands, tips it back, sets it down and lets out a breath. The lens fogs with steam. Sound only. Transition: Cut back to phone image quality (0:23.5–0:27) — Tạ Hiện beer street ★signature. She steps into the narrow lane on an extended-arm selfie, walking between the rows of low plastic stools set out on the ground, and slowly lifts her head. Red, yellow and green lanterns hung low across the lane slide over her face and the same colours bleed across the wet ground. Rack focus — her face sharp, the signs behind spreading. Practical light only, no glow. 60% slow motion. Transition: Soft cut with her head still up (0:27–0:30) — Long Biên Bridge, night reveal. Close selfie → arm extends → the river and the Hanoi night open up below. Wind pushes her bangs across her eyes once. Natural night phone exposure. Dialogue: "그럼 모두 tạm biệt~!" She waves broadly at the camera and that same hand covers the lens as the frame goes dark. AUDIO: real location sound over the music. Unbroken motorbike horns and engines, stools scraping the pavement, charcoal sizzling, a train horn and rails, cyclo wheels, broth boiling and chopsticks, slurping at the next stool, night street noise, wind. Her muttering is natural Korean. CONSISTENCY: the same face, the same hair and the same clothes in every shot. Hands and chopsticks are natural with no smeared fingers. No text, no subtitles, no logo and no watermark on screen. No filming equipment is visible in frame. FINALLY: this has to look like footage a real person shot on a phone. Nothing about the face, the skin or the movement should read as AI-generated. Every line of dialogue is enunciated clearly, syllable by syllable — no slurring, no swallowed syllables, no clipped word endings, and the tense consonants and final consonants of Korean are pronounced accurately. Expressions and gestures are not performed; they are what the moment would naturally produce.
0:31

Seedance 2.5 is incredible It can take you to any city in the world. Xin chào Việt Nam 🇻🇳 It feels like I actually traveled to Hanoi, Vietnam! 👇Feel free to add any city you’d like to visit to this prompt. HANOI TRAVEL VLOG — 30 SEC No reference image. The woman below is described in words and must be built from the text alone. SUBJECT: one Korean woman, early 20s, the only person the film follows. Small oval face with a soft jawline, large round eyes with double lids, a small straight nose, full coral-red lips, fair skin. Black wavy hair tied low at the nape and pulled forward over one shoulder, with loose strands left at the temples. A small gold hoop in each ear. Real Korean skin texture with visible pores — no doll-like AI smoothness, no beauty filter. The face established in the first shot is repeated exactly in every following shot: same features, same hair, same colour. She never morphs into a different person and no lookalike appears. OUTFIT (identical throughout): burgundy ribbed knit halter top, cream high-waist flared trousers, tan leather belt with a gold buckle, burgundy platform heeled sandals, a thin gold bracelet on one wrist. There is no changing shot. CAMERA: she is filming herself on her own phone. Most shots are selfies with her arm extended; objects and food are shot by turning the phone toward them. 16:9 landscape throughout, no black bars. 26mm phone lens, deep focus, neutral iPhone colour, handheld jolt on every step, autofocus landing a beat late, exposure lagging when she moves from bright to dark, a fingerprint smudge bleeding beside strong lights. No cinematic grading, no studio lighting, no glow fx. Background people stay out of focus and nobody looks at the camera for long. DIALOGUE: lines are short and land in one breath. An interjection plus one short sentence is fine, but never two complete sentences strung together. There is breath between them and they are never rushed into each other. Punctuation is used once — no doubled question marks or exclamation marks. The two Vietnamese greetings are not fluent — just phrases she has picked up. (0:00–0:02) — Hotel window, Hanoi morning reveal. Selfie, low angle. She shoves the curtain sideways and narrow tube houses under bundled cables open up behind her. The window blows out white, then the exposure catches up. Bright grin. Dialogue: "Xin chào~ 하노이 왔다!" Transition: Hard cut on beat (0:02–0:04) — Old Quarter junction, a river of motorbikes. Selfie, stepping out between the bikes. She swings the phone to her face while a stream of helmets and conical hats flows behind her, horns overlapping. Overcast daylight, deep focus. Dialogue: "이걸 어떻게 건너?" Transition: Fast cut on beat (0:04–0:06) — Street café. Selfie, arm short. She pushes a glass with condensed milk settled at the bottom toward the lens until it fills half the frame, eyebrows raised. Low backless stools, a stained yellow French wall behind. Transition: Snap cut (0:06–0:08) — Alley bánh mì cart. Insert, phone pointed down at her hands. A baguette split over the charcoal is handed to her in newspaper and she peels the paper down with her fingertips. Steam rises and a few sprigs of coriander stick out of the split. White tube light on the cart, a parked motorbike beside it. Transition: Cut on natural movement (0:08–0:09.75) — Huc Bridge reveal. She raises the phone from her face and tilts it up until the red wooden bridge crossing the lake fills the frame. Natural daylight, sky blown out behind a banyan tree. Her mouth opens slightly. Transition: Soft cut mid-upward motion (0:09.75–0:12) — Train Street café. Selfie. On a low stool beside the track she is holding a coffee glass in both hands; hearing it come she sets the glass down and pulls her stool back against the wall. She looks at the lens, then sideways, and her face collapses into a laugh as a train comes out of the far end of the lane and passes an arm's length away. Dialogue: "헐 진짜 온닷ㅋㅋㅋㅋ" Transition: Cut on the end of the laugh (0:12–0:13.75) — Old Quarter, the 36 streets. Follow from behind, phone low. She shoulders through the packed lane with the bánh mì, finishes the last piece and folds the newspaper away. Unlit lanterns and signs stacked tight overhead, people pushing past. Overcast afternoon light. Transition: Cut on forward movement (0:13.75–0:15.5) — Back seat of a cyclo. Her hands are empty now — the phone low at knee height in one hand, the rail in the other. The street slides past under the folded canopy, the driver's back swaying in front. She looks out, not at the lens. The music drops a beat, leaving only wheels and horns. Transition: Snap cut (0:15.5–0:18) — Phở shop. From here the image is camcorder: blooming tape, light noise, late focus. The camera is fixed at eye level across the counter, no phone or camera visible in frame. Medium. She sits down on a low blue stool under a hand-painted Phở sign. The owner sets a steaming bowl of beef phở down — thin-sliced beef, rice noodles, spring onion, a side plate of sprouts and basil. Dialogue: "쌀국수! 이거 먹으러 왔어~" Transition: Cut on the bowl landing (0:18–0:20) — Lifting the noodles. Macro, phone lowered to the bowl, shallow focus. She draws rice noodles up out of the clear broth with her chopsticks, steam climbing. The steam crosses the lens and one side of the frame hazes over and clears. Only the broth and the slurping at the next stool. Transition: Cut with the noodles still raised (0:20–0:22) — First mouthful. Selfie, handheld. She pulls in a big mouthful, closes her eyes and opens them. Her shoulders drop and she nods once at the lens. Just after sundown, the white fluorescent light of the shop. Dialogue: "미쳤다 진짜." Transition: Cut where her face softens (0:22–0:23.5) — The broth. Selfie, close. She lifts the bowl in both hands, tips it back, sets it down and lets out a breath. The lens fogs with steam. Sound only. Transition: Cut back to phone image quality (0:23.5–0:27) — Tạ Hiện beer street ★signature. She steps into the narrow lane on an extended-arm selfie, walking between the rows of low plastic stools set out on the ground, and slowly lifts her head. Red, yellow and green lanterns hung low across the lane slide over her face and the same colours bleed across the wet ground. Rack focus — her face sharp, the signs behind spreading. Practical light only, no glow. 60% slow motion. Transition: Soft cut with her head still up (0:27–0:30) — Long Biên Bridge, night reveal. Close selfie → arm extends → the river and the Hanoi night open up below. Wind pushes her bangs across her eyes once. Natural night phone exposure. Dialogue: "그럼 모두 tạm biệt~!" She waves broadly at the camera and that same hand covers the lens as the frame goes dark. AUDIO: real location sound over the music. Unbroken motorbike horns and engines, stools scraping the pavement, charcoal sizzling, a train horn and rails, cyclo wheels, broth boiling and chopsticks, slurping at the next stool, night street noise, wind. Her muttering is natural Korean. CONSISTENCY: the same face, the same hair and the same clothes in every shot. Hands and chopsticks are natural with no smeared fingers. No text, no subtitles, no logo and no watermark on screen. No filming equipment is visible in frame. FINALLY: this has to look like footage a real person shot on a phone. Nothing about the face, the skin or the movement should read as AI-generated. Every line of dialogue is enunciated clearly, syllable by syllable — no slurring, no swallowed syllables, no clipped word endings, and the tense consonants and final consonants of Korean are pronounced accurately. Expressions and gestures are not performed; they are what the moment would naturally produce.

MagicAI

22,943 Aufrufe • vor 1 Monat

She doesn’t play tennis. She hunts points. Every cut hits like a winner. Made with Seedance 2.5 on Fish Creative Try it for free 👇 Prompt: STEP 05 - SEEDANCE 2.5 GENERATION SEEDANCE 2.5 STORYBOARD AS REFERENCE FAST CUT 24FPS HANDHELD THROUGHOUT AESTHETIC: Cinematic sports reel, 20 seconds, 16:9. Natural light, highlight halation. Handheld micro-tremor, never gimbal. Fast cuts every 0.8-1.5s. Motion blur 24fps, 35mm grain. Fixed midday light all 20 seconds: overhead sun, hard short shadows. CHARACTER: Young athletic woman from REFERENCE IMAGE. Dark brown hair in high ponytail with loose strands, white Nike visor, navy Nike racerback tank with white swoosh, navy pleated tennis skirt with white swoosh, white wristband, fine gold chain with small cross, holding tennis racket. USE REFERENCE IMAGE FOR FACE AND EXACT WARDROBE. Same outfit every single shot. Do not change colors, logos, hair, or jewelry. LOCATION: Outdoor tennis court. Blue cobalt inside, green outside, white lines. Black fence, empty bleachers. Midday sun. [0:00-0:01] Extreme close-up top-down. White sneakers and navy skirt hem frame the racket. She spins the racket two rotations from the handle on the blue court. [0:01-0:02] Close-up face from reference image — eyes bright, half smile, one hand on visor, tosses yellow ball in air, slight dolly-out. [0:02-0:03] Match cut on ball to overhead top-down. She completes the serve on the baseline. Hard short shadow at her feet. [0:03-0:05] Medium handheld counter-direction. Violent forehand drive, torso rotating, navy tank twisting, racket cutting air. [0:05-0:06] Low angle dutch tilt. Running parallel to the net in navy skirt, forehand with motion blur. [0:06-0:07] Full shot. Jumping to smash overhead against the sky, ponytail and visor catching sun. [0:07-0:08] Extreme close-up footwork. White sneakers moving fast on blue cobalt court. [0:08-0:09] Medium through net mesh, slow dolly-in, slow motion. Tucks a loose strand behind ear, lowers racket, same face and navy kit from reference. [0:09-0:10] Extreme low angle, backlit sun. Serves in slow motion from behind, silhouette of visor, tank, and skirt against sky. [0:10-0:11] Wide from blurred bleachers. Small figure hitting crosscourt backhand. [0:11-0:12] Reverse medium handheld other side of the net. Two-handed backhand, weight back, navy outfit identical to reference. [0:12-0:13] Wide from bleachers. Small figure forehand drive. [0:13-0:15] Medium handheld counter-direction. Violent forehand drive closing the point. [0:15-0:17] Hero close-up. Same face as reference image, slight smile, hand near visor, midday sun, navy Nike kit. [0:17-0:20] Extreme low angle through racket strings. Face from reference behind the strings. Bounces yellow ball twice, brings ball toward lens until it fills the frame. AUDIO: No dialogue. Diegetic sound only — ball impact, sneaker squeak, breathing, ball bounce, palm wind, fence vibration. No music in engine.
0:20

She doesn’t play tennis. She hunts points. Every cut hits like a winner. Made with Seedance 2.5 on Fish Creative Try it for free 👇 Prompt: STEP 05 - SEEDANCE 2.5 GENERATION SEEDANCE 2.5 STORYBOARD AS REFERENCE FAST CUT 24FPS HANDHELD THROUGHOUT AESTHETIC: Cinematic sports reel, 20 seconds, 16:9. Natural light, highlight halation. Handheld micro-tremor, never gimbal. Fast cuts every 0.8-1.5s. Motion blur 24fps, 35mm grain. Fixed midday light all 20 seconds: overhead sun, hard short shadows. CHARACTER: Young athletic woman from REFERENCE IMAGE. Dark brown hair in high ponytail with loose strands, white Nike visor, navy Nike racerback tank with white swoosh, navy pleated tennis skirt with white swoosh, white wristband, fine gold chain with small cross, holding tennis racket. USE REFERENCE IMAGE FOR FACE AND EXACT WARDROBE. Same outfit every single shot. Do not change colors, logos, hair, or jewelry. LOCATION: Outdoor tennis court. Blue cobalt inside, green outside, white lines. Black fence, empty bleachers. Midday sun. [0:00-0:01] Extreme close-up top-down. White sneakers and navy skirt hem frame the racket. She spins the racket two rotations from the handle on the blue court. [0:01-0:02] Close-up face from reference image — eyes bright, half smile, one hand on visor, tosses yellow ball in air, slight dolly-out. [0:02-0:03] Match cut on ball to overhead top-down. She completes the serve on the baseline. Hard short shadow at her feet. [0:03-0:05] Medium handheld counter-direction. Violent forehand drive, torso rotating, navy tank twisting, racket cutting air. [0:05-0:06] Low angle dutch tilt. Running parallel to the net in navy skirt, forehand with motion blur. [0:06-0:07] Full shot. Jumping to smash overhead against the sky, ponytail and visor catching sun. [0:07-0:08] Extreme close-up footwork. White sneakers moving fast on blue cobalt court. [0:08-0:09] Medium through net mesh, slow dolly-in, slow motion. Tucks a loose strand behind ear, lowers racket, same face and navy kit from reference. [0:09-0:10] Extreme low angle, backlit sun. Serves in slow motion from behind, silhouette of visor, tank, and skirt against sky. [0:10-0:11] Wide from blurred bleachers. Small figure hitting crosscourt backhand. [0:11-0:12] Reverse medium handheld other side of the net. Two-handed backhand, weight back, navy outfit identical to reference. [0:12-0:13] Wide from bleachers. Small figure forehand drive. [0:13-0:15] Medium handheld counter-direction. Violent forehand drive closing the point. [0:15-0:17] Hero close-up. Same face as reference image, slight smile, hand near visor, midday sun, navy Nike kit. [0:17-0:20] Extreme low angle through racket strings. Face from reference behind the strings. Bounces yellow ball twice, brings ball toward lens until it fills the frame. AUDIO: No dialogue. Diegetic sound only — ball impact, sneaker squeak, breathing, ball bounce, palm wind, fence vibration. No music in engine.

Shami

30,367 Aufrufe • vor 24 Tagen

U-Net by hand ✍️ ~ 17 steps walkthrough below I consider U-Net as a key milestone in deep learning, the first image-to-image model that really worked! It came out of medical imaging, an unusual place, not from NeurIPS or CVPR or ACL. Now it is the backbone of diffusion models, which you see in almost all modern image generation models. I drew the network as a C so the matrix multiplication flows naturally down. Tilt your head to the right and it is a U again. 🤣 Goal: push a 3 x 16 image down to a 2 x 4 bottleneck and back out again, filling in every cell yourself. = 1. Given = An image of three channels, R, G and B, sixteen pixels wide, and every kernel the network will use. = 2. Convolution 1 = Let us slide the first kernel over the image. Each output is one multiply-and-add over a 2 x 3 window, and the result is the green feature map. = 3. Find the maxima = We circle the largest value in each 1 x 2 window. Circling first is worth the extra step: it is the pooling decision, made before anything is written down. = 4. Max pool 1 = Let us copy those maxima down. Sixteen columns become eight, and half the detail is gone for good. = 5. Convolution 2 = We convolve again with the second kernel, deeper into the contracting path. The feature map is blue now. = 6. Find the maxima again = Same move as step 3, on the blue map. = 7. Max pool 2 = Eight columns become four. = 8. The bottleneck = Let us convolve once more. This is the bottom of the U, a 2 x 4 block that is everything the network kept. = 9. Spread it out = We start back up. The transposed convolution writes each bottleneck value into a wider grid, leaving gaps between them. = 10. Transposed convolution 1 = Let us fill those gaps by convolving over the spread-out grid. Four columns become eight. = 11. The first skip = We copy the encoder's matching row straight across. This is the skip connection, and it is the whole reason a U-Net can recover detail that pooling threw away. = 12. Convolution with the skip = Let us convolve the upsampled features together with the copied ones. = 13. Spread it out again = Same as step 9, one level up. = 14. Transposed convolution 2 = Eight columns become sixteen, back to the width we started at. = 15. The second skip = The encoder's first feature map comes across, the one made before any pooling happened. = 16. Convolution and ReLU = We convolve, then cross out every negative and set it to zero. = 17. Output convolution = Let us apply the last kernel. Out comes R', G' and B', an image the same size as the one we started with. The outputs: R' = [3, 0, 7, 0, 7, 0, 17, 0, 3, 0, 9, 0, 2, 0, 6, 0] G' = [1, 20, 1, 10, 1, 12, 1, 19, 2, 5, 1, 11, 1, 3, 1, 7] B' = [4, 20, 8, 10, 8, 12, 18, 19, 5, 5, 10, 11, 3, 3, 7, 7] Congrats! You just calculated a U-Net by hand. 💾 Save this post!
0:37

U-Net by hand ✍️ ~ 17 steps walkthrough below I consider U-Net as a key milestone in deep learning, the first image-to-image model that really worked! It came out of medical imaging, an unusual place, not from NeurIPS or CVPR or ACL. Now it is the backbone of diffusion models, which you see in almost all modern image generation models. I drew the network as a C so the matrix multiplication flows naturally down. Tilt your head to the right and it is a U again. 🤣 Goal: push a 3 x 16 image down to a 2 x 4 bottleneck and back out again, filling in every cell yourself. = 1. Given = An image of three channels, R, G and B, sixteen pixels wide, and every kernel the network will use. = 2. Convolution 1 = Let us slide the first kernel over the image. Each output is one multiply-and-add over a 2 x 3 window, and the result is the green feature map. = 3. Find the maxima = We circle the largest value in each 1 x 2 window. Circling first is worth the extra step: it is the pooling decision, made before anything is written down. = 4. Max pool 1 = Let us copy those maxima down. Sixteen columns become eight, and half the detail is gone for good. = 5. Convolution 2 = We convolve again with the second kernel, deeper into the contracting path. The feature map is blue now. = 6. Find the maxima again = Same move as step 3, on the blue map. = 7. Max pool 2 = Eight columns become four. = 8. The bottleneck = Let us convolve once more. This is the bottom of the U, a 2 x 4 block that is everything the network kept. = 9. Spread it out = We start back up. The transposed convolution writes each bottleneck value into a wider grid, leaving gaps between them. = 10. Transposed convolution 1 = Let us fill those gaps by convolving over the spread-out grid. Four columns become eight. = 11. The first skip = We copy the encoder's matching row straight across. This is the skip connection, and it is the whole reason a U-Net can recover detail that pooling threw away. = 12. Convolution with the skip = Let us convolve the upsampled features together with the copied ones. = 13. Spread it out again = Same as step 9, one level up. = 14. Transposed convolution 2 = Eight columns become sixteen, back to the width we started at. = 15. The second skip = The encoder's first feature map comes across, the one made before any pooling happened. = 16. Convolution and ReLU = We convolve, then cross out every negative and set it to zero. = 17. Output convolution = Let us apply the last kernel. Out comes R', G' and B', an image the same size as the one we started with. The outputs: R' = [3, 0, 7, 0, 7, 0, 17, 0, 3, 0, 9, 0, 2, 0, 6, 0] G' = [1, 20, 1, 10, 1, 12, 1, 19, 2, 5, 1, 11, 1, 3, 1, 7] B' = [4, 20, 8, 10, 8, 12, 18, 19, 5, 5, 10, 11, 3, 3, 7, 7] Congrats! You just calculated a U-Net by hand. 💾 Save this post!

Tom Yeh

17,722 Aufrufe • vor 2 Monaten

What if your favorite childhood toy had its own story before finding you? 🧸 Created with Seedance 2.0 on FlovaAI #Flovaai #Flovacpp FlovaAI_Japan PROMPT: Style: Premium Pixar-quality 3D animation, anime-inspired facial expressions, ultra-detailed fur simulation, cinematic lighting, magical realism, vibrant toy store, expressive eyes, soft bloom, ray-traced reflections, dynamic camera movement, Hollywood animated film quality. Prompt: Open with an ultra-wide cinematic establishing shot of a massive premium toy store during golden hour as families browse colorful aisles. Fast dolly shot through shelves overflowing with plush toys, action figures, trains, dolls, and racing cars. Cut to a low-angle close-up of Oliver, the caramel teddy bear with his blue scarf, sitting proudly on the shelf. His amber eyes sparkle with hope. Match cut to six-year-old Emma running excitedly into frame, stopping directly in front of Oliver. Extreme close-up of her smiling face as she hugs him tightly against her chest. Over-the-shoulder shot from Oliver's perspective as Emma happily says, "Can we get this one?" Her mother reaches toward the shelf—but accidentally grabs another identical teddy from behind him. Quick push-in on Oliver's face as his smile fades. Slow-motion shot of Emma walking away while looking back at him. Rack focus from Oliver's tearful eyes to the closing automatic doors. The store lights dim one by one. A loud CLICK echoes as the final light switches off. 🎬 PART 2 — "When Toys Wake Up" Duration: 0:15–0:30 Prompt: Complete darkness. Oliver's button eyes slowly blink open. Extreme close-up of his eyes reflecting moonlight. Whip pan across the store as hundreds of toys suddenly come alive. RC cars drift through polished floors leaving glowing tire streaks. Toy trains rush along display tracks. Dolls laugh while twirling between shelves. Giant Rex the dinosaur lets out a playful roar that shakes nearby boxes. Titan-X activates with glowing cyan eyes. Fast handheld-style tracking shot follows Oliver sprinting across shelves. He leaps between toy boxes in slow motion. Dynamic overhead shot as Bolt the RC car races underneath him, giving him a boost. Oliver lands perfectly onto Chug the toy train as it speeds around a corner. Dramatic orbit shot around Oliver as he quietly whispers, "I have to find her." The music builds rapidly. 🎬 PART 3 — "The Adventure" Duration: 0:30–0:45 Prompt: High-speed action montage. Oliver jumps off the moving train onto hanging gift ribbons, swinging across the aisle. Fast rotating camera follows him weaving through floating balloons. Rex accidentally crashes through stacked toy boxes, causing colorful blocks to rain everywhere. Oliver slides beneath a closing display shelf in slow motion. Bolt races beside him before launching him off a miniature toy ramp. FPV-style camera flies alongside Oliver as he narrowly avoids spinning helicopters and bouncing rubber balls. Titan-X extends a mechanical arm, catching Oliver just before he falls from a high shelf. Cinematic top-down shot reveals the giant locked entrance doors. Oliver runs with everything he has, but the automatic doors refuse to open. Extreme close-up of his tiny paw pressing against the cold glass. Outside, the first rays of sunrise begin to appear. 🎬 PART 4 — "Meant to Be" Duration: 0:45–1:00 Prompt: Soft emotional piano begins. Low-angle shot of Oliver sitting sadly near the entrance as the toys quietly watch from behind. Suddenly, a restocking employee pushes Mr. Wheels, the shopping cart, through the entrance. Dynamic tracking shot as Mochi nudges Oliver forward. Titan-X gently lifts him while Bolt gives one final speed boost. Oliver jumps through the air in beautiful slow motion, perfectly landing inside the shopping cart filled with new toys. Match cut to the toy display being restocked moments later. The store opens. Bright morning sunlight floods the entrance. Emma runs back inside with her mother. Handheld child-height camera follows her weaving through customers. She suddenly freezes, her eyes widening. Push-in on Oliver sitting exactly at the front of the display. "Mom! It's him!" She hugs Oliver tightly against her chest. Extreme close-up of Oliver's stitched smile as one tiny happy tear forms in his eye. The camera slowly cranes upward as Emma walks toward the glowing exit carrying Oliver. Warm golden sunlight fills the frame. Fade to white. Final Screen Text: "Some friendships are simply meant to be." 🧸✨
1:00

What if your favorite childhood toy had its own story before finding you? 🧸 Created with Seedance 2.0 on FlovaAI #Flovaai #Flovacpp FlovaAI_Japan PROMPT: Style: Premium Pixar-quality 3D animation, anime-inspired facial expressions, ultra-detailed fur simulation, cinematic lighting, magical realism, vibrant toy store, expressive eyes, soft bloom, ray-traced reflections, dynamic camera movement, Hollywood animated film quality. Prompt: Open with an ultra-wide cinematic establishing shot of a massive premium toy store during golden hour as families browse colorful aisles. Fast dolly shot through shelves overflowing with plush toys, action figures, trains, dolls, and racing cars. Cut to a low-angle close-up of Oliver, the caramel teddy bear with his blue scarf, sitting proudly on the shelf. His amber eyes sparkle with hope. Match cut to six-year-old Emma running excitedly into frame, stopping directly in front of Oliver. Extreme close-up of her smiling face as she hugs him tightly against her chest. Over-the-shoulder shot from Oliver's perspective as Emma happily says, "Can we get this one?" Her mother reaches toward the shelf—but accidentally grabs another identical teddy from behind him. Quick push-in on Oliver's face as his smile fades. Slow-motion shot of Emma walking away while looking back at him. Rack focus from Oliver's tearful eyes to the closing automatic doors. The store lights dim one by one. A loud CLICK echoes as the final light switches off. 🎬 PART 2 — "When Toys Wake Up" Duration: 0:15–0:30 Prompt: Complete darkness. Oliver's button eyes slowly blink open. Extreme close-up of his eyes reflecting moonlight. Whip pan across the store as hundreds of toys suddenly come alive. RC cars drift through polished floors leaving glowing tire streaks. Toy trains rush along display tracks. Dolls laugh while twirling between shelves. Giant Rex the dinosaur lets out a playful roar that shakes nearby boxes. Titan-X activates with glowing cyan eyes. Fast handheld-style tracking shot follows Oliver sprinting across shelves. He leaps between toy boxes in slow motion. Dynamic overhead shot as Bolt the RC car races underneath him, giving him a boost. Oliver lands perfectly onto Chug the toy train as it speeds around a corner. Dramatic orbit shot around Oliver as he quietly whispers, "I have to find her." The music builds rapidly. 🎬 PART 3 — "The Adventure" Duration: 0:30–0:45 Prompt: High-speed action montage. Oliver jumps off the moving train onto hanging gift ribbons, swinging across the aisle. Fast rotating camera follows him weaving through floating balloons. Rex accidentally crashes through stacked toy boxes, causing colorful blocks to rain everywhere. Oliver slides beneath a closing display shelf in slow motion. Bolt races beside him before launching him off a miniature toy ramp. FPV-style camera flies alongside Oliver as he narrowly avoids spinning helicopters and bouncing rubber balls. Titan-X extends a mechanical arm, catching Oliver just before he falls from a high shelf. Cinematic top-down shot reveals the giant locked entrance doors. Oliver runs with everything he has, but the automatic doors refuse to open. Extreme close-up of his tiny paw pressing against the cold glass. Outside, the first rays of sunrise begin to appear. 🎬 PART 4 — "Meant to Be" Duration: 0:45–1:00 Prompt: Soft emotional piano begins. Low-angle shot of Oliver sitting sadly near the entrance as the toys quietly watch from behind. Suddenly, a restocking employee pushes Mr. Wheels, the shopping cart, through the entrance. Dynamic tracking shot as Mochi nudges Oliver forward. Titan-X gently lifts him while Bolt gives one final speed boost. Oliver jumps through the air in beautiful slow motion, perfectly landing inside the shopping cart filled with new toys. Match cut to the toy display being restocked moments later. The store opens. Bright morning sunlight floods the entrance. Emma runs back inside with her mother. Handheld child-height camera follows her weaving through customers. She suddenly freezes, her eyes widening. Push-in on Oliver sitting exactly at the front of the display. "Mom! It's him!" She hugs Oliver tightly against her chest. Extreme close-up of Oliver's stitched smile as one tiny happy tear forms in his eye. The camera slowly cranes upward as Emma walks toward the glowing exit carrying Oliver. Warm golden sunlight fills the frame. Fade to white. Final Screen Text: "Some friendships are simply meant to be." 🧸✨

Sophia

126,206 Aufrufe • vor 1 Monat

Who better than our God of Style, #Thalaivar Rajinikanth as Baasha? 😎🔥 Bringing that authentic ’90s Thalaivar vibe into the Storm Dance trend #HiggsfieldLavaStorm ⚡ 🎥 Powered by Higgsfield AI 🧩 Genjutsu #Superstar #Rajinikanth Prompt 👇 Recreate this music video shot-for-shot using Video1 as the complete motion, performance and camera reference, Image1 as the crowd characters, Image2 as the lead, Image3 as the location, and Image4 as the cigar prop. CAST REPLACEMENT: The LEAD PERFORMER in Video1 is replaced by the lead from Image2 — a commanding stylish man, 6ft, silver-streaked dark wavy hair, full dark beard, round tinted sunglasses, cream-white tailored blazer over an open white shirt with a red cravat at the throat, a wide red silk sash at the waist, white trousers and white dress shoes. He stands dead centre with total authority and performs the lead's exact movements, turns and timing. The ENTIRE CROWD in Video1 is replaced by identical copies of the character in Image1 — a faceless humanoid figure in a glossy white helmet with a black mirrored visor and white over-ear headphones, black high-collar jacket over a black turtleneck, black tactical cargo trousers with straps and buckles, black high-top sneakers. Dozens of them, identical, in tight geometric rows filling the frame, moving in perfect unison exactly as the reference crowd does. LOCATION: replace the setting with Image3 — wide monumental black steps made of deep star-field stone speckled with glittering constellations, thin luminous edge-lines along each step, a vast black void above, and the faint silhouette of a colossal coiling dragon arcing through the darkness in the background. Pale floor at the base. PROP: in the opening shot, the lead holds and draws on the cigar from Image4 — a thick dark maduro cigar with a black-and-gold band and red BAASHA lettering, lit tip glowing with a grey ash cap and a thin curl of smoke — replacing the cigarette from the reference. He raises it to his lips and exhales slowly on the same beat. COPY TWO LAYERS FROM Video1 EXACTLY: 1. Motion and performance — copy the choreography, unison crowd movement, formation changes, head tilts, bows, body rolls and all timing exactly. Every beat lands at the same moment. Match the pace exactly, not slower. The crowd moves as one machine, perfectly synchronised. 2. Camera motion — copy the camera work exactly: the same angles, the slow continuous pull-back and scale reveal, push-ins, rises, tilts and framing at every moment, frame-for-frame, keeping the lead centred throughout. VFX: as the camera pulls back for the full group reveal, thin veils of soft white smoke drift in low from the left and right edges of the frame and rise gently through the rows, catching the light and thickening the atmosphere without obscuring the figures. STYLE: cinematic black-and-white, high contrast, ultra-wide cinematic framing, glossy white helmets against deep black, dramatic monumental scale, premium music-video quality matching Video1. Negative prompt: visible eyes on the robots, mismatched crowd outfits, lead blending into the crowd, cigarette, colour footage, warm colour grade, slow motion, slower than reference, static locked-off camera, ignoring reference camera motion, breaking formation, changing the location, heavy fog obscuring the figures, distorted hands, extra limbs, watermark, logo, subtitles.
0:36

Who better than our God of Style, #Thalaivar Rajinikanth as Baasha? 😎🔥 Bringing that authentic ’90s Thalaivar vibe into the Storm Dance trend #HiggsfieldLavaStorm ⚡ 🎥 Powered by Higgsfield AI 🧩 Genjutsu #Superstar #Rajinikanth Prompt 👇 Recreate this music video shot-for-shot using Video1 as the complete motion, performance and camera reference, Image1 as the crowd characters, Image2 as the lead, Image3 as the location, and Image4 as the cigar prop. CAST REPLACEMENT: The LEAD PERFORMER in Video1 is replaced by the lead from Image2 — a commanding stylish man, 6ft, silver-streaked dark wavy hair, full dark beard, round tinted sunglasses, cream-white tailored blazer over an open white shirt with a red cravat at the throat, a wide red silk sash at the waist, white trousers and white dress shoes. He stands dead centre with total authority and performs the lead's exact movements, turns and timing. The ENTIRE CROWD in Video1 is replaced by identical copies of the character in Image1 — a faceless humanoid figure in a glossy white helmet with a black mirrored visor and white over-ear headphones, black high-collar jacket over a black turtleneck, black tactical cargo trousers with straps and buckles, black high-top sneakers. Dozens of them, identical, in tight geometric rows filling the frame, moving in perfect unison exactly as the reference crowd does. LOCATION: replace the setting with Image3 — wide monumental black steps made of deep star-field stone speckled with glittering constellations, thin luminous edge-lines along each step, a vast black void above, and the faint silhouette of a colossal coiling dragon arcing through the darkness in the background. Pale floor at the base. PROP: in the opening shot, the lead holds and draws on the cigar from Image4 — a thick dark maduro cigar with a black-and-gold band and red BAASHA lettering, lit tip glowing with a grey ash cap and a thin curl of smoke — replacing the cigarette from the reference. He raises it to his lips and exhales slowly on the same beat. COPY TWO LAYERS FROM Video1 EXACTLY: 1. Motion and performance — copy the choreography, unison crowd movement, formation changes, head tilts, bows, body rolls and all timing exactly. Every beat lands at the same moment. Match the pace exactly, not slower. The crowd moves as one machine, perfectly synchronised. 2. Camera motion — copy the camera work exactly: the same angles, the slow continuous pull-back and scale reveal, push-ins, rises, tilts and framing at every moment, frame-for-frame, keeping the lead centred throughout. VFX: as the camera pulls back for the full group reveal, thin veils of soft white smoke drift in low from the left and right edges of the frame and rise gently through the rows, catching the light and thickening the atmosphere without obscuring the figures. STYLE: cinematic black-and-white, high contrast, ultra-wide cinematic framing, glossy white helmets against deep black, dramatic monumental scale, premium music-video quality matching Video1. Negative prompt: visible eyes on the robots, mismatched crowd outfits, lead blending into the crowd, cigarette, colour footage, warm colour grade, slow motion, slower than reference, static locked-off camera, ignoring reference camera motion, breaking formation, changing the location, heavy fog obscuring the figures, distorted hands, extra limbs, watermark, logo, subtitles.

Syed Abuthahir ∞

20,071 Aufrufe • vor 8 Tagen

DRONE VIDEOGRAPHERS CHARGE $10K FOR THIS SHOT. HE PULLS IT FROM GOOGLE EARTH AND A PROMPT You never buy a drone, book a pilot, or leave the house. You pick any city on Earth, trace the flight path you want, and let Gemini render it as real-looking FPV footage. Clients pay thousands for this shot. You make it from a screenshot Here is the exact process: 1. Open Google Earth. Find the city or building you want. Frame the angle you'd want a drone to start from and take a screenshot 2. Draw the path. On that screenshot, draw a red line showing exactly where the drone should fly through the scene. This line is what the AI follows 3. Open Gemini and drop in the screenshot. Use the video generation in the Gemini app, the part that animates a still image into motion. Nano Banana handles images, the video engine is what turns your shot into footage 4. Paste the prompt. Tell it to follow the red flight path through the city, fast smooth motion, banking around buildings, golden-hour light, motion blur, 9:16 vertical, real FPV drone look. Full prompt is in the comments 5. Generate and clean it up. One clip is a few seconds. Stitch a couple together for a full flythrough and you have a reel Set the prompt once and you can re-run it for any location on the planet Who pays for this: Real estate agents, hotels, restaurants and event venues all need aerial b-roll and almost none can afford a real drone shoot Pull listings or venues with flat, ground-level photos and zero aerial footage. Send a free sample flythrough of their own location, then charge per clip or a monthly rate for ongoing reels One agent with ten listings is a recurring client, fully online Full prompt in the comments Bookmark this
0:21

DRONE VIDEOGRAPHERS CHARGE $10K FOR THIS SHOT. HE PULLS IT FROM GOOGLE EARTH AND A PROMPT You never buy a drone, book a pilot, or leave the house. You pick any city on Earth, trace the flight path you want, and let Gemini render it as real-looking FPV footage. Clients pay thousands for this shot. You make it from a screenshot Here is the exact process: 1. Open Google Earth. Find the city or building you want. Frame the angle you'd want a drone to start from and take a screenshot 2. Draw the path. On that screenshot, draw a red line showing exactly where the drone should fly through the scene. This line is what the AI follows 3. Open Gemini and drop in the screenshot. Use the video generation in the Gemini app, the part that animates a still image into motion. Nano Banana handles images, the video engine is what turns your shot into footage 4. Paste the prompt. Tell it to follow the red flight path through the city, fast smooth motion, banking around buildings, golden-hour light, motion blur, 9:16 vertical, real FPV drone look. Full prompt is in the comments 5. Generate and clean it up. One clip is a few seconds. Stitch a couple together for a full flythrough and you have a reel Set the prompt once and you can re-run it for any location on the planet Who pays for this: Real estate agents, hotels, restaurants and event venues all need aerial b-roll and almost none can afford a real drone shoot Pull listings or venues with flat, ground-level photos and zero aerial footage. Send a free sample flythrough of their own location, then charge per clip or a monthly rate for ongoing reels One agent with ten listings is a recurring client, fully online Full prompt in the comments Bookmark this

Yarchi

53,401 Aufrufe • vor 3 Monaten

一番最後の[Prompt for original image]の部分に画像生成に使用したPromptを入れると一貫性が増します。不要な場合は3行削ってしまっても大丈夫です。 --- Extreme wide-angle perspective and dynamic pose remix edit. This is an EDIT of the original image, not a new character. Use the original image as a strict reference for: – the person’s identity, hairstyle, and overall fashion style, – the general type of background and location (same street, same room, same beach, same kind of architecture, etc.). You are allowed to completely change the camera position, angle, and pose, but you must keep the scene in the SAME location and keep the SAME person and outfit design. Camera and perspective: – Use an ultra wide-angle or fisheye feeling lens (around 12–18mm full-frame look). – The camera angle MUST change significantly from the original: use dramatic angles such as • worm’s-eye view from directly below looking up, • bird’s-eye view from directly above looking down, • very low angle from the ground, • high angle from above, • tilted Dutch angles. – Always create strong foreshortening: body parts close to the lens look huge, while the rest of the body falls away in perspective. – The final result must look like a bold fashion or street photo, fully photorealistic, not illustration or anime. Background consistency: – Keep the same location as the original image: same street, same bridge, same room, same studio, same beach, same general structures and materials. – Do NOT replace the background with a completely different place. – Because the camera angle changes, it is allowed and expected that different parts of the environment become visible. – When new areas appear, extend the original environment logically (same buildings, fences, road markings, walls, colors, materials, lighting style), as if the camera moved within the same place. Body parts near the lens (1–2 parts, sometimes 3): – In each edit, choose ONE or TWO main body parts to be extremely close to the lens (sometimes even THREE in more complex poses). – Vary them from image to image, do NOT always use the same body part. – Allowed near-the-lens parts include: • one or both hands / fingers reaching toward the camera, • one or both feet / shoes / boots near the lens, • knees or thighs, • face very close to the lens, • shoulders or chest close to the lens in a leaning pose. – The chosen body parts should come extremely close to the lens, almost touching it, with visible skin texture, fabric texture, and realistic wide-angle distortion. Pose and overall body (complex and varied): – Create strong, cool, dynamic poses that match the extreme perspective. – Randomly use different pose types, including: • standing with one leg or one arm reaching toward the camera, • crouching or squatting low to the ground, • sitting on the floor or on objects, • lying on the ground with legs or feet toward the lens, • leaning forward aggressively toward the camera, • twisting the body, crossing legs, or arching the back for more dynamic lines. – Allow complex poses where: • both hands are near the lens forming shapes (peace signs, triangles, frames, pointing toward the viewer), • both feet are toward the lens, • one hand and one foot are both large in the foreground, • the face is close to the lens while hands or feet are also visible in perspective. – Maintain believable anatomy even with extreme foreshortening. Angle and attitude (randomized): – Randomize camera angle and orientation (up, down, side, Dutch tilt) while keeping the composition visually balanced and powerful. – Keep the vibe cool, confident, and fashion/editorial or street style, depending on the original outfit. – Facial expressions can vary (serious, playful, confident, mysterious), but must still look like the same person. Lighting and rendering: – Keep the general time of day and lighting mood similar to the original (night vs day, indoor vs outdoor, soft vs hard light), but you may enhance contrast and color to make the image punchy and dramatic. – Maintain realistic shadows and contact points with the ground or floor. – High-resolution, sharp details with clear skin texture, fabric weave, and material highlights. Variation and randomness: – Each edit should look noticeably different from the original image and from other edits, with different: • camera angles, • pose types, • which body parts are closest to the lens, • orientation (straight, tilted, from above, from below). – Avoid repeating the exact same single-foot-close-up composition; produce a wide variety of dynamic poses and angles. Strict rules: – Do NOT change the person into someone else. – Do NOT change the outfit type; only restyle it through pose, perspective, and small natural movement of clothing. – Do NOT move the scene to a completely different location; always stay in a plausible extension of the original place. – Do NOT add text, logos, watermarks, or graphic design elements. – Do NOT switch to painting, illustration, or anime style; keep it photorealistic. Overall: Transform the original photo into a dramatic, photorealistic, ultra wide-angle shot with an extreme camera angle (including views from directly below or above), where one or more body parts are right next to the lens and look huge, the rest of the body recedes in perspective, and the same person strikes a stylish, complex, powerful pose in a consistent, expanded version of the original environment. Also, below is the prompt for generating the original image. Please use it as a reference. [Prompt for original image] #nanobanana2
0:20

一番最後の[Prompt for original image]の部分に画像生成に使用したPromptを入れると一貫性が増します。不要な場合は3行削ってしまっても大丈夫です。 --- Extreme wide-angle perspective and dynamic pose remix edit. This is an EDIT of the original image, not a new character. Use the original image as a strict reference for: – the person’s identity, hairstyle, and overall fashion style, – the general type of background and location (same street, same room, same beach, same kind of architecture, etc.). You are allowed to completely change the camera position, angle, and pose, but you must keep the scene in the SAME location and keep the SAME person and outfit design. Camera and perspective: – Use an ultra wide-angle or fisheye feeling lens (around 12–18mm full-frame look). – The camera angle MUST change significantly from the original: use dramatic angles such as • worm’s-eye view from directly below looking up, • bird’s-eye view from directly above looking down, • very low angle from the ground, • high angle from above, • tilted Dutch angles. – Always create strong foreshortening: body parts close to the lens look huge, while the rest of the body falls away in perspective. – The final result must look like a bold fashion or street photo, fully photorealistic, not illustration or anime. Background consistency: – Keep the same location as the original image: same street, same bridge, same room, same studio, same beach, same general structures and materials. – Do NOT replace the background with a completely different place. – Because the camera angle changes, it is allowed and expected that different parts of the environment become visible. – When new areas appear, extend the original environment logically (same buildings, fences, road markings, walls, colors, materials, lighting style), as if the camera moved within the same place. Body parts near the lens (1–2 parts, sometimes 3): – In each edit, choose ONE or TWO main body parts to be extremely close to the lens (sometimes even THREE in more complex poses). – Vary them from image to image, do NOT always use the same body part. – Allowed near-the-lens parts include: • one or both hands / fingers reaching toward the camera, • one or both feet / shoes / boots near the lens, • knees or thighs, • face very close to the lens, • shoulders or chest close to the lens in a leaning pose. – The chosen body parts should come extremely close to the lens, almost touching it, with visible skin texture, fabric texture, and realistic wide-angle distortion. Pose and overall body (complex and varied): – Create strong, cool, dynamic poses that match the extreme perspective. – Randomly use different pose types, including: • standing with one leg or one arm reaching toward the camera, • crouching or squatting low to the ground, • sitting on the floor or on objects, • lying on the ground with legs or feet toward the lens, • leaning forward aggressively toward the camera, • twisting the body, crossing legs, or arching the back for more dynamic lines. – Allow complex poses where: • both hands are near the lens forming shapes (peace signs, triangles, frames, pointing toward the viewer), • both feet are toward the lens, • one hand and one foot are both large in the foreground, • the face is close to the lens while hands or feet are also visible in perspective. – Maintain believable anatomy even with extreme foreshortening. Angle and attitude (randomized): – Randomize camera angle and orientation (up, down, side, Dutch tilt) while keeping the composition visually balanced and powerful. – Keep the vibe cool, confident, and fashion/editorial or street style, depending on the original outfit. – Facial expressions can vary (serious, playful, confident, mysterious), but must still look like the same person. Lighting and rendering: – Keep the general time of day and lighting mood similar to the original (night vs day, indoor vs outdoor, soft vs hard light), but you may enhance contrast and color to make the image punchy and dramatic. – Maintain realistic shadows and contact points with the ground or floor. – High-resolution, sharp details with clear skin texture, fabric weave, and material highlights. Variation and randomness: – Each edit should look noticeably different from the original image and from other edits, with different: • camera angles, • pose types, • which body parts are closest to the lens, • orientation (straight, tilted, from above, from below). – Avoid repeating the exact same single-foot-close-up composition; produce a wide variety of dynamic poses and angles. Strict rules: – Do NOT change the person into someone else. – Do NOT change the outfit type; only restyle it through pose, perspective, and small natural movement of clothing. – Do NOT move the scene to a completely different location; always stay in a plausible extension of the original place. – Do NOT add text, logos, watermarks, or graphic design elements. – Do NOT switch to painting, illustration, or anime style; keep it photorealistic. Overall: Transform the original photo into a dramatic, photorealistic, ultra wide-angle shot with an extreme camera angle (including views from directly below or above), where one or more body parts are right next to the lens and look huge, the rest of the body recedes in perspective, and the same person strikes a stylish, complex, powerful pose in a consistent, expanded version of the original environment. Also, below is the prompt for generating the original image. Please use it as a reference. [Prompt for original image] #nanobanana2

AI Girl's Photo Studio

20,684 Aufrufe • vor 9 Monaten

FULL PROMPT Consistent Character (use in every scene for continuity) A stylish woman in her late 20s, warm brown skin, glam makeup with soft glossy lips and defined lashes, wearing an elaborate teal-and-gold aso-oke gele (Nigerian head-tie), matching teal lace/aso-ebi gown with intricate gold embroidery, gold jewelry (layered necklaces, drop earrings, bangles), and metallic heels. Confident, elegant, camera-aware demeanor. Cinematic, hyperrealistic, shot-on-iPhone aesthetic, vertical 9:16, soft natural lighting, shallow depth of field, warm color grade. Scene 1 — Mirror Selfie in Living Room Full-length mirror selfie in a bright, luxury living room: marble floors, floor-to-ceiling gold-trimmed curtains, crystal chandelier overhead, cream sofas, gold side tables, a lit fireplace and wall-mounted TV in the background. She holds up a phone in a black case with visible triple-camera module, angled to capture her full outfit and a small teal-and-gold clutch bag. Static shot, soft daylight through the windows. Scene 2 — Driving Away From Home Interior of a luxury SUV (cream leather interior, panoramic sunroof). She’s in the driver’s seat in profile, smiling, one hand on the steering wheel, the other adjusting it, palm trees and a gated estate visible through the window. Camera positioned from the passenger side, slight handheld sway, bright midday light. Scene 3 — Exiting the Car at a Church/Estate Wide exterior shot of a parked white luxury SUV in front of a modern glass-and-stone house. Door open, her leg and heeled foot stepping out, gele visible through the windshield. Static tripod-style shot, hard sunlight, clean concrete driveway. Scene 4 — Emotional Moment in Church Pew Close-up, shallow depth of field: she stands with eyes closed, brows furrowed in an emotional, prayerful expression, hands clasped at chest. Blurred congregation and a stained-glass-lit sanctuary behind her, a balcony choir visible in soft focus above. Slow subtle push-in. Scene 5 — Praise and Worship, Arms Raised Medium shot inside a packed church sanctuary, wooden pews, ceiling fans, arched windows. She stands center-aisle with both hands raised, joyful expression, surrounded by a diverse congregation in coordinated aso-ebi (gold, purple, blue) clapping and worshipping. Handheld documentary-style camera movement. Scene 6 — Dancing in the Aisle Similar sanctuary setting, now mid-movement: she dances with arms bent and swaying, other women in teal and cream lace beside her, congregation clapping in rhythm. Slight low-angle handheld shot, warm indoor lighting mixed with window daylight. Scene 7 — Greeting Guests Outside a Stone Church Exterior of a Gothic-style stone church with arched doorways and stained glass. She’s mid-handshake/greeting with an older woman in cream lace, smiling broadly, surrounded by other churchgoers in pastel and jewel-toned aso-ebi. Bright sunny day, medium wide shot, natural crowd movement in background. Scene 8 — Walking Away Through a Parking Lot Shot from behind as she walks away across a parking lot full of SUVs (including a white Range Rover), showing the full back detail of her gown and gele, tree line and a brick building in the background. Slow tracking shot following her at a few paces back, bright afternoon sun casting a hard shadow. • Aspect ratio: 9:16 vertical, ~1080×1864 •Frame rate: 30fps, total runtime ~25 seconds across 8 cuts (~3 sec each) •Consistent grading: warm, slightly desaturated highlights, punchy golds/teals •Motion: mix of static/tripod shots (mirror selfie, car exit) and handheld documentary movement (church scenes) for realism •Continuity: same face, same outfit, same gele across all 8 clips
0:24

FULL PROMPT Consistent Character (use in every scene for continuity) A stylish woman in her late 20s, warm brown skin, glam makeup with soft glossy lips and defined lashes, wearing an elaborate teal-and-gold aso-oke gele (Nigerian head-tie), matching teal lace/aso-ebi gown with intricate gold embroidery, gold jewelry (layered necklaces, drop earrings, bangles), and metallic heels. Confident, elegant, camera-aware demeanor. Cinematic, hyperrealistic, shot-on-iPhone aesthetic, vertical 9:16, soft natural lighting, shallow depth of field, warm color grade. Scene 1 — Mirror Selfie in Living Room Full-length mirror selfie in a bright, luxury living room: marble floors, floor-to-ceiling gold-trimmed curtains, crystal chandelier overhead, cream sofas, gold side tables, a lit fireplace and wall-mounted TV in the background. She holds up a phone in a black case with visible triple-camera module, angled to capture her full outfit and a small teal-and-gold clutch bag. Static shot, soft daylight through the windows. Scene 2 — Driving Away From Home Interior of a luxury SUV (cream leather interior, panoramic sunroof). She’s in the driver’s seat in profile, smiling, one hand on the steering wheel, the other adjusting it, palm trees and a gated estate visible through the window. Camera positioned from the passenger side, slight handheld sway, bright midday light. Scene 3 — Exiting the Car at a Church/Estate Wide exterior shot of a parked white luxury SUV in front of a modern glass-and-stone house. Door open, her leg and heeled foot stepping out, gele visible through the windshield. Static tripod-style shot, hard sunlight, clean concrete driveway. Scene 4 — Emotional Moment in Church Pew Close-up, shallow depth of field: she stands with eyes closed, brows furrowed in an emotional, prayerful expression, hands clasped at chest. Blurred congregation and a stained-glass-lit sanctuary behind her, a balcony choir visible in soft focus above. Slow subtle push-in. Scene 5 — Praise and Worship, Arms Raised Medium shot inside a packed church sanctuary, wooden pews, ceiling fans, arched windows. She stands center-aisle with both hands raised, joyful expression, surrounded by a diverse congregation in coordinated aso-ebi (gold, purple, blue) clapping and worshipping. Handheld documentary-style camera movement. Scene 6 — Dancing in the Aisle Similar sanctuary setting, now mid-movement: she dances with arms bent and swaying, other women in teal and cream lace beside her, congregation clapping in rhythm. Slight low-angle handheld shot, warm indoor lighting mixed with window daylight. Scene 7 — Greeting Guests Outside a Stone Church Exterior of a Gothic-style stone church with arched doorways and stained glass. She’s mid-handshake/greeting with an older woman in cream lace, smiling broadly, surrounded by other churchgoers in pastel and jewel-toned aso-ebi. Bright sunny day, medium wide shot, natural crowd movement in background. Scene 8 — Walking Away Through a Parking Lot Shot from behind as she walks away across a parking lot full of SUVs (including a white Range Rover), showing the full back detail of her gown and gele, tree line and a brick building in the background. Slow tracking shot following her at a few paces back, bright afternoon sun casting a hard shadow. • Aspect ratio: 9:16 vertical, ~1080×1864 •Frame rate: 30fps, total runtime ~25 seconds across 8 cuts (~3 sec each) •Consistent grading: warm, slightly desaturated highlights, punchy golds/teals •Motion: mix of static/tripod shots (mirror selfie, car exit) and handheld documentary movement (church scenes) for realism •Continuity: same face, same outfit, same gele across all 8 clips

Stephanie Iniidara

11,683 Aufrufe • vor 1 Monat