Loading video...

Video Failed to Load

Go Home

🚨PromptShare🚨 Cool JSON prompt with VEO 3.1 made in Leonardo.Ai { "shot": { "composition": "locked rear chase cam millimeters above cockroach body with massive floor parallax", "lens": "macro ultra-wide insect lens", "camera_movement": "ground-hugging sprint, sudden direction snaps, ultra-low door dive" }, "subject": { "description": "realistic cockroach sprinting at full...

25,174 views • 8 months ago •via X (Twitter)

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Crafted with Seedance 2.0 + GPT Image 2 Pollo AI Storyboard Prompt: Create a raw kung fu performance storyboard focused on extreme physical action. Use reference image for the character. 16:9 storyboard sheet, 12 cinematic panels. The actual storyboard drawings must be black and white only: rough pencil lines, minimal detail, fast gesture drawing energy, simple anatomy construction and strong silhouette readability. Keep the artwork lightweight, dynamic and unfinished like early fight choreography previs. Start directly in action. Do not begin with a calm stance, preparation shot or slow introduction. A solitary female performer executes an aggressive Tibetan kung fu master-style routine inside a vast ancient temple. The choreography is exaggerated, explosive and constantly escalating: flying diagonal kicks, monk-style low stances, rapid palm strikes, spinning cloth-like body turns, animal-form hand shapes, deep lunges, aerial twists, floor-level sweeps, sudden drops, claw-like blocks, back-arched jumps, sliding recoveries and violent sculptural impact poses. Every panel must contain visible motion and strong body momentum. Avoid static standing poses. The performer should feel like a ritual warrior moving with discipline, fury, spiritual pressure and total body control. Action progression: 1. begin mid-air with a flying diagonal kick already in motion 2. handheld close-up palm sweep cutting through air 3. orbiting wide shot of a full-body spin 4. low-angle impact palm strike with shockwave 5. long-lens side profile spinning kick 6. top-down aerial turn with body, hair and fabric flaring outward 7. hard floor stomp cracking the temple stone 8. sliding low sweep across the floor 9. aggressive close-up flurry of elbows, palms and backfist strikes 10. extreme low monk-style beast stance with energy rising 11. spinning elemental vortex around the body 12. final airborne action pose, suspended above the temple floor, body twisted in a powerful kung fu strike, all elements converging around her before impact Add selective elemental energy effects as VFX-style storyboard accents. The effects should feel spiritual, ritualistic and cinematic, not superhero-like: air bursts around spins and flying kicks, dust and stone fragments lifting from stomps, water-like floor ripples during slides, fire-like trails around explosive strikes, heat distortion around high-intensity movement, elemental vortex near the climax. Element progression: early panels: subtle wind, dust and pressure lines middle panels: stronger stone fragments, floor ripples and air shockwaves late panels: controlled fire trails and energy spirals final panel: the strongest combined elemental surge while the performer is still airborne Use cinematic arthouse action camerawork: handheld energy, whip-pan feeling, orbiting camera moves, overhead shots, side silhouettes, aggressive close-ups, long-lens compression, extreme low angles, wide negative space, strong parallax. Keep the temple environment minimal and atmospheric: towering stone columns, worn temple floor, drifting incense smoke, hanging fabric, harsh light shafts, faint dust in the air, subtle wet floor reflections. Do not overcrowd the frames. Annotation color system: red arrows = body movement blue arrows = camera movement green marks = framing / composition notes orange marks = lighting direction yellow marks = elemental VFX / energy effects black text = short lens notes and panel labels No timestamps. No dialogue. No singing. No extra characters. No enemies. No logos. No watermark. Seedance video prompt: Video Prompt Seedance 2.0 Create a 15-second cinematic kung fu performance video. Use Image1 as the fixed character sheet reference. The character must strictly match the character sheet. Use Image2 ] as the storyboard reference. Follow the storyboard shot by shot as the main source for action order, camera rhythm, body movement, framing, movement direction, camera angles and visual progression. Treat each storyboard panel as a sequential keyframe. Preserve the shot order and make the video feel like the storyboard has been translated into continuous live-action motion. The sequence must end on a frozen final frame while the performer is still airborne. Do not add text, captions, storyboard labels, arrows, UI, logos or watermarks. Do not treat the storyboard as a single image. Do not redesign the character, change the costume or alter the face. Do not begin with a calm stance, preparation pose or slow introduction. Do not make the elemental effects look like superhero powers or excessive fantasy glow. Visual style: stylized cinematic realism, high-end 3D painterly animation quality, dynamic cloth simulation, expressive silhouette design, rich cinematic lighting, controlled color palette, natural motion blur, dramatic scale, beautiful but aggressive physicality, premium feature-animation aesthetic. Environment: vast ancient temple, towering stone columns, worn temple floor, drifting incense smoke, hanging fabric, harsh light shafts, faint dust in the air, subtle wet floor reflections, high contrast shadows. The performance is a solitary female kung fu routine inside a vast ancient temple. The routine starts immediately in action, with no calm stance, no preparation pose and no slow introduction. The movement should feel aggressive, ritualistic, disciplined, physically extreme and spiritually charged. This is not a fight against an enemy. It is a solo performance of force, control, exhaustion, fury and release. Follow story board for choreography direction. Element progression: early sequence: subtle wind, dust and pressure lines responding to movement. middle sequence: stronger air shockwaves, stone fragments, floor cracks and water-like ripples across the temple floor. late sequence: controlled fire trails, heat distortion and energy spirals around explosive strikes and kicks. climax: wind, dust, stone, water ripple and fire accents combine into a stronger elemental vortex. final beat: the performer is airborne above the temple floor in a powerful kung fu strike, body twisted mid-air, hair and fabric flaring outward, with all elements converging around her before impact. Elemental VFX must feel spiritual, ritualistic and cinematic. The effects should be integrated with the choreography and motivated by physical movement. Keep the energy raw, elemental, atmospheric and grounded in the temple environment. Use Laban movement logic throughout: weight: strong, heavy, grounded during impacts, with brief lightness during jumps and aerial twists time: quick during strikes, kicks, drops and turns, sustained during suspended holds and recovery transitions space: direct during attacks, blocks and lunges, indirect during spinning turns and elemental vortex moments flow: bound during rooted stances and precise strikes, free during aerial motion, spinning fabric movement and elemental releaseSee less

Ciri

77,861 views • 1 month ago

Seedance 2.0 on Higgsfield AI just raised the bar. The quality, motion, and creative control are on another level. Full open-source prompts & assets below. SCENE CONTEXT A young man carries the sleeping woman into her pink bedroom, lays her down on the bed, covers her with the blanket and switches off the lamp, then sits on the floor at the foot of the bed, rests his head on the mattress edge, and falls asleep there, keeping a respectful distance. ACTIVE REFERENCES >>: young man, messy light-brown hair, white t-shirt, carrying then floor-sitting posture, tender careful movement. 100% matches the reference. >>: sleeping young woman, low pigtails, pink hair-roller clip, beige t-shirt with brown long sleeves, pink plaid pajama bottoms, eyes closed, carried then lying tucked in bed. 100% matches the reference. >>: pink bedroom. 100% matches the reference. Every element and corner is preserved and stays consistent across all shots. LOCATION MAP Pink bedroom, remembered corner by corner from >> and held identical in every shot: - Wooden door with brass knob and dark wood trim / wardrobe on one side wall. - A large ornate pink-and-white Victorian dollhouse standing on the floor against the wall. - A wide window with sheer white curtains, cool outside light filtering through. - A vanity desk with an upright mirror and a pink desk chair beside the window, a leafy potted plant next to it. - A tall warm floor lamp — the main practical light — near the bed, wall-mounted shelves with small items above it, wood wainscoting along the lower wall. - An ornate white bed frame with pink ruffled bedding and a soft pink pillow, the central anchor of the room. - A woven area rug on a wooden floor, light soft clutter (tissue boxes, papers) scattered naturally. Open floor between the door and the bed is his carrying path; clear floor space at the foot of the bed is where he sits. FIRST FRAME AND SPATIAL BLOCKING The first visible frame matches the attached carry reference exactly: he stands mid-room holding her in a bridal carry, her head resting against his chest and shoulder, eyes closed, pink plaid fabric bundled across his forearms, the white ornate bed and pink bedding soft behind, sheer-curtained window and dollhouse readable in the background. No empty establishing frame. FORMAT MODE Controlled four-shot sequence with HARD CUTs at 3.5s, 7.5s, and 11.0s. Real-time motion, gentle handheld for the carry only. No subtitles, no music. OPTICS Shot 1 (carry): 50° diagonal field of view, standard normal lens character, camera 1.5 to 2 meters, clean medium two-shot holding both faces. Shot 2 (lay down): 56° diagonal field of view, near-normal lens character, camera low at the head of the bed looking down along her body, 1 to 1.3 meters, shallow depth on her settling face. Shot 3 (blanket + lamp): 63° diagonal field of view, slightly-wide lens character, camera 2 meters back at a bedside three-quarter angle, wide enough to hold him, the tucked bed, and the floor lamp in frame. Shot 4 (floor sleep): 63° diagonal field of view, slightly-wide lens character, camera low at the foot of the bed, then a slow crane-up to a high three-quarter looking down the length of the bed. CAMERA Shot 1: gentle handheld follow, slow dolly-in with him toward the bed, subtle vertical bob and weight-shift pulse matching the carry, human motion not digital jitter. Shot 2: separate angle from the head of the bed; slow push-in as he lowers her, settling as her head meets the pillow. Shot 3: static-leaning three-quarter as he draws the blanket up and tucks it, then reaches and clicks off the floor lamp; frame holds through the drop into moody low light, her tucked body still framed. Shot 4: low static at the foot of the bed as he sinks to the floor and lowers his head to the mattress edge, then a smooth crane-up to a high three-quarter — her tucked on the bed, him asleep on the floor below. ACTION TIMING 0.0s to 3.5s: he carries her in a bridal hold, walking slowly toward the bed, her head lolling gently against his chest, pigtail swaying with each step. 3.5s HARD CUT. 3.5s to 7.5s: from the head-of-bed angle he lowers her onto the mattress, her shoulders and head settling into the pillow, hair fanning out, body coming to rest. 7.5s HARD CUT. 7.5s to 11.0s: he draws the pink blanket up over her and tucks the edge along her shoulder with both hands, then reaches to the floor lamp and switches it off; the warm glow dies and the room falls to cool moody window light — she lies exactly as he left her, tucked and unmoved. 11.0s HARD CUT. 11.0s to 15.0s: in the dim room he lowers himself to sit on the floor at the foot of the bed, rests his head sideways on the mattress edge near her feet, settles, breathing slows, and he closes his eyes and falls asleep there — not on the bed, a clear respectful distance kept. PHYSICS Her body carries real dead-weight during the carry — limbs sag, head lolls, pigtail swings freely. As he lowers her, pillow and mattress compress under her head and shoulders, hair sliding and resettling; the pink blanket drapes and folds naturally as it is pulled up and tucked. His footsteps are grounded heel-to-toe with real weight transfer. As he sinks to the floor his weight settles, one arm resting on the mattress, head lowering onto the edge which dips slightly; his eyelids close with a soft final settle. LIGHTING Cinematic low-key interior, moody and restrained, never bright or flat. Primary motivation: the warm floor lamp and a low bedside practical, casting soft warm pools with gentle falloff into deep but detailed shadow, cool bluish light from the sheer-curtained window balancing the warmth for filmic warm-cool contrast. Naturalistic film texture, soft grain, gentle highlight rolloff, faces modeled and readable within the low light, not lit up. Shots 1–3 carry the warm lamp motivation. At the lamp switch (shot 3) the room drops to cool low-key window moonlight — atmospheric, shadows deep, her tucked form and his movement still clearly readable, never a crushed black frame. Shot 4 stays in this cool moody light, his sitting, head-lowering, and closing eyes visible, the bed and floor softly modeled by the window. AUDIO Shot 1: soft footsteps, faint effort breath under her weight, a quiet sleepy sigh from her. Shot 2: soft mattress and pillow settle as she comes to rest. Shot 3: gentle blanket rustle as he tucks her in, a quiet lamp-switch click, room tone shifting. Shot 4: a soft floor settle and faint cloth rustle as he sits and lowers his head, then quiet steady breathing from both. No dialogue, no music, no subtitles. POSITIVE LOCKS First frame matches the attached carry reference exactly. Man matches >> exactly, woman matches >> exactly. The bedroom matches >> exactly and every listed corner — door and wood trim, ornate dollhouse, sheer-curtained window, vanity with mirror and pink chair, floor lamp, shelves, ornate white bed with pink ruffled bedding, woven rug — stays present and consistent across all four shots, with no new or missing furniture. Carrying and laying her down are two separate shots with different angles. Lighting stays cinematic and dim, motivated by the practical lamps, never bright or flat. When the lamp is switched off she remains tucked in the exact pose he left her, unmoved. He does not lie on the bed: he sleeps sitting on the floor at the foot of the bed with his head on the mattress edge, a clear respectful gap kept.

𝗦𝗮𝗻𝗶𝗮

51,899 views • 2 months ago

This looks so neat and clean Created by using GPT Image 2 + Seedance 2.0 on TapNow Prompt Ultra-luxury cinematic fashion construction film. STRICTLY follow all 12 storyboard panels sequentially without skipping, merging, shortening, reordering, or improvising any panel. Every shot must transition smoothly into the next in exact numerical order from Panel 1 through Panel 12. Total runtime exactly 155 seconds. Maintain absolute continuity in lighting, material behavior, camera language, scale progression, and object identity throughout the entire film. Only ONE shoe exists during the entire video — never show a pair under any circumstance. Visual format: 65mm IMAX film aesthetic, macro-capable Panavision anamorphic lens, ultra-sharp macro detail, shallow cinematic depth of field, fine editorial film grain throughout, subtle horizontal anamorphic lens flares ONLY from thread highlights and suede edge speculars. Infinity cyclorama studio environment with seamless pale grey-to-white gradient background where the floor curves upward into the wall with no visible horizon line. Warm-neutral soft key light from above camera-left creating one consistent clean shadow falling back-right in every shot. Lighting inspired by Loewe / Hermès luxury editorial campaigns — soft but directional, warm and premium, never harsh, never blue, never high contrast, never crushed blacks. Stable cinematography only. No jitter, no AI morphing, no flicker, no ghosting. The entire narrative is a meditative material-transformation journey where a single deep crimson liquid droplet gradually evolves into a handcrafted suede slingback heel through couture construction and hidden comfort engineering. Every material interaction obeys realistic physics. Diegetic sound only — no music, no score. PANEL 1 — THE VOID (00:00–00:10) Wide locked-off cinematic shot of an empty infinity cyclorama studio with pale grey-to-white seamless gradient background. Atmospheric dust floating slowly in warm studio light. Exposure breathing subtly. Silence and soft room tone dominate. After several seconds, one tiny deep crimson droplet slowly falls into frame from above in near weightless slow motion, rotating slightly while catching warm highlights. The droplet lands center frame on the polished cyclorama floor with realistic liquid surface tension physics. It briefly holds spherical form before gently flattening outward. One soft shadow falls back-right. Sound: low room tone, elegant bell-like tick on impact, delicate reverb decay. PANEL 2 — SURFACE TENSION (00:10–00:22) Cut to macro floor-level close-up. Camera slowly orbits around the flattened crimson liquid pool. Surface tension creates organic rounded edges and subtle thickness variation. Warm key light reflects softly like satin lacquer. Tiny ripples propagate outward and gradually settle. Floating dust visible in the beam of light. The liquid slowly begins thickening microscopically as if memory is forming beneath the surface. Edges transition from glossy wetness toward velvety softness. Sound: soft viscous liquid movement, faint atmospheric resonance. PANEL 3 — THE FIRST FIBERS (00:22–00:36) Extreme macro push-in across the crimson surface. Thousands of microscopic suede nap fibers begin extruding upward organically in rhythmic waves. Individual fibers catch warm highlights differently depending on density and angle. The transformation moves naturally across the surface like wind through grass. Matte suede texture gradually replaces liquid gloss entirely. Camera glides slowly across the newly forming velvet landscape. Sound: microscopic fiber rustling, delicate textile friction. PANEL 4 — MATERIAL MEMORY (00:36–00:50) Macro tracking shot across fully formed crimson suede terrain. Every velvet strand visible in extreme detail. Invisible pressure waves beneath the suede subtly shift the nap direction, creating tonal changes across the material surface. Warm light rolls gently over the velvet texture. The material gradually lifts upward from the floor, beginning to imply the sculptural shape of a pointed shoe toe. Sound: soft velvet brushing, low warm resonance. PANEL 5 — THE THREAD ARRIVES (00:50–01:06) Extreme-extreme macro couture construction sequence. One single crimson thread enters frame illuminated by warm directional light. FPV-style camera flies beside the advancing thread as it stitches into the suede surface. Thread fibers visibly twist under tension. The thread enters the suede, disappears beneath the surface, emerges again at the next stitch peak, pulls taut, and repeats rhythmically. Camera passes over every stitch mountain in sequence. Each stitch slightly reshapes surrounding suede. Sound: couture stitching ticks, thread tension tightening, soft textile compression. PANEL 6 — CONSTRUCTION OF FORM (01:06–01:20) Transition from macro to medium scale. Behind the advancing stitch line, the shoe body begins solidifying into recognizable structure. Pointed toe box forms first, then elegant sidewalls rise upward with sculptural precision. The slingback silhouette slowly emerges from previously flat suede terrain. Camera performs a slow floating cinematic arc around the forming structure. Matte crimson suede texture remains perfectly consistent. Sound: restrained structural textile movement, distant stitching continuation. PANEL 7 — THE INTERIOR (01:20–01:34) Macro cutaway revealing the inside of the forming shoe. Cream-colored lambskin lining flows organically into place beneath the crimson suede shell. The lining smooths itself naturally against elegant internal curves. Strong visual contrast between warm cream lambskin and deep crimson suede under soft editorial lighting. Materials appear tactile and luxurious. Sound: soft leather settling, delicate tactile friction. PANEL 8 — ENGINEERED COMFORT (01:34–01:48) Macro cross-sectional engineering sequence. Internal comfort layers assemble one by one with realistic material physics. Dense foam base layer forms first with subtle porous texture. Softer memory foam settles gently above and compresses naturally under its own weight. Cream lambskin velvet seals the upper layer. The completed cushion compresses once slowly and rebounds naturally, demonstrating softness and resilience. Camera glides across microscopic velvet interior texture. Sound: soft pneumatic settling, muted resonance, cushion compression. PANEL 9 — THE HEEL SCULPTURE (01:48–02:02) Macro cinematic focus on the kitten heel gradually forming from the same crimson suede structure beneath the shoe body. Elegant curvature emerges slowly and becomes refined and balanced. Camera tracks upward along the heel contour toward the slingback strap. Warm highlights skim softly across suede edges. Sound: low structural resonance, faint textile shaping. PANEL 10 — FINAL REFINEMENT (02:02–02:18) Medium macro editorial beauty detailing. Camera slowly explores completed craftsmanship: stitch consistency, velvet nap direction, edge finishing, cream lambskin softness, seamless slingback geometry. Tiny dust particles drift through warm studio light. The shoe settles microscopically as if materials are naturally relaxing into final form. Sound: quiet room tone, soft textile creaks, near silence. PANEL 11 — HERO EMERGENCE (02:18–02:32) Slow cinematic pullback from macro detail into full product reveal. The fully completed deep crimson suede slingback heel stands alone centered on the infinity cyclorama floor. Same warm-neutral key light from above camera-left and same single clean shadow falling back-right for continuity with Panel 1. Camera movement extremely slow and controlled. Every material reads clearly: deep crimson suede upper, cream lambskin interior, sculpted kitten heel, elegant slingback strap. Sound: deep low resonant tone gradually fading into room tone. PANEL 12 — THE FINAL HOLD (02:32–02:35) Locked-off front three-quarter hero composition. The single crimson suede slingback heel remains perfectly still at center frame on the seamless infinity cyclorama. Velvet nap subtly catches warm light with natural tonal variation. Silence gradually overtakes the room tone. Hold on pure luxury restraint. No text. No logo. No end card. Global Constraints: Only ONE shoe visible at all times. Never show a pair. No hardware, buckles, laces, or metallic elements. No logos, subtitles, typography, branding, or watermarks. No lighting changes between shots. Maintain consistent deep crimson suede color. Preserve ultra-sharp macro clarity and stable cinematography. No morphing artifacts, no flicker, no surreal deformation. Realistic liquid surface tension. Realistic suede microfiber extrusion. Visible thread twist and accurate stitch tension. Natural foam compression and rebound physics. Consistent matte velvet nap behavior. Diegetic sound only — liquid, textile, stitching, room resonance. No music. No soundtrack.

Aaliya

33,420 views • 4 months ago

this model is so f*cking good for animations less hallucinations than gemini and it takes like 20 seconds to generate full clip + 1 min video costs only like ~$7 prompt that i used: Create a 15-second cinematic 3D animated product advertisement for supportive shoe insoles. Use a polished, high-end stylized 3D animation aesthetic with expressive but natural characters, soft cinematic lighting, realistic materials, believable anatomy, and subtle facial expressions. The scene takes place in a modern apartment hallway in the early morning. Warm sunlight enters through a large window, creating soft golden reflections on the wooden floor. A few pairs of shoes are scattered near the entrance, with a small bench and coat rack in the background. A completely different male character appears: a slim-to-average build man in his early 30s with short slightly messy brown hair, light stubble, casual gray hoodie, dark joggers, and white sneakers. He should look like an ordinary everyday person, not a fitness model. Preserve his face, hairstyle, clothing, body proportions, and overall appearance consistently throughout the entire animation. The advertisement should feel like a natural short-form social media ad, with the character speaking directly and casually rather than acting like a professional commercial presenter. [0–3 seconds] Begin with a medium-wide cinematic shot. The man walks into the apartment after spending several hours on his feet. He takes two steps, suddenly slows down, and looks uncomfortable. He takes off one sneaker and sits on the bench, rubbing the bottom of his foot with a slightly frustrated expression. He looks toward the camera and says naturally: "Man, my feet used to kill me after a long day." His delivery should feel conversational and believable, with natural lip movement and subtle facial animation. [3–7 seconds] Cut to a closer shot as he picks up the original factory insole from inside his sneaker and looks at it skeptically. He says: "Then I realized it wasn't even my shoes." He pulls the old insole out and places it beside the shoe. The camera gently pushes closer as he reaches for a new supportive shoe insole lying on the bench. Make the insole clearly visible and easy to understand as the hero product, with realistic cushioning, ergonomic shape, and premium material details. [7–11 seconds] Show him placing the new insole inside his sneaker. Use a smooth close-up of his hands fitting the insole naturally into the shoe. Show the insole sitting correctly inside the shoe with believable proportions and physical interaction. He puts the sneaker back on, stands up, and takes several comfortable steps across the hallway. His posture immediately looks more relaxed. He smiles slightly and says: "These made such a difference." Keep the acting subtle and realistic. Do not make the effect exaggerated or magical. [11–15 seconds] Move into a slightly closer cinematic shot as he walks confidently toward the apartment door, then turns back toward the camera. He briefly lifts one foot, showing the sneaker, and says with a relaxed smile: "Honestly, I wish I'd tried them sooner." Finish with a clean product-focused composition: the pair of supportive insoles is visible on the bench next to the sneakers while the man walks naturally into the background. Hold the final frame for a moment. Camera: Smooth cinematic dolly movement, subtle handheld-style realism, natural perspective, gentle push-ins, no rapid camera movement, no dramatic orbiting, no abrupt zooms. Lighting: Warm morning sunlight mixed with soft ambient indoor light. Cinematic shadows, realistic reflections, soft highlights on the product, premium commercial look. Audio: Natural male voice dialogue, subtle apartment ambience, quiet footsteps on wooden floor, soft fabric movement, shoe sounds, and minimal understated background music. Voice: Young adult male, friendly, slightly casual, conversational delivery. No exaggerated commercial voiceover. Lip synchronization must be accurate to every spoken word. Product: The shoe insoles must remain physically consistent throughout the scene. They should look like premium supportive orthopedic-style insoles designed for everyday comfort. Show their shape and cushioning clearly without adding logos, text, or branding unless explicitly provided. Maintain: Realistic anatomy, stable facial identity, accurate hands and fingers, correct foot placement, natural walking mechanics, believable shoe deformation, physically accurate interaction between hands, shoes, and insoles, consistent lighting, consistent character proportions, and smooth temporal continuity. Avoid: Extra characters, unrelated locations, duplicated limbs, distorted hands, floating objects, sliding feet, broken anatomy, sudden costume changes, exaggerated reactions, magical transformations, unrealistic product effects, subtitles, captions, text, logos, watermarks, or cuts to unrelated scenes.

MAX

21,356 views • 22 days ago

Seedance 2.0 on Higgsfield AI Full open-sourced prompts & assets below: SCENE CONTEXT A young woman sleeps on her side in her pink bedroom at night; in a single locked frame the room snaps instantly from night to morning like a finger-snap time jump. She sleepily half-wakes, turns over to find a white cat curled against her back, then pushes up to half-sitting and sees her room quietly tidied — her school uniform hung on the chair and her backpack packed on the vanity. ACTIVE REFERENCES >>: young woman, low pigtails, pink hair-roller clip, beige t-shirt with brown long sleeves, sleeping then waking. 100% matches the reference. >>: fluffy white long-haired cat, adult, curled and pressed against her back. 100% matches the reference. >>: pink bedroom. 100% matches the reference. Every element and corner is preserved and stays consistent across all shots. >>: school uniform — navy cardigan, white shirt, green-striped tie, plaid skirt, knee socks — draped and hung on the pink chair. 100% matches the reference. >>: solid pink backpack with front zip pocket and pink pompom keychain, packed and zipped, standing on the vanity table. 100% matches the reference. LOCATION MAP Pink bedroom, remembered corner by corner and held identical in every shot: - Screen-left: a wooden door with a brass knob, dark wood trim and wood wainscoting along the lower wall, blush-pink upper walls. - Beside the door: a large ornate pink-and-white Victorian dollhouse with a small pink chair at its base. - A white vanity desk with a trifold arched mirror, cluttered with cosmetics, brushes and small bottles, a pink desk chair tucked at it. - A wide window with sheer white curtains behind the vanity; a leafy potted plant beside it. - A tall brass floor lamp standing near the bed. - A wooden nightstand at the head of the bed with a small lamp, a framed photo, a tissue box and a cup. - The bed against the wall: carved wooden headboard, pink ruffled bedding, pink pillows, a soft pink blanket — the central anchor of the room. - A woven area rug over dark hardwood floor, a small wall shelf with items above the bed side. FIRST FRAME AND SPATIAL BLOCKING The first visible frame is a close-up of her sleeping face. She lies on her left side facing the bedside lamp / nightstand side, cheek on the pink pillow, hair loose, pink hair-roller clip visible, breathing slow. The bed's pink blanket is clean and clear. No empty establishing frame. FORMAT MODE Controlled four-shot sequence with HARD CUTs at 4.0s, 8.0s and 11.5s. The night-to-morning transition inside shot 1 is an instantaneous in-frame light change, not a cut. Real-time motion. No subtitles, no music. OPTICS Shot 1: 50° diagonal field of view, standard normal lens character, camera 0.6 to 0.8 meters from her face, shallow depth of field — closed eyelids, lashes, loose strands and the hair-roller clip razor-sharp, the room soft behind. Shot 2: 56° diagonal field of view, near-normal lens character, camera 1 meter, holding her face and the white cat against her back, rack focus available between them. Shot 3: 63° diagonal field of view, slightly-wide lens character, camera 1.5 to 2 meters, rising with her as she sits up, more of the room entering frame. Shot 4: 84° diagonal field of view, classic wide lens character, camera 2 meters, wide enough to reveal the tidied room — vanity, chair and bed together — then easing toward her. CAMERA Shot 1: locked close-up with a very slow creeping push-in; the framing does not change through the night-to-morning snap. Shot 2: small reframe and rack focus as she turns, pulling focus onto the cat curled at her back, then back to her reacting face. Shot 3: a smooth crane-up rising with her from lying to half-sitting, revealing the room behind the bed. Shot 4: a slow pan across the tidied room — uniform on the chair, packed backpack on the vanity — settling with a gentle push-in on her half-sitting figure and dawning expression. ACTION TIMING 0.0s to 2.0s: close on her sleeping face at night, perfectly still, breathing slow, cool dim room around her. 2.0s: an instantaneous in-frame light snap — the room flips from night to morning in a single frame, no cut, no dissolve; she does not move at all, only the light changes, like a finger-snap time jump. 2.0s to 4.0s: hold on her face now in soft warm morning light, still asleep for a beat. 4.0s HARD CUT. 4.0s to 8.0s: she sleepily half-opens her eyes, stirs, and turns over toward screen-right, discovering a fluffy white cat curled warmly against her back; her half-lidded eyes drift to it. 8.0s HARD CUT. 8.0s to 11.5s: she pushes herself up on one arm to half-sitting, hair mussed from sleep, blinking and groggy, beginning to glance around the room. 11.5s HARD CUT. 11.5s to 15.0s: reveal of the quietly tidied room — her navy cardigan and plaid skirt uniform hung neatly on the pink chair at the vanity, the packed pink backpack standing zipped on the vanity table, its pompom keychain still — her expression softening into slow, disbelieving realization as she takes it in. PHYSICS During the night-to-morning snap her body is absolutely motionless — only light changes, no drift, no shift. As she wakes, eyelids lift heavily, she rolls with natural weight and the mattress and blanket shift under her; the cat's long fur rises and falls with slow breathing and compresses softly where it presses to her back. Sitting up, her hair falls loose in individual strands, the blanket sliding down naturally, her supporting arm taking real weight. LIGHTING Cinematic and restrained throughout, never bright or flat. Night (pre-snap): low-key cool moonlight through the sheer curtains with a faint warm practical accent, deep but detailed shadow, moody film texture and soft grain. At the snap, the light flips instantly to soft warm directional morning sun through the sheer curtains — golden but controlled and filmic, gentle rolloff, faces readable, shadows soft, not overexposed or blown out. The warm-cool contrast and naturalistic grain carry the cinematic feel into every shot. AUDIO Shot 1: quiet steady sleeping breath, faint cool room tone; at the snap a soft airy shimmer-whoosh transient marks the time jump, then gentle morning birdsong and warm ambience fade in. Shot 2: a soft sleepy inhale, faint fur rustle as she finds the cat, a quiet purr. Shot 3: soft blanket rustle as she sits up. Shot 4: quiet held breath, faint ambient morning tone under her realization. No dialogue, no music, no subtitles. POSITIVE LOCKS Woman matches >> exactly, cat matches >> exactly, bedroom matches >> exactly and every listed corner — wooden door, dollhouse, vanity with trifold mirror, pink chair, brass floor lamp, wooden nightstand, carved bed with pink ruffled bedding, woven rug — stays present and consistent across all four shots, with no new or missing furniture. The bed's pink blanket is clean and clear — no laptop, bag, papers or objects resting on top of it. The night-to-morning transition is one instantaneous in-frame light change on a single locked framing; she does not move during it — no dissolve, no fade, no camera cut. The white cat lies pressed against her back. In the final shot the uniform hangs on the pink chair matching >> and the packed backpack sits on the vanity matching >>. Lighting stays cinematic and controlled, never bright or washed out.

Noor

14,073 views • 2 months ago

I love that Higgsfield is making its best AI commercial workflows completely open-source. Seedance 2.0 on Higgsfield AI Full open-sourced prompts & assets below. Prompts : Style: 8K IMAX. Photorealistic — no 3D render, no game engine, no game-cutscene aesthetic. Cinematography: Emmanuel Lubezki × Roger Deakins. Lighting: Natural light only — contre-jour backlight, camera on shadow side, atmospheric haze throughout. Key light from sky and windows only. Color: 60:30:10 — dominant / secondary / accent. Camera: Physical cine lens. 180° shutter motion blur. Skin: Pore-level realism — vellus hair, asymmetric moles, capillary flush, pore-shadow matching on-set light. Acting: Hollywood — micro-pauses before reactions, precise eye-line, wet living eyes with catch-lights, visible breath and chest rise. Physics: Gravity and inertia respected — mass has real weight, correct contact shadows. No floating props. Composition: Rule of thirds + golden ratio. Every person moving from frame one. Continuity: Characters, props, environment identical across every cut. No identity drift. Technical: 24fps smooth motion. 8K detail. No jitter. Audio: Environmental SFX only. No music. No subtitles. SUBJECT — >>, character matches input 100%, >> can in right hand. By end fully transformed into >> — armor assembled mid-air in real-time, >> matches input 100%. WB 6500K. MULTISHOT — fast cinematic cutting, escalating energy across the full 15s. LOCATION — >> is a STYLE REFERENCE ONLY, not a fixed keyframe. Use it for the look, mood, architecture and lighting of the environment — a deserted NYC-type avenue in hard midday sun. Seedance should freely generate and extend the world: new buildings, new stretches of avenue, fresh camera angles. The character TRAVELS through space across the shots — he is NOT pinned to the exact spot or framing of the input image. Do not reproduce the reference frame 1:1. ACTION — SHOT 1 (0:00–0:02) — EXTREME CLOSE, chin to forehead. >> raises >> to lips, deep pull. Adam's apple descends then rises twice. Hard cut. SHOT 2 (0:02–0:04) — Same close framing. Can lowers fast. Eyes snap open, sharp and alert (natural skin and iris detail, no glow). Zygomaticus major fires — wide genuine grin builds in under a second, 2mm to 8mm at mouth corners. Sternum rises with a full deep inhale. He is electric. Hard cut. SHOT 3 (0:04–0:06) — WIDE, low. >> EXPLODES forward into a sprint at 30 km/h, continuing in the SAME direction he was already facing — straight ahead down the avenue, NOT turning around. First strides — sneakers slam cracked asphalt, dust puffs eject 10cm. Hard cut. SHOT 4 (0:06–0:08) — Tracking the sprint. Arms drive at 90°, track jacket trails 15cm, grin held, brow raised, jaw relaxed open. Stride extends, ground contacts shorten. Building speed. Hard cut. SHOT 5 (0:08–0:10) — Final two strides, knees compress to 110°. Right foot drives into asphalt — surface fractures 20cm radius. He LAUNCHES upward at 65 km/h. Hard cut. SHOT 6 (0:10–0:13) — Mid-air in the >> building canyon, 24fps FULL SPEED, NO slow-motion. He is NOT frozen — his whole body keeps moving through the jump: torso rotates, legs cycle and tuck, arms swing out and reach, head turns to track the incoming armor. As he flies and twists through the air, armor pieces rip in from the city geometry and converge onto his moving body — chest plate LOCKS mid-rotation, pauldrons CLAMP as his shoulders swing, gauntlets SNAP onto forearms while his arms extend, shin plates clamp onto cycling legs, helmet descends and visor SLAMS shut as his head turns forward — one violent fluid sequence, body in constant motion throughout. Sharp metallic CRACK at visor seal. Hard cut. SHOT 7 (0:13–0:15) — >> SLAMS into >> in a hard crouch, both armored feet hit asphalt simultaneously, dust ring erupts 80cm. He rises, snaps gauntleted fists open and shut — left then right — glances down at the chest plate. Muffled laugh from behind the sealed visor. Hard cut to black. CAMERA — SUPER-DYNAMIC HANDHELD, never static, never locked off. Strong aggressive operator shake on every shot — 4–8cm bounce, organic human jitter, no stabilization. Pronounced DUTCH ANGLE throughout — frame canted 12–20° and shifting between shots, tilting harder as energy builds. SHOT 1: FOV 18° extreme close, hard dutch 15°, violent micro-shake. SHOT 2: FOV 18°, dutch flips to opposite side ~18°, jittery. SHOT 3: FOV 84° low, dutch 12°, whip into the sprint. SHOT 4: FOV 84°, camera physically chasing the run, dutch 16°, heavy stride bounce, motion blur on pans. SHOT 5: FOV 63°, dutch 20°, snap-tilt up tracking the launch. SHOT 6: FOV 63°, AGGRESSIVE HANDHELD CAMERA MOVEMENT — operator arcs and swings around the airborne body, 6–8cm bounce, fast reframes chasing each armor piece as it locks onto his moving form, strong DUTCH ANGLE swinging 18°→8°, no slow-mo. SHOT 7: FOV 63°, hard jolt on landing impact, dutch 14°, camera recoils 8cm then keeps breathing on the suit inspection. STYLE — Dominant: bleached asphalt grey and building canyon 60%. Secondary: navy/cream outfit transitioning to chrome armor 30%. Accent: grin, dust, chrome flash and visor LED blue on landing 10%. WB 6500K. NO glowing eyes — eyes lit by natural sunlight only. CONSTRAINTS — Cut to black at end. 16:9. MULTISHOT with hard cuts per the timecodes above. NO slow-motion anywhere — everything 24fps full speed, especially the transformation. Camera always handheld with strong shake and dutch angle — NEVER static or locked. NO eye glow. >> is a reference for style only — do NOT lock to the input frame or keep him in the same spot; the world extends and he moves through it. Grin must be fully established before the sprint begins.

yopiwhs

11,743 views • 2 months ago

A FULL ANIME FIGHT SCENE GENERATED WITH AI. AND THE PROMPT IS PUBLIC. Higgsfield just open-sourced its Originals: their flagship in-house productions are now fully transparent. For every video you can see: → the full prompt → every reference (image and audio) → the exact generation settings: model, quality, resolution This clip has a creature transformation, two-character fight choreography, slow motion, even pink blood to dodge the gore. All described in a single prompt you can copy, reproduce or remix as is. Full prompt: "Girll with blue hair and guy with black hair enters empty classroom at dusk, red-orange sky bleeding through tall windows, desks and chairs overturned and scattered with loose papers on the floor; the black-bob girl in a white sailor uniform with blue collar sits collapsed against the wall beneath the blackboard, knees drawn up, sweat soaking her bangs, shoulders convulsing in short spasms, one hand pressed to her stomach, breath ragged and wet. Blue-haired girl in a navy school blazer and pleated skirt enters first through the sliding door, kusarigama scythe held low at her side, blade catching the red window-light; black-haired boy in an open-collar white shirt and loosened tie follows a beat behind, war hammer resting on his shoulder, smirk fading as he sees the sick girl. Camera pushes in low and fast toward the collapsed girl, handheld micro-shake, then whip-pans to the two arrivals freezing in the doorway. The sick girl's spine arches unnaturally, a wet tearing sound as her skin splits along the shoulder blades, bone spurs punching outward, extra eyelids blistering open across her collarbone and cheeks — camera holds in a static wide as the transformation escalates, cutting to tight inserts of individual eyes opening one by one along her growing arms, her school uniform shredding as the body doubles then triples in mass, clawed feet cracking the floorboards, her head deforming into a horned, skull-white cranium ringed with curved fangs, one massive central eye where her face used to be, remnants of the blue collar-ribbon still hanging from a warped throat. She rises to full monster height, towering over the desks, guttural roar rattling the windows. Blue-haired girl plants her feet and swings the scythe up into guard as the boy drops the hammer off his shoulder into a two-handed grip; camera does a fast 180-degree orbit around both of them as they charge. Dutch-angle low shot as the boy closes distance first, hammer swinging in a wide horizontal arc into the monster's leg — impact throws him sideways through a row of desks, wood splintering, into the side wall, plaster cracking around his body, hard cut to his grunt and a slow recovery push off the wall. Blue-haired girl vaults over the wreckage, scythe trailing a whip of motion blur, camera speed-ramping into slow motion as the curved blade connects across the monster's forearm — hot pink ichor sprays in thick arcing ribbons instead of red blood, droplets suspended mid-air in the slowed frame, blade sound a wet metallic tear. Monster backhands her mid-recovery, camera whip-pans to follow her body slamming into the blackboard, chalk dust exploding outward, board cracking down the middle. Rapid cross-cutting: low hero-angle on the boy re-entering with a rising hammer strike into the monster's exposed ribcage-like plating, close slow-mo insert on the point of impact as bone-white shards and pink fluid burst outward; over-the-shoulder shot from the monster's height looking down as both fighters flank it from opposite sides. Girl's scythe hooks into the monster's shoulder joint, camera locked tight on her straining grip and gritted teeth as she wrenches it downward, boy's hammer following through into the same joint a half-second later — impact sound layered, thick and final, monster's roar breaking into a low collapsing groan as its mass folds inward and it drops to its knees then face-first into the floor in a slow, weighty fall, camera pulling back and up into a wide static shot of the wrecked classroom settling into stillness. Both fighters stand over the fallen mass, weapons lowering, chests heaving, camera slowly circling them at floor level; blue-haired girl wipes pink fluid off her cheek with the back of her wrist and starts laughing between breaths, boy lets the hammer head drop to the floor with a thud and laughs too, leaning against a desk, both grinning, exhausted, shoulder-checking each other, red dusk light still pouring through the cracked windows. Ambient sound throughout: creaking wood, scattering papers, cracking plaster, wet impact foley, labored breathing, the monster's guttural vocalizations, ending on genuine breathless laughter. Render risk: full-body transformation sequence may render as a static morph or skip frames — fallback to hard-cutting between three discrete transformation stages rather than one continuous morph if the engine smooths it into mush. Risk: pink blood may drift toward red under default color grading — reinforce with explicit magenta-pink hue callouts at each blood beat. Risk: multi-character wide fight choreography may merge the two fighters' silhouettes in wide shots — favor alternating single-subject framing over simultaneous two-shot action if clarity fails." Made with Seedance 2.0 on Higgsfield AI Full open-sourced prompts & assets below👇

gus

100,376 views • 2 months ago

THIS ENTIRE CINEMATIC ACTION SHOT WAS GENERATED WITH AI. AND YOU CAN SEE EXACTLY HOW IT WAS MADE. Higgsfield has just open-sourced its Originals, giving creators full access to the workflow behind some of its best productions. For every project you can inspect: → the complete prompt → every image and audio reference → the exact generation settings, including model, quality and resolution This scene combines a continuous one-take camera move, large-scale naval combat, realistic explosions, character consistency and cinematic pacing, all driven by a single prompt. Nothing is hidden. You can study it, copy it, recreate it or use it as the starting point for your own projects. Full prompt: "SCENE CONTEXT One continuous shot. The camera faces down the wrecked, burning deck toward the BOW of the ship — and Eduardo, blown off the raised STERN DECK behind the camera by a blast, comes FLYING IN from ABOVE AND BEHIND — leaping off the second level, sailing in over the lens on a forward arc, through raining seawater — slams onto the MAIN deck one level below, AHEAD of the camera, and rolls through a tumbling somersault, momentum carrying him toward the bow. Two crewmen flee past him — one leaps overboard. Eduardo fights his way toward the bow under incoming fire: an explosion bursts on his LEFT — he dodges away and is knocked down; he struggles back to his feet — a second explosion on his RIGHT — he ducks and shields behind debris; then he breaks into a sprint for the bow — the camera sweeps around ahead of him and settles OFF THE BOW, FRONTAL: he leaps over the bow rail TOWARD the camera, the ship filling the background behind him — and THE INSTANT he clears the rail, a COLOSSAL explosion consumes the ship behind him: the blast wall catches him MID-AIR and he VANISHES inside it — he never escapes. The cloud overtakes the camera; the frame floods to 100% smoke and dust. The shot ENDS inside the dust: no transition, no reveal — it holds to the end. ACTIVE REFERENCES >> — lean pirate captain, dark curly hair falling free from under a dusty mustard-yellow cloth bandana, a small white shark tooth pinned to the front of the bandana above his temple, thin moustache, gold hoop earrings, cream linen shirt under a worn brown leather waistcoat, cloth sash and leather belts. 100% matches the reference; the man fighting down the deck toward the bow. >> — Eduardo's galleon: pale square sails, tall wooden sterncastle. 100% matches the reference; controls the ship's exterior — sails, masts, rigging and hull; already battle-damaged in this shot — burst bulwark, smoldering rigging, debris on the deck. >> — the deck of the same galleon seen FROM THE RAISED STERN DECK LOOKING FORWARD TOWARD THE BOW: the great wheel and brass compass binnacle in the near foreground, an ornate lantern post, a carved balustrade, a staircase descending to the long MAIN deck — weathered planking, small cannons along both rails, black gratings, coiled ropes, the mainmast amidships, the forecastle and bow in the far depth, open sea on both sides. 100% matches the reference; controls the full on-deck geography, set dressing AND the shot's base viewing direction — from the stern toward the bow. >> — calm bright sea, glittering sun path, hazy horizon. Controls water and sky atmosphere only. >> — weathered pirate crewmen (bandanas, rough shirts, vests). 100% match the reference; TWO of them appear early in the shot, fleeing — one leaps overboard. LOCATION MAP The deck of >> aboard >> on >> — the raised stern deck (wheel, binnacle, balustrade) at the BACK, the staircase down, the long main deck with cannons, gratings and the mainmast running FORWARD to the distant BOW, exactly as on the reference — the main deck now a wrecked corridor of splintered planks, fallen spars, torn rigging and small fires. The camera sits at the forward edge of the raised stern deck, just past the wheel, LOOKING FORWARD along the whole deck toward the bow — the reference's own vantage; the wheel and binnacle may edge the near foreground. The bow rail and bowsprit are the destination, background-center, open sea beyond them. Sea and smoke beyond the broken side rails; seawater from near-miss columns rains down over the deck in the opening. FIRST FRAME / BLOCKING First frame: deck level, MS, camera facing down the wrecked deck toward the BOW in the background-center — the view of >>: from the stern-deck edge the long main deck runs away to the bow and bowsprit against open sea and sky, cannons along both rails, the mainmast mid-depth, smoke streaming across the frame, small fires burning left and right, seawater spray falling across the deck like rain, the deck listing, loose gear sliding; the wheel and binnacle just behind/beside the camera, edging the near foreground. Eduardo is NOT in the first frame; within the first half second he comes off that second level behind the camera — his body sweeping in OVER the lens from above and behind, boots crossing the top of the frame, flying FORWARD and DOWN one deck-height into the depth of the shot toward the bow. FORMAT MODE One continuous shot — the camera does not cut on its own. The shot ENDS inside the dust whiteout; there is NO location change and NO reveal after it. PHASE 1 — the landing and the gauntlet: >> comes FLYING IN from ABOVE AND BEHIND the camera — blown off the stern deck by a blast, his body sweeping in over the lens and arcing DOWN-AND-FORWARD one full deck-height onto the main deck below, arms out in front of him, back to camera — falling THROUGH a curtain of seawater raining down from a collapsed near-miss column; he SLAMS onto the wet MAIN-deck planks in the depth of the frame and rolls through a hard tumbling somersault AWAY from the lens, toward the bow, water bursting off him and the boards, scattering debris, coming up to a crouch facing the bow, soaked and shaken. TWO crewmen of >> bolt past him in panic — one sprints aft past the camera, the other vaults the side rail and LEAPS OVERBOARD, legs kicking. Eduardo starts working down the deck toward the bow, camera following behind. An incoming round EXPLODES on his LEFT — a burst of flame, planks and spray — he flinches away to the right and is knocked off his feet onto the deck. He struggles up, heavy and unsteady, one hand pushing off a fallen spar — and a second round EXPLODES on his RIGHT — he ducks hard, shielding his head behind a broken mast stump, debris raining over him. PHASE 2 — the sprint, the frontal jump, the blast, the dust: he shoves off and breaks into a desperate sprint at 12 km/h for the bow — and as he runs, the camera SWEEPS AROUND him in one continuous arc, ending positioned OFF THE BOW, out over the open water, FACING BACK at the ship: now Eduardo sprints STRAIGHT AT THE CAMERA, the burning ship towering behind him. He plants one boot on the bow rail and LEAPS OVERBOARD TOWARD THE CAMERA — body launching up and out over the water, frontal, face and reaching arms filling the frame — and THE INSTANT he clears the rail, mid-air, the ENTIRE SHIP EXPLODES behind him in full view: a colossal white flash silhouetting his flying body for two frames, the whole vessel going up in one blast — and the expanding wall of flame-lit smoke and debris CATCHES HIM IN THE AIR from behind, swallowing his silhouette whole before he can fall clear — he VANISHES inside the explosion, never escaping it — and the cloud overtakes the lens, the dust filling 100% of the frame. The dust churns, a deep orange glow pulsing inside it and fading. HOLD inside the full dust to the last frame — the generation ENDS here, inside the dust. He never reaches the water; the blast takes him mid-air. OPTICS 47° neutral through the landing, the gauntlet and the jump. No drift. Focus rides Eduardo throughout; in the final dust the frame is pure particulate with no fixed plane. CAMERA Handheld chase behind him for the entire shot, deck level, always looking TOWARD THE BOW — footstep energy visible, jolted by each explosion; in phase 2 it accelerates after his sprint, then arcs around him in one unbroken move and settles off the bow over the water, FRONTAL to Eduardo — he runs and leaps straight into the lens with the ship in the background of his jump. The final blast is the WHOLE SHIP exploding behind his airborne body — a colossal flash, then the wall of smoke bursting forward, swallowing him mid-air and then the lens — the camera stays buried, holding inside the churning dust until the end. ACTION Strict order of events: flying entry from above through falling seawater → hard landing roll (somersault over one shoulder, forward momentum carrying the roll toward the bow, ending in a crouch) → two crewmen flee past, one over the side → left explosion → dodge right → knocked down → a hard, clumsy struggle back to his feet → right explosion → duck and shield behind the mast stump → shove off → full sprint to the bow, camera arcing around to meet him head-on → one boot on the rail → LEAP overboard straight toward the camera → THE INSTANT he clears the rail, the ENTIRE SHIP EXPLODES behind him → the blast wall catches him MID-AIR and swallows him whole → the cloud overtakes the camera → dust to 100% → hold in the dust → END. He never escapes and never reaches the water. Each explosion visibly moves his body: the first throws him down, the second folds him behind cover. PERFORMANCE During the gauntlet: jaw clenched, eyes fixed forward, water streaming off his face after the landing. The fleeing crewmen are pure panic — arms pumping, one glance back, the vault over the rail desperate. In the final sprint: full commitment, arms reaching for the rail, eyes wide — in the jump: full commitment, arms reaching at the lens, eyes wide — and mid-air the world behind him turns white: his flying silhouette swallowed by the blast, reaching hands the last thing visible. PHYSICS The flying entry has true ballistic momentum: he arrives on an arc from above, and the landing roll absorbs it — impact compresses the body, the somersault carries the leftover energy, no weightless float. Falling seawater has real weight — it rains in heavy drops and sheets, splashing off planks, soaking cloth so it clings and darkens. The listing deck tilts his movement; debris has weight and stops his foot when hit. The two deck explosions throw real shockwaves — planks lift, flame flashes then roll into smoke, and Eduardo's falls carry true body weight, hard contact with the deck, no bounce. The overboard crewman drops with real gravity. The final whole-ship explosion obeys mass: the shockwave arrives first — cloth and hair snap flat, the deck bucks under his planted boot — then the fireball's light, then the wall of smoke and debris, heavy pieces falling short, fine dust travelling farthest and swallowing the frame. Dust churns with internal motion, dense, filling every corner of the frame. LIGHTING High sea daylight 5600K, hardened by fire-glow accents from the deck fires and smoke shadow sweeping the deck; falling water catches the sun as bright streaks; each of the two explosions throws a brief warm flash from its side of the frame. The final whole-ship blast: two frames of white-hot overexposure flooding from behind, then deep fire-orange glow inside the rolling dust, fading toward neutral grey-brown as the frame holds and ends. AUDIO Phase 1: a whistling whoosh as he drops in, heavy water raining on planks, a THUD and clatter of the landing roll, grunt, ragged breath; panicked boots of the fleeing crewmen, a yell and a distant splash as one goes over the side; then BOOM left, ringing ears, his grunt as he hits the deck; scrabbling boots; BOOM right, debris pattering down over him. Phase 2: sprinting boots hammering the deck, the wooden knock of his boot on the bow rail, half a beat of pure wind as he hangs in the air — then ONE colossal BOOM as the whole ship goes up behind him, the deepest sound of the film, cracking timber and folding masts inside the roar, everything collapsing into a muffled ring, sound buried with the picture — the ring and the churn of dust holding to the last frame. No music. STYLE Photoreal live-action, fine film grain, real pyrotechnic and particulate language, one unbroken take, 8K master. POSITIVE LOCKS One continuous shot; the camera stays at deck level, behind Eduardo, always looking TOWARD THE BOW. The shot OPENS with Eduardo NOT in frame; he flies in from ABOVE AND BEHIND the camera, over the lens, on a forward arc toward the bow, through falling seawater, and lands in a tumbling roll ahead of the camera — he does not walk into frame and never appears standing before the landing. Exactly TWO fleeing crewmen: one runs aft, one leaps overboard — they appear only in the opening beat. The deck explosions land in strict order after his landing: first LEFT of him (he dodges and falls), then RIGHT of him (he ducks behind cover), then the final blast — the ENTIRE SHIP exploding the INSTANT he clears the bow rail — three explosions total, no more. The jump is FRONTAL: the camera faces Eduardo from off the bow, he leaps toward the lens with the exploding ship behind him in frame. HE NEVER ESCAPES: the blast wall catches him MID-AIR and he vanishes inside the explosion before he can fall clear — no water contact, no landing, no survival beat; the dust swallows him and then the lens. The deck matches >> throughout the run — the shot holds the reference's vantage: from the stern deck forward to the bow, wheel and binnacle at the near edge of frame, never ahead of him; sails, masts and hull match >>. The dust reaches 100% frame coverage and the shot ENDS inside the dust: the frame stays fully dust-filled to the last frame, no clearing, no new location, no reveal. Eduardo's head: mustard-yellow bandana with the small white shark tooth at the front, hair loose." Made with Seedance 2.0 on Higgsfield AI. Full open-sourced prompts & assets below 👇

roman

106,768 views • 2 months ago

john wick seedance text to video prompt: [STYLE / CINEMATIC SETUP] A 10.5-second, 16:9 photorealistic AAA action-game cinematic rendered at real-time speed with no slow motion. The setting is a cramped, cluttered late-night Asian restaurant connected to a rain-soaked street. Cyan-green fluorescent light, red neon and warm practical lamps create a high-contrast mixed-light environment, with reflections across wet floors and pavement. Shoot with a 35mm spherical lens, shallow-to-moderate depth of field and cinematic motion blur appropriate to the actual speed of movement. Use close shoulder-mounted and handheld coverage, connecting seven short close-combat shots with fast hard cuts. The camera instinctively pans, retreats or drops with each block, takedown and collision while keeping the action and contact points readable. No dialogue, no subtitles and no BGM. Generate only synchronized rain, appliance hum, urgent footsteps, fabric movement, body impacts, gunshots, metal contact and breaking glass. [IMAGE REFERENCES] No external still-image reference. Follow the written character and environment descriptions consistently. If the platform supports reference video, use the supplied video only as a reference for editing rhythm, camera distance, action direction and lighting atmosphere, not for copying a specific actor’s identity. The protagonist remains the same lean, agile man in his early forties throughout the sequence: neck-length black hair swept back, a short beard, a tired but focused face, a slightly wrinkled black suit, white shirt and narrow black tie, all carrying faint rain and wear marks. Preserve his face, hairstyle, body proportions, clothing and screen direction across all seven shots. Keep every opponent visually distinct: a man in a blue work uniform, a bald man in a navy jacket, a heavy man in a black jacket, a bald counter attacker, a red-headband attacker, a red-jacketed armed attacker and a heavy man in a dark green coat outside. [TIMELINE SECOND BY SECOND] 0–1.9s: [Shoulder-height medium close-up, tight lateral handheld tracking, real-time speed] The protagonist stands on screen left, pinning the blue-uniformed attacker against a glass refrigerator with his left forearm and palm. He delivers two compact, weighted elbow and palm-heel strikes. Each impact drives the attacker’s head into the refrigerator door, loosening his white headband and leaving a small blood trace on the glass; the attacker finishes sliding down the door while the protagonist remains standing. 1.9–4.3s: [Medium shot transitioning into a high-angle overhead, shoulder-mounted drop, real-time speed] Hard cut near the restaurant’s rear entrance. The bald attacker in a navy jacket locks the protagonist from behind. The protagonist lowers his center of gravity, traps the attacker’s arm and rotates his hips, throwing him heavily over the shoulder onto the wet floor. The camera drops with them into an overhead view. Kneeling across the attacker’s torso, the protagonist draws a compact black pistol and fires one downward shot; recoil travels through his wrist and the attacker jolts once before becoming still. 4.3–5.9s: [Tight medium shot, lateral handheld follow, real-time speed] Hard cut with both men already upright. A heavy attacker in a black jacket swings from screen right. The protagonist slips outside the punch, allowing it to pass close to his face, circles behind the attacker and locks his shoulder and neck off balance. He presses the pistol close to the side of the attacker’s head and fires. The muzzle flash briefly illuminates both faces; the attacker’s head and shoulders snap backward and his body begins to collapse. 5.9–7.9s: [Counter-height medium close-up, subtle handheld push-in, real-time speed] Hard cut to the restaurant counter. Another bald attacker bends forward and clamps around the protagonist’s waist. The protagonist pins the attacker’s head and neck under his left arm while grabbing a short, rigid pointed utensil from the counter. He drives two compact downward thrusts into the upper shoulder and side of the neck. Each contact bends the attacker’s knees further; a restrained amount of blood marks the shirt and counter edge before the attacker hangs helplessly beneath the protagonist’s controlling arm. 7.9–9.0s: [Two-person medium close-up, fast pan with a short retreat, real-time speed] Hard cut as the red-headband attacker rushes into close range. He throws a wide hook from screen right. The protagonist raises his forearm to block, catches the wrist and pulls it outward, then drives a palm heel and forearm into the attacker’s face. The camera retreats with the impact as the attacker loses his balance and staggers toward the rear right of the frame. 9.0–9.9s: [Low-angle wide shot, slight arc around the action, real-time speed] Hard cut to a wider section of the restaurant. The red-jacketed armed attacker advances from screen left. Holding a long black firearm with both hands, the protagonist uses it as a blunt weapon and swings horizontally from right to left. The weapon strikes the attacker’s upper chest and shoulder, rotating his torso, crossing his feet and sending him off balance toward screen left. 9.9–10.5s: [Exterior rainy-street medium shot, fast parallel tracking, real-time speed] Hard cut outside the restaurant. The protagonist already controls a heavy attacker in a dark green coat and uses his forward momentum to drive the man’s head and upper body into the side window of a parked black station wagon. The glass bursts inward at the contact point, scattering both large and fine fragments. The attacker folds through the broken window while the protagonist regains stable footing beside the car, ending with glass fragments still falling. [STYLE & QUALITY BOOSTERS] Maintain the protagonist’s face, black suit, white shirt, tie, hairstyle and body proportions through every hard cut. The pistol, pointed utensil, injuries and blood marks must appear only in their designated shots and must never morph or change ownership. Throws, recoil, strike reactions, loss of balance and window breakage must show believable weight, inertia and precise contact. Apply motion blur only to rapidly moving arms, weapons, glass fragments and camera-relative backgrounds. No sudden face or costume changes; no extra fingers, fused limbs or inverted joints; no morphing weapons, utensils or vehicles; no foot sliding or rubber-like collision reactions; no blood, bullet damage or glass fragments appearing before physical contact.

underwood

12,588 views • 1 month ago

The countdown to chaos begins. GPT Image 2 + Seedance 2.0 on Thank You AI prompt Use [Image 1](image_1)only as the layout, shot-order, camera, staging, screen direction, pacing, and spatial continuity reference. Treat every storyboard panel as an individual shot. Ignore storyboard drawing style, simplified anatomy, panel text, headers, borders, annotations, scribbles, malformed props, duplicate silhouettes, stray marks, icons, and effect sketches. Use @[Image 3](image_3) only for Character 1's final appearance, face, body proportions, long wavy blonde hair, black long coat, gloves, wardrobe materials, and overall likeness. Use @[Image 2](image_2)only for Character 2's final appearance, face, body proportions, short hair, dark hoodie, wrist device, multi-barrel handgun, wardrobe materials, and overall likeness. Create a photorealistic 15-second cinematic Hollywood action trailer with seamless continuity, maintaining exactly two lead characters throughout every shot. CHARACTER LOCK • C1: Female whip duelist only. Uses only a glowing crimson energy whip attached to her hand. • C2: Male gunner only. Uses only a blue wrist holographic device and a futuristic multi-barrel handgun. • Never merge identities. • Never duplicate either character. • Never introduce additional heroes. • Background pedestrians, guests, taxis and vehicles remain simplified environmental extras only. VISUAL STYLE Ultra photorealistic. Bright daytime. Gritty cyberpunk realism. Wet reflective New York streets. Orange construction barriers. Yellow taxis. Steam rising from manholes. Glass skyscrapers reflecting sunlight. Modern luxury glass building with a red carpet entrance. Purple architectural accent lighting. Hollywood blockbuster cinematography. Natural motion blur. Volumetric smoke. Practical explosions. Lens flares. Realistic debris. High-speed tracking. Large-scale cinematic lighting. 4K feature-film realism. Maintain consistent geography from the street battle into the red-carpet location. SHOT SEQUENCE SHOT 1 Street-level camera positioned behind C1 on wet reflective asphalt. Steam rises from a nearby manhole. C1 plants her feet and swings the crimson energy whip low across the pavement, generating a bright red whip trail that lashes sideways while the city reflects in the wet road. SHOT 2 Wide tracking shot. C1 launches into the air over an exploding yellow taxi. Fire and debris erupt behind her as the crimson whip forms a long glowing arc through the bright daytime skyline. SHOT 3 Extreme floor-level insert. Close on C1's boot striking wet pavement while the whip tip cracks the asphalt, sending sparks, shattered concrete and glowing fragments outward. SHOT 4 Low tracking shot beside C2 sprinting directly toward camera through drifting smoke. His glowing blue wrist device illuminates one raised arm while debris flies behind him. SHOT 5 Close-medium shot. C2 extends his arm forward. A bright cyan holographic grid rapidly projects from the wrist device, expanding outward while taxis and skyscrapers remain visible in the background. SHOT 6 Extreme close-up. C2 draws a futuristic multi-barrel handgun. The weapon fires its first brilliant blue energy shot, producing an intense muzzle flash with cinematic lens flare. SHOT 7 Bird's-eye overhead shot. Street geometry clearly visible below. C1's crimson whip trail and C2's blue muzzle fire cross dramatically through opposite corners of the frame while both characters remain small at opposite edges. SHOT 8 Slow-motion tilted action shot. C2 vaults over an exploding taxi as blue muzzle flashes continue beneath him. Fireballs, smoke and debris scatter realistically through the air. SHOT 9 Hard cinematic location transition. Wide establishing shot outside a luxurious modern glass building. Bright daylight continues. A pristine red carpet stretches toward the entrance. Elegant guests stand watching. C1 and C2 occupy opposite ends of the carpet. No weapons active. No energy effects visible. SHOT 10 Close two-shot. C1 and C2 stand only an arm's length apart on the carpet. Absolute stillness. Silent confrontation. Controlled breathing. Intense eye contact. Purple architectural lighting reflects softly on the glass facade. SHOT 11 Medium shot. C2 slowly raises one hand and pulls his hood over his head while already turning three-quarters away from C1 toward the entrance. C1 remains perfectly still behind him. SHOT 12 Maintain identical framing and geography from Shot 11. C2 calmly walks toward the building entrance as guests subtly turn to watch. C1 stays motionless at the edge of frame, silently observing his departure. Hold on the unresolved tension before fading to black. CAMERA STYLE Aggressive cinematic tracking. Steadicam. Drone overhead. Ground-level perspectives. Extreme close-ups. Wide establishing shots. Smooth transitions. Natural handheld energy during action. Controlled locked-off framing during the red-carpet sequence. ACTION STYLE Fast. Powerful. Readable silhouettes. Fluid stunt choreography. Heavy environmental interaction. Convincing physics. No exaggerated anime motion. Grounded Hollywood realism. COLOR PALETTE Bright daylight. Warm sunlight. Wet asphalt reflections. Crimson energy whip. Brilliant blue muzzle flashes. Cyan holographic projections. Orange construction barriers. Yellow taxis. Black wardrobe. Red carpet. Purple entrance lighting. Natural skin tones. AUDIO Large cinematic orchestral hybrid score. Driving trailer percussion. Deep sub-bass impacts. Powerful whip cracks. Explosive booms. Metal and glass debris. Blue energy weapon blasts. Holographic interface tones. Crowd ambience fading into near silence at the red carpet. The final moments become quiet, tense and emotionally restrained before ending with a dramatic cinematic trailer hit.

Sharon Riley

43,583 views • 2 months ago

Seedance 2.0 Prompt: Create a 15 second, 16:9 photorealistic nighttime urban fashion film sequence following one consistent young adult man through a frantic city run. SUBJECT: A slim young man in his early twenties with naturally messy short brown hair, slightly pale skin, lean athletic build, wearing an oversized plain white cotton T-shirt, loose black trousers and simple dark-and-white running shoes. Keep his facial structure, hairstyle, body proportions, clothing and footwear perfectly consistent throughout every shot. He should look genuinely exhausted from running: subtle perspiration, flushed skin, heavy breathing, naturally disheveled hair. No model-like posing. OVERALL VISUAL LANGUAGE: Raw contemporary street fashion music video mixed with documentary night photography. Photoreal, physically believable, imperfect and spontaneous rather than polished CGI. Shot as though a real camera operator is chasing the subject through the city. 24fps cinematic motion, natural 180-degree shutter motion blur, approximately 24mm wide-angle full-frame lens aesthetic for chase shots, occasional 35–50mm observational shot, realistic handheld operator movement, slight rolling-shutter behavior during aggressive pans, imperfect focus pulls, subtle sensor noise and fine low-light grain. Do not make the camera artificially smooth. Preserve tiny footsteps, vertical camera bounce, imperfect reframing and occasional edge cropping when the operator struggles to keep up. COLOR: Cool cyan-green fluorescent interiors contrasted against deep blue-black nighttime streets and occasional warm amber streetlights. Natural skin tones despite mixed illumination. Slightly lifted fluorescent highlights, rich black shadows, modest digital grain, restrained saturation. Avoid glossy blockbuster grading. SHOT SEQUENCE: 0.0–1.5 SEC — Begin immediately behind the young man inside a modern underground transit passage. He rushes toward an escalator beneath long fluorescent tube lights. Camera follows only 1–2 meters behind him at waist/chest height. The oversized white shirt folds, stretches and moves naturally with every stride. Fluorescent fixtures create realistic exposure fluctuations as he passes underneath them. Patterned stone and brushed-metal architecture streak gently in the background. At approximately 1.3 seconds insert a 3–4 frame photographic negative/inverted silhouette flash followed immediately by a brief overexposed white flash, synchronized perfectly with the music. 1.5–3.3 SEC — Smash cut into a concrete underground corridor. Low handheld rear-follow shot as he sprints around a structural column and through a slightly empty parking/transit passage. Camera operator runs behind him, producing authentic vertical bounce and small rotational instability. His footsteps should demonstrate real body weight: heel contact, torso rotation, swinging arms, shifting fabric and believable momentum. 3.3–4.5 SEC — During a fast whip pan, city lights stretch into organic red, cyan and white trails caused by real long-exposure-style camera motion. The streaks naturally resolve into an extreme-wide nighttime city view from an elevated position. A nearly empty multi-lane street cuts through tall buildings. The runner is tiny in the lower central portion of the frame, emphasizing human scale against the architecture. No impossible traffic or duplicated pedestrians. 4.5–6.2 SEC — Hard cut to a lateral observational shot from across the street. The man runs horizontally past a glowing generic convenience storefront. The foreground is partially obscured by a dark architectural edge, producing the feeling that the camera accidentally catches him racing through the city. Cut immediately to a ground-level tracking shot beside a modern glass office building. Reflections of real streetlights ripple across the glass while illuminated apartment and office windows fill the distant skyline. 6.2–8.6 SEC — Cut to the bottom of a narrow indoor stairwell. Camera is low and nearly stationary, looking upward along symmetrical black stairs, silver handrails and white tiled walls under cold cyan fluorescent lamps. The runner suddenly appears at the top and races down toward the lens. His movements must obey real gravity and balance. One hand briefly contacts the railing. His shoes strike individual stairs rather than floating over them. As he passes extremely close to camera, allow the image to become partially blurred and imperfectly framed. Camera rapidly swings around behind him and follows onto the landing. 8.6–10.8 SEC — Hard cut as he bursts from the dark street into a brightly illuminated independent convenience store. Rear handheld chase through the doorway. The automatic exposure takes a fraction of a second to compensate for the dramatic brightness change. Realistic compact shop interior: densely stocked shelves, colorful snack packages, refrigerated drink cabinets, glossy commercial flooring, fluorescent ceiling panels, believable product variety but NO recognizable real-world brand logos. The runner navigates the aisle quickly while the wide-angle camera struggles to follow. 10.8–12.8 SEC — He reaches the refrigerated drink section and finally stops. Camera moves into a loose medium-close handheld angle. He pulls one clear plastic water bottle from the cooler, twists the cap open while catching his breath and immediately drinks. Show physically correct transparent plastic, liquid refraction, condensation, bottle deformation under finger pressure and believable hand anatomy. His breathing remains visible through subtle chest and shoulder movement. 12.8–15.0 SEC — He lowers the bottle, takes one final breath, suddenly turns and accelerates. Camera whips behind him. He sprints back down the store aisle toward the open doorway. Shelves naturally stretch with directional motion blur while the subject remains intermittently sharp. At 14.5 seconds he bursts through the doorway into the dark city. As he crosses the threshold, create a tiny physically plausible shower of warm orange sparks/light fragments from an unseen practical source outside, lasting only a fraction of a second — subtle, not magical. Camera stops inside the brightly lit store while he disappears rapidly into the black nighttime street. Finish on the contrast between the empty glowing doorway and the darkness outside. CUT TO BLACK exactly at 15.0 seconds. AUDIO / MUSIC: Original instrumental soundtrack, no vocals and no copyrighted melody. Fast 150–158 BPM nocturnal electronic breakbeat with underground fashion-film energy. Tight dry kick drum, punchy low sub-bass, nervous syncopated percussion, crisp metallic hi-hats, distant distorted synth pulse and a restrained atmospheric pad. 0–3 sec: minimal heartbeat-like sub pulse with rhythmic percussion building. 3–6 sec: bass and breakbeat enter harder during the city reveal. 6–9 sec: aggressive percussion synchronized to the stair descent. 9–11 sec: slight musical filtering during entry into the convenience store. 11–13 sec: beat briefly strips back while he drinks, leaving bass pulse and atmospheric synth. 13–15 sec: full beat returns with maximum momentum, then abrupt hard stop when the image cuts to black. REALISTIC SOUND DESIGN mixed underneath the music: running footsteps changing acoustically between tile, concrete, stairs and shop flooring; distant city traffic; escalator machinery; clothing movement; authentic breathing; stairwell reverb; fluorescent electrical hum; convenience-store door chime; refrigerator compressor ambience; plastic bottle handling; cap twist; water gulp; final door movement; subtle spark crackle. Sound perspective must follow camera distance naturally.

BMX

11,865 views • 2 months ago

Made with Wan 3.0 Prompt : Create a 12–15 second photorealistic luxury food commercial using the supplied PAIN dessert images as the visual reference. The finished video must look like a real high-budget food advertisement filmed on a professional tabletop set with a cinema camera, real studio lighting, practical food styling, and high-speed commercial photography. IMPORTANT: The vanilla cream vortex is ALREADY FULLY FORMED from the very first frame. Do NOT generate the cream from nothing. Do NOT make the dessert magically grow, transform, explode, or assemble itself. Keep the existing sculptural cream composition intact and introduce only small, physically believable movements. PRODUCT CONSISTENCY: Keep the PAIN dessert cup exactly consistent with the reference images throughout the entire video. Preserve: - exact black cup shape and proportions - PAIN logo - typography - logo position - packaging colors - cup rim - dessert proportions - vanilla cream structure - caramel placement - wafer and chocolate elements Do not redesign, deform, stretch, melt, rotate incorrectly, or morph the packaging. FOOD REALISM: The vanilla cream must look like real dense whipped dairy cream with natural folds, tiny air pockets, subtle surface imperfections, realistic softness, slight moisture, and naturally controlled highlights. The cream should feel heavy and edible. Never make the cream look like: - plastic - foam - clay - fabric - rubber - glossy CGI - liquid splash The caramel should look like real warm caramel: thick, viscous, sticky, glossy but naturally glossy, slightly translucent amber, with realistic surface tension and subtle stretching. Do not make the caramel glow like neon or behave like weightless ribbons. Chocolate-coated wafer pieces should have real physical weight, crisp edges, visible wafer layers, small imperfections, realistic chocolate coating, and natural crumbs. Crumbs should fall naturally under gravity and move slightly differently from each other. Do not make every object move perfectly or symmetrically. MOTION: Keep all motion subtle, restrained, elegant, and physically believable. The cream sculpture should remain almost completely stable. Only introduce realistic micro-movement such as: - extremely subtle rotation of the hero dessert - gentle natural movement in the caramel - a few wafer pieces slowly shifting or rotating - several small crumbs naturally falling - subtle foreground and background parallax - tiny settling movements The overall scene should feel like carefully rigged practical food photography captured with a high-speed cinema camera. Avoid excessive floating objects. CAMERA: Use realistic professional food-commercial cinematography. Use the visual characteristics of: - full-frame cinema camera - 50mm lens for hero product shots - 85mm macro lens for close-up food details Use: - natural shallow depth of field - realistic focus falloff - subtle lens breathing - natural motion blur - physically plausible perspective - gentle focus transitions Camera movement must be extremely smooth and restrained. Use only: - slow physical dolly push-in - gentle 10–15 degree orbit - slow macro vertical glide - stable final packshot No aggressive zooms. No fast orbit. No handheld shaking. No impossible camera movement. No sudden speed changes. SHOT SEQUENCE: 0:00–0:03 — HERO REVEAL Begin with the complete PAIN dessert already fully assembled and sculpted exactly like the reference image. The PAIN cup sits firmly on a real studio surface. The vanilla cream vortex is already fully formed above the cup. Warm studio lighting slowly reveals the texture of the cream, caramel, chocolate, and cup. Use a very slow physical camera push-in. The cream itself stays stable. Only the caramel has extremely subtle natural movement and a few tiny crumbs gently fall through the scene. The PAIN branding remains clear and stable. 0:03–0:06 — MACRO FOOD DETAIL Cut naturally to a close macro shot. Camera slowly travels upward along the existing vanilla cream folds. Show realistic details: tiny air pockets in the cream, natural irregularities, caramel thickness, caramel reflections, chocolate texture, wafer layers, small crumbs. The camera should feel physically close to real food. Caramel moves only slightly. One or two crumbs fall naturally. No magical movement. No morphing. 0:06–0:10 — CINEMATIC ORBIT Return to a wider hero angle. Perform a very gentle 10–15 degree camera orbit around the dessert. Keep the cream structure unchanged. Create realistic parallax between: - cup - cream - caramel - wafer pieces - foreground crumbs - background A few wafer pieces may rotate very slowly with believable physical weight. Several small crumbs naturally drift downward. The scene should feel carefully choreographed but still physically real. 0:10–0:15 — FINAL PACKSHOT Slowly transition into a perfectly composed full-product hero shot. The camera gently pulls back and then becomes completely stable. Caramel movement becomes almost imperceptible. Remaining crumbs slowly settle. Keep the PAIN logo sharp, correct, readable, and unchanged. Create a soft warm backlight behind the upper cream structure. Do not create excessive glow. Hold the final frame almost completely still for approximately one second so it feels like a real premium advertising end frame. LIGHTING: Use realistic professional tabletop studio lighting. Use: - large diffused warm key light - subtle tungsten warmth - soft golden backlight - controlled rim lighting on the black PAIN cup - realistic reflections on caramel and chocolate - natural contact shadows - controlled specular highlights - dark brown-to-black background falloff Lighting must look physically generated by real studio lights. Avoid: - excessive bloom - strong lens flares - glowing particles - fake volumetric beams - neon lighting - oversaturated orange Highlights should roll off naturally like real cinema footage. COLOR: Use premium realistic food-commercial color grading. Rich chocolate blacks. Natural warm amber caramel. Creamy off-white vanilla. Deep brown chocolate. Warm but restrained highlights. Subtle filmic contrast. Natural saturation. Do not make the entire video heavily orange. MUSIC: Use soft, elegant, restrained luxury-commercial music. The music must NOT be aggressive. Absolutely no: - aggressive music - EDM - hard drums - fast electronic beats - trailer music - dramatic impacts - heavy bass drops - intense percussion - action-style music Use instead: - soft ambient cinematic pads - delicate piano notes - subtle glass-like tones - very light organic percussion - warm atmospheric textures - gentle minimal electronic pulse - slow sophisticated emotional build The music should feel luxurious, calm, refined, modern, sensual, and expensive. Think premium fragrance commercial combined with a luxury chocolate advertisement. The music should support the product rather than dominate the video. SOUND DESIGN: Use extremely subtle realistic sound effects only. Add: - very soft caramel movement - delicate wafer crisp texture - subtle falling crumb sounds - gentle airy movement - soft cinematic transition sounds - one understated low tonal resolve at the final packshot No exaggerated whooshes. No cartoon sound effects. No aggressive impacts. CRITICAL REALISM RULES: The video must NOT look AI-generated. Avoid: - morphing - warping - flickering - melting packaging - changing cup shape - changing logo - misspelled PAIN text - distorted typography - duplicated wafers - disappearing objects - objects appearing from nowhere - changing dessert structure between frames - impossible physics - weightless toppings - perfectly synchronized particles - random food explosions - exaggerated splashes - excessive slow motion - unnatural glowing caramel - plastic cream - rubbery caramel - waxy chocolate - artificial reflections - excessive depth of field - sudden camera jumps - unrealistic floating ingredients Prioritize real food texture, physical weight, natural imperfections, realistic gravity, believable studio lighting, authentic cinema-camera optics, restrained movement, consistent product identity, and perfect temporal continuity. The final result should feel like a real luxury dessert commercial shot practically in a professional studio, not a CGI animation.

Liam | AI Tools & News

11,844 views • 1 month ago

Grok Imagine text-to-video prompt: SCENE CONTEXT One continuous locked-off wide shot inside a cluttered high-rise gaming apartment at night. A fully clothed adult man sits at his desk facing the monitor, absorbed in a computer game. An adult anime woman (age 22 or older) carrying a metal frying pan sneaks up behind him from frame-left, swings the pan hard and fast into the back of his head with a single whip-crack strike that knocks him out cold instantly, his head dropping hard onto the desk with a small bounce. She delivers a short Japanese line, then runs off frame-right while giggling. LOCATION MAP Foreground: edge of the desk and chair legs. Midground: the seated man at the gaming desk with dual monitors, keyboard, mouse, RGB lighting, and scattered energy-drink cans. Background: cluttered apartment wall with posters, shelves of figures, city-window view at night. The anime woman enters from frame-left rear, moves behind the man's chair, then exits frame-right. Warm practical room lamps mixed with cool blue monitor glow and red PC accent lights. FIRST FRAME / BLOCKING Wide shot already framed and locked. The man is seated center-right, torso facing the monitors, head slightly forward. The anime woman is partially visible at the far left edge of frame, body oriented toward the man, frying pan held low in both hands at waist height. Spatial relationship readable immediately: she is behind and slightly to his left, outside his peripheral vision. FORMAT MODE One continuous shot, the camera does not cut on its own. The frame stays identical from first second to last. OPTICS 47° neutral wide FOV, eye-level height matching the man's seated eye line, deep focus so both the desk and the space behind the chair remain sharp. No drift for the full duration. CAMERA Locked tripod, completely stationary, frame fixed for the entire 15 seconds. The operator stays hands-off after the first frame. ACTION 0.0s–3.5s — The man clicks the mouse and taps the keyboard with natural, focused movements, leaning slightly toward the monitor. The anime woman advances on light tiptoe steps from frame-left at about 3 km/h, body low, frying pan close to her torso, eyes fixed on the back of his head. 3.5s–6.0s — She reaches the position directly behind his chair and coils into a short compact wind-up: pan raised above her right shoulder, both hands gripping the handle, weight loaded onto her rear foot, hips turned slightly away like a batter ready to swing. 6.0s–6.5s — She uncoils and swings hard and fast: hips rotate first, shoulders whip through, the pan accelerates through a tight horizontal arc and reaches roughly 30 km/h at the moment the flat of the pan meets the exact center of the back of his head. The full swing takes 0.4 seconds from launch to contact, a single clean whip of motion. 6.5s–7.5s — Knocked out cold, lights out on impact. On the exact contact frame his eyes shut and every muscle releases at once. His head drops hard and fast, driven forward by the strike, and his forehead smacks the desk surface with a solid thud, bounces up once about five centimeters, and lands again, coming to rest cheek-down on the desk. His torso folds forward behind the falling head, arms flopping off the keyboard and mouse and settling limp on the desk. He is out cold and remains completely motionless from this point through the end of the shot, head down, dead to the world. 7.5s–10.5s — She lowers the pan to her side, stands upright behind the slumped man, and speaks her line with clear lip sync while looking down at his knocked-out body, chest rising with a satisfied breath. 10.5s–15.0s — She turns sharply to her right, takes three quick running steps toward frame-right at about 10 km/h, and exits the frame still holding the frying pan, body leaning forward into the run, shoulders bouncing with a giggle. PERFORMANCE Man: fully absorbed in the game until impact, natural micro-adjustments of hands and slight forward lean. From the contact frame onward he is unconscious dead weight: face slack, jaw loose, eyes closed, zero muscle tension anywhere in his body. After the head bounce settles he is a motionless heap draped over the desk, held perfectly still through the end of the shot, clearly out cold. Anime woman: bright adult face with clean 2D cel-shaded features, mischievous grin, tongue pressed to the corner of her mouth during the wind-up. The swing is committed and athletic: full-body rotation, arms extending through the arc, a small follow-through past the contact point before she checks the pan. After the hit her posture opens into a brief proud stance, then she pivots and runs with lively bouncing steps and a visible giggle that lifts her shoulders. Eyes stay alive with micro-saccades throughout. Playful older-sister prank energy, posture upright and comedic. PHYSICS The frying pan carries visible metal mass and inertia: it lags a fraction behind her hands at the start of the swing, whips through the arc with accelerating momentum, and stops dead on contact with a small vibration through the pan face and her forearms. The man's head falls as pure dead weight accelerated by the strike: fast drop, hard contact with the desk, one small five-centimeter rebound, then final settle with zero further motion. The desk registers the impact: a nearby energy-drink can jitters, the mouse shifts a centimeter. His torso folds forward behind the head and settles as a limp mass, no residual muscle movement afterward. Her hair and clothing trail the swing rotation with natural delay and settle after the follow-through. Her footsteps show clear weight transfer on the sneak and the exit run. LIGHTING Primary sources: warm 3200K practical desk and room lamps from upper left, cool monitor glow illuminating the man's face and hands, red PC case lighting under the desk. Soft natural falloff into the background. The pan catches a brief warm lamp glint as it whips through the swing arc, and the contact shadow of the pan and her arms sweeps across the man's back at the moment of impact. AUDIO Clear adult feminine Japanese anime voice with accurate lip sync delivering exactly: 「おやすみなさい!」 A sharp air-whoosh as the pan whips through its arc, ending in a single bright comedic metallic BONK on contact, followed immediately by a solid wooden thud as his head hits the desk and a lighter second tap on the bounce landing. Continuous quiet keyboard taps and mouse clicks up to the hit, then silence from the desk. Computer-fan hum, faint game audio from the speakers, quiet room tone, distant city ambience through the window. Her light footsteps on the floor, then a short bright giggle as she runs. Only the listed sounds and the single spoken line. STYLE Photorealistic cluttered apartment interior combined with a crisp, clean 2D cel-shaded adult anime character. Warm practical lighting mixed with cool monitor and red PC accents, natural contact shadows, light cinematic grain. Wholesome slapstick gaming-comedy tone, the energy of a classic anime frying pan bonk. POSITIVE LOCKS Camera remains completely locked and stationary for the full 15 seconds, identical framing first frame to last. The man keeps facing his monitors until the strike and is knocked out cold on the exact contact frame: head drops hard and fast, forehead smacks the desk, one small five-centimeter bounce, then final rest, body limp and motionless through the end of the shot. Single pan strike only, swung hard and fast with full-body rotation, the arc completed in 0.4 seconds. Anime woman is clearly adult (22+), modest casual gaming-themed clothing, 2D cel-shaded style only. Only the one scripted Japanese line is spoken.

tetsuo

12,738 views • 1 month ago

AI creations are becoming more impressive, but the most interesting part is often what happens behind the scenes. Higgsfield has open-sourced its Originals, giving creators access to the prompts, references, and workflows behind these AI films. Now you can see how these creations come together, explore the process, and learn from the techniques behind them. Prompt for this video: Style: 8K IMAX, traditional hand-drawn 2D animation, animated on twos at 12 frames per second — each drawing held for two frames then replaced, choppy stepped motion cadence, visible pose-to-pose timing, distinct keyframe drawings with no smooth in-between interpolation, hand-painted oil-brush texture on every drawing, brushstrokes shifting and redrawn from frame to frame, line jitter and boil between frames. No 3D render, no game engine, no CGI smoothness. The 12 principles of animation throughout: anticipation, squash and stretch, follow-through and overlapping action, slow in/slow out, arcs, secondary action, exaggeration, solid drawing — applied to every element including wolf bodies, clothing, breath, and snow particles. Cinematography: Lubezki / Deakins. Aggressively handheld inside the scene — constant restless shake and jitter every frame, jerky bounce, frame buffeted sideways by gusts, sharp reframing jolts, breathing sway. Horizon never perfectly level. Never gimbal-smooth, never tripod, never dolly, never crane, never aerial. Wide anamorphic approximately 24mm. Shallow depth of field. Camera eye level or below. CHARACTER REFERENCE IS ABSOLUTE — faces and designs from reference images exactly 1-to-1. Reference always overrides text description. CHARACTER TAGS: - THE MOTHER = woman from >>. Bundle clamped to her chest in one arm, the bundle a dark non-glowing shape, faint pale grey breath vapor torn off by the wind, no glow. - THE TODDLER = small girl from >>. Name Umai. - THE WOLVES = animals from >>. Each wolf stands roughly half a human's height at the shoulder. Body length from head to tail equals approximately one full human height. Large, heavy, and low to the ground. - THE FOREST = location from >>. Lighting: no light source, no moon, no stars, no rim light, no contre-jour, no key light. Flat dim diffuse ambient grey-white glow only — no direction, no gradient shading. Flat painted shapes. All forms read as dark silhouettes or mid-grey against white atmosphere. Atmosphere: violent blizzard continuous every frame. Snow driven horizontally. Visibility approximately 3 meters. Rolling white-out waves sweeping the lens. Wind never drops. Hair and robe ends stream sideways with full follow-through and overlapping action. Audio: dominant roaring blizzard wind. THE MOTHER's trembling breath close. Distant low wolf howl buried under wind, barely audible in Shot 2D. No dialogue. No music. No subtitles. SHOT 2C — EXTREME CLOSE-UP handheld on THE MOTHER's eyes. Duration: 3 seconds. COMPOSITION: asymmetric — forbidden: any centered or symmetric framing. One eye occupies the left two-thirds of frame. The other eye cut by the right frame edge — only the inner corner visible. Slight Dutch angle tilt. Lashes ice-crusted and heavy. Whites faintly red-veined from cold and wind. Main eye narrowed, gazing off-screen into far distance below frame. ACTION on twos: eyeball in micro left-right tracking movement — pause — pupils contract sharply — the instant of recognition — eyelids flutter slightly in two held frames — jaw corner tightens off-frame, visible only as a tension in the cheek — breath vapor drifts across the lower corner of frame, torn sideways by wind. Constant handheld micro-shake throughout. A rolling wave of buran briefly obscures the frame. Animated on twos. HARD CUT TO SHOT 2D — WIDE SHOT handheld — wolf pack as shadow mass — distance mode. Duration: approx. 8 seconds. COMPOSITION: asymmetric — forbidden: centered framing. Camera positioned within the tree line, offset to the left. Dense tree trunks occupy and crowd the right third of frame. Open space to the left. Depth axis shifted right, not centered. Wolf pack drives into frame from the lower right — mass heaviest on the right side, left edge showing only sparse fringe and trailing edge. THE PACK — approximately two hundred wolves. They do not exist as individual animals. NOT smoke, NOT mist, NOT vapor — the pack has mass, weight, and momentum. The entire pack moves as a single body of dark water surging downhill — liquid with density and pressure behind it, not diffuse or drifting. It is also shadow: it swallows light rather than reflects it, leaving a presence darker than everything around it in the flat grey-white atmosphere. Water and shadow — these two qualities together, never smoke. Movement pace: swift and relentless — faster than expected for something so massive, the speed of a flash flood or a river breaking its banks, not slow and rolling. The mass covers ground urgently, with weight and velocity combined. Mass density clearly differentiated: the core is near-opaque dense black like deep water — solid, heavy, light-swallowing — toward the edges it thins like water spreading at its margins, individual silhouettes briefly legible at the fringe then reabsorbed into the core. The edge is not soft or diffuse like smoke — it is the ragged turbulent edge of moving water. Large waves and small waves alternating with speed: heavy large waves surge and crest — small fast wave-crests explode between them. White teeth are the only thing in frame that does not belong to the shadow — solid, material, flashing simultaneously at multiple points as wave-crests break, then swallowed back. Skull outlines breach the surface and are pulled under like objects in fast current. Charcoal black with deep navy-blue sheen. Amber-yellow eye-points ignite in clusters in the darkness then extinguish in batches like bioluminescence in black water. Black water flood pours between the tree trunks — trunks submerged by black then re-emerging as the mass passes. Contrast: white blizzard / black wolf mass — white fear, black death. Camera near-still, breathing micro-shake only — as if the observer has instinctively stopped breathing. Animated on twos. Constraints: wolf pack is NEVER smoke, mist, or vapor — it has mass, weight, density, and speed — it is water and shadow. Wolf pack is NEVER a collection of individually animated animals — always a single fluid mass. DISTANCE MODE: mass coherence is absolute, individual wolves do not detach or become readable as separate figures. White teeth are the ONLY non-shadow element within the pack mass. Amber-yellow eye-points appear and extinguish in clusters, never individually. No warm light source anywhere in any frame. No rim light, no backlight, no moonlight — flat grey-white diffuse ambient only. No amber glow from forest reference applied. Camera handheld throughout — never stabilized, never smooth. Animated on twos throughout, no interpolation. 11 seconds total. 12fps. 8K. No music. SFX only. No subtitles. No 3D.

Latte

13,565 views • 2 months ago

Seedance 2.0 on FlovaAI =================== Prompt: [Reference Identity Lock] Image 1 is ONLY the main female protagonist. Her face, hairstyle, body type, and outfit must match Image 1 exactly and stay consistent for the entire video. Image 2 is ONLY a uniform reference. All four opponents wear the school uniform shown in Image 2. Never swap, merge, duplicate, or blend identities. The protagonist's identity comes ONLY from Image 1. The four opponents have NO reference images. They are defined by the text descriptions below. The four opponents must not resemble the protagonist, and they must not resemble each other. All five characters must remain clearly distinct and recognizable until the end. [Priority Order] 1. Preserve the protagonist's identity from Image 1. 2. Keep the four opponents visually distinct from her and from each other. 3. Maintain one continuous shot with no cuts. 4. Keep the classroom layout spatially consistent. 5. Make the action fast but readable and physically connected. 6. Keep the tone as a Korean school action drama, stylish but grounded. Korean school action drama classroom fight scene — 15 seconds, ONE CONTINUOUS SHOT, NO CUTS. A single uninterrupted handheld shot. No cuts, no scene transitions, no montage. The camera should feel handheld, with micro-jitters, slight rolling shutter, and raw unstable realism. The camera must physically travel through the same classroom space. Every transition must be motivated by camera movement, not editing. Whip pans are allowed, but they must not hide a cut. Do not teleport the camera or characters. The classroom layout and character positions must remain spatially consistent. Audio: No music. Only realistic school and classroom ambient sounds: old fluorescent light hum, distant hallway noise, ceiling fan, shoes scraping the floor, desks dragging, chair legs screeching, cloth friction, dull body impacts, and breathing that gradually becomes heavier. Breathing continues throughout the scene and keeps building. Lighting: Late afternoon in a Korean high school classroom. Mixed cool fluorescent light and warm sunlight through the windows. Dust floating in the sunlight. Soft fan shadows moving across desks and school uniforms. Main character: The Korean female high school student from Image 1, age 17–18. Cold, emotionless, calm, and intimidating. She barely speaks and does not scream during the fight. She remains composed from beginning to end. Her movements are efficient, explosive, and precise. Even if her frame is not large, she dominates through speed, timing, and accuracy. Main outfit: Exactly the outfit shown in Image 1. Do not change its colors, design, or details. Her jacket or outer layer is either removed and hanging on a chair, or worn in a slightly messy way. The action must be non-sexualized and combat-focused. Fabric movement, dust, sweat, wrinkles, and impact response should feel realistic. Opponent rules: Four Korean female high school students, all wearing the Hanlim Multi Art School uniform shown in Image 2. They have no reference images. Define them strictly by these descriptions and keep each one consistent: Opponent A: short black bob with straight bangs, medium build, round face. Opponent B: long straight hair tied in a high ponytail, tall and lean, sharp jawline. Opponent C: shoulder-length hair with side-swept bangs, slim build, narrow face. Opponent D: long wavy hair worn loose, slightly stocky and broad-shouldered. A, B, C, and D must each keep clearly different faces, hairstyles, body shapes, and silhouettes. They must not resemble the protagonist, and they must not resemble each other. No face duplication, no face merging, no identity confusion. Environment: An empty classroom at Hanlim Multi Art School, a Korean performing arts high school in Seoul. Green chalkboard, chalk tray, worn wooden desks, plastic chairs, classroom clock, class schedule poster, discipline/life-guidance posters, cleaning tools, blinds or curtains, wall study materials, and a slightly scuffed floor. Desks and chairs should react naturally to impacts, sliding, shaking, and collapsing when hit. Camera framing rules: Even during kicks, framing should stay around chest-level or eye-level. No low-angle shots under the skirt. Do not focus on legs, thighs, underwear, or fetish-like details. All action framing must prioritize faces, upper-body motion, impact, and spatial choreography. Continuous action and camera choreography: From 0 to 15 seconds, the fight continues without any cuts. The action should be stylish but readable, and every movement must be physically connected. 0–3s: The camera starts behind the protagonist at a slightly low handheld angle, drifting left through the classroom aisle. Opponent A grabs the protagonist's shoulder roughly and says in Korean: "야, 너 지금 뭐 하자는 거야?" The protagonist silently turns and lands one hard straight punch to A's face. At impact, use a very brief 15% slow motion: cheek ripple, dust particles, deep thud. A falls sideways into a desk. The camera dips slightly from the shock, then whip-pans right without cutting. 3–6s: Opponent B charges in from the right. The protagonist steps forward instead of retreating. A short body shot to the stomach. Immediate uppercut to the chin. Without pausing, she drives forward into a flying knee to B's chest. B is thrown backward across or into a desk. The camera follows the forward motion low, then rebounds upward with the impact. 6–9s: Opponent D attacks with two fast punches. The protagonist deflects both strikes with her arms, then flows into a turning backfist to D's face. As D staggers, she continues the same rotation into a spinning back elbow that lands hard on D's jaw or temple. D crashes sideways into two or three desks. The camera arcs around her shoulder and jitters slightly at each impact. No cuts. 9–12s: Opponent C rushes in from the chalkboard side. The protagonist clearly grabs C's collar with her left hand. C's face must be fully visible from the front and clearly different from the protagonist. The protagonist lands one short, hard punch to C's face, then immediately throws a powerful high kick or flying high kick into C's chest. The force sends C backward into the green chalkboard. The protagonist remains in the foreground and never touches the board. The protagonist's face should be side-profile or partially obscured. C's face should be clearly visible from the front at the moment of impact. Their faces must never overlap in frame. Use a very brief 20% slow motion at the chalkboard impact: chalk dust bursts outward, and C slides down the board. The camera pushes up with the impact, then tilts down as C slides. 12–15s: Through the chalk dust, the camera hard-pans right. D makes one final charge. The protagonist sidesteps and lands a tight uppercut to D's chin, followed immediately by a cross. D crashes into a row of desks, causing a chain reaction of collapsing desks and chairs. The camera drifts forward slowly. The protagonist adjusts her loose tie or ribbon and brushes chalk dust off her shoulder. Her expression stays cold and serious. She walks past the camera and exits the frame. Dust floats in the sunlight. Natural ending. =================== Made with Flova #FlovaAI #FlovaCPP

TSUBAKI

19,474 views • 2 months ago

Seedance 2.0 on Higgsfield AI delivers some of the best camera motion, consistency, and creative control I've seen in AI video generation. Full Open-sourced prompts & assets below: SCENE CONTEXT A bright summer afternoon on the coastal road: the young man drives the mint scooter down toward the sea with the young woman riding behind him, arms around his waist — an easy, happy ride past the railway crossing along the water. ACTIVE REFERENCES >> — young woman, 20 years old, 165 cm tall, slender, straight dark brown hair with side-swept bangs pinned by a small black clip, freckles across her cheeks and nose. 100% matches the reference. >> — young man, 22 years old, 178 cm tall, lean, sun-tanned, messy dark hair under a tan baseball cap worn backwards. 100% matches the reference. >> — vehicle: vintage mint-green scooter with a brown leather saddle, chrome mirrors and silver wheels. 100% matches the reference. >> — location: coastal road curving downhill past a railway crossing with yellow-and-black crossbuck signs, utility poles and wires, stone embankment walls, an orange convex traffic mirror on a pole, the open sea with white-capped waves behind. LOCATION MAP The road from >> curves downhill through the midground toward the railway crossing, the sea filling the background beyond it. Stone embankments rise on both sides, the orange convex mirror stands on the right shoulder in the near foreground, utility poles line the curve. Their path: down the curve, past the crossing, along the water toward screen-left. Primary light: bright seaside daylight, sun high, wind off the sea. FIRST FRAME AND SPATIAL BLOCKING The first visible frame already contains >> rolling down the curve with both riders aboard — >> driving, hands on the grips, >> seated close behind him, arms wrapped around his waist, her head just above his shoulder, a full head shorter than him. No empty establishing frame, no delayed reveal. He drives in every segment; she is always the passenger. FORMAT MODE Controlled four-segment multi-shot sequence: one INSERT CUT and two HARD CUTS. Real-time motion at an easy unhurried scooter pace. Every segment is shot handheld — no static shot anywhere in the sequence. OPTICS LENS LOCK SEGMENT 1 = 47° diagonal field of view, standard normal lens character, camera 12 to 15 meters at the roadside, the scooter and both riders full in frame with the crossing and sea behind, straight lines rectilinear, no fisheye. Soft vintage lens rendering: gentle edge softness, mild halation in the bright sky and sea glare, even brightness across the whole frame — no vignette, corners stay as bright as the center. This rendering applies to every segment. LENS LOCK SEGMENT 2 = 29° diagonal field of view, short telephoto character, camera 3 to 4 meters tracking alongside from a following vehicle, close two-shot of their faces and shoulders, the sea streaming soft behind them. LENS LOCK SEGMENT 3 = 29°, camera 1.5 to 2 meters, tight insert on her hands clasped at his stomach, the mint body and brown saddle below, road surface blurring past. LENS LOCK SEGMENT 4 = 47°, camera 10 to 12 meters behind the orange convex mirror on the right shoulder, the mirror large in the near foreground reflecting the road, the real scooter passing through the frame and receding along the sea. No drift mid-segment. CAMERA Handheld in every segment with no exceptions — a real operator at the roadside and in a following vehicle: the frame breathes with shoulder sway and soft micro-tremor visible in every second, small late reframes chasing the scooter and easing back; the tracking shot carries gentle road vibration on top of the hand movement; the insert trembles slightly more; the mirror wide breathes slower but never freezes. No tripod stillness, no gimbal smoothness, no stabilization anywhere. On top, the footage behaves like an old film print running through a projector: constant subtle gate weave, faint exposure flicker, occasional tiny dust specks and hairline scratches, image soft and slightly diffused like an aged 16mm print — never sharp, never digitally clean, no vignette or darkened corners at any moment. ACTION TIMING 0.0s to 3.5s — Roadside wide: the mint scooter putters down the curve at an easy pace, leaning gently with the bend; >> relaxed at the grips, >> pressed close behind him, her hair and skirt hem streaming in the sea wind; they pass the yellow-and-black crossing signs with the white-capped sea glittering beyond. 3.5s HARD CUT 3.5s to 6.5s — Tracking close two-shot: she rests her chin almost on his shoulder and says something teasing into his ear — lips moving without audible words; he barks a laugh, shaking his head, cap holding snug; she grins wide against the wind, bangs whipping, eyes squinting happily. 6.5s INSERT CUT 6.5s to 8.5s — Tight insert: her hands clasped over his stomach, fingers laced, giving a little squeeze as the scooter sways through a bend; the mint body flexes light reflections, the road surface streams underneath in soft blur. 8.5s HARD CUT 8.5s to 12.0s — Wide past the orange convex mirror: the tiny reflection of the scooter slides across the round mirror in the foreground a beat before the real scooter enters and crosses the frame, unhurried, the two of them small against the vast bright sea; she tips her head back and laughs into the wind as they recede along the coast; the engine putter fades. PHYSICS The scooter carries real combined weight: soft suspension compression over road seams, a gentle lean into each bend with both bodies tilting as one, slight throttle sway she counterbalances by gripping tighter; engine vibration trembles through their sleeves; wind at riding speed streams her hair, his tee and her skirt hem backward continuously with fabric flutter; the sea wind adds gusts; the convex mirror reflection tracks their motion with true optics. LIGHTING Bright seaside daylight only — no artificial light. Aged film print look: the sky and the glittering sea bloom into a soft white-gold haze with visible halation rings, gentle glow hanging in the air, creamy highlights rolling off softly. Faded pastel grade of an old print: lifted milky blacks, warm ivory and honey tones over softened sea blues, the mint scooter body reading as a gentle washed pastel green, the orange mirror and yellow-black signs as warm muted accents — never oversaturated; slightly yellowed whites, low contrast, colors gently washed as if the print has aged for twenty years, heavy visible film grain crawling in every frame, delicate haze. Exposure stays natural across the frame — no added vignette, no darkened edges or corners. The whole image reads as an old 2000s Japanese film discovered on a dusty reel. No crisp modern digital look, no cool color cast. AUDIO SFX only, with the worn texture of an old optical soundtrack — slightly muffled, faint constant hiss: the soft putter of the small scooter engine rising and fading with the throttle, wind buffeting past, waves breaking below the road, gull cries, her bright laugh snatched by the wind, the faint tick of the engine at the far end. No music, no intelligible spoken words, no captions, no score. POSITIVE LOCKS Identities lock 100% to >> and >> in every segment — same outfits as their references throughout, her natural 165 cm and his 178 cm with true relative proportions, his cap staying backwards and snug at riding speed in every shot. >> drives in every segment; >> rides pillion with her arms around his waist from first frame to last, hands unclasping never. The scooter stays 100% >> — mint-green body, brown saddle, chrome mirrors — in every shot. Road geography stays consistent with >> across all cuts: downhill curve, crossing signs, embankments, orange mirror on the right shoulder, sea always beyond the road; travel direction constant toward screen-left. Handheld breathing holds in every single segment, and the aged-film texture holds identically throughout: grain, gate weave, flicker, dust, halation and faded grade never weaken, frame stays vignette-free with even corner brightness; no segment turns rigid, stabilized, sharp or digitally clean. Only these two people appear; the road stays otherwise empty, no cars, no train.

WasifAI

17,571 views • 2 months ago

Hailuo MiniMax H3 vs. Seedance 2.0 Experimented more for comparisons, i am loving MiniMax H3. 2K resolution videos for 4 times cheaper than seedance 2.0 is too hot to resist. Thank you Hailuo AI (MiniMax) for making it easier to creators. Its not just cheap, in some cases it is also performing way better than seedance 2.0 in terms of visuals and framing. One example is given below. Used same Text to Video Prompt Prompt: Create a 15-second photorealistic cinematic dark-fantasy sequence in 16:9 widescreen. The video must contain exactly three clearly separated cinematic shots connected by clean hard cuts. No dissolves, morphing transitions or continuous camera orbit. MASTER DRAGON LOCK: Show one enormous ancient dragon with a broad powerful body, charcoal-black overlapping scales, subtle dark crimson colouring across its head and neck, two swept-back horns, smaller facial spikes, glowing amber-orange eyes, one long tail and one pair of enormous bat-like wings with dark leathery membranes. The dragon has four legs: two forelegs and two hind legs. Its design, size, horns, colour, anatomy and facial structure remain identical in all three shots. The dragon must feel extremely heavy, ancient and physically realistic. MASTER RIDER LOCK: One adult armoured rider is already seated securely in a dark leather saddle on the dragon from the very first frame. The rider wears detailed weathered silver plate armour, dark under-clothing, a fitted medieval helmet with a narrow shadowed visor and a long dark cloak. The rider’s face is never clearly visible. The rider holds leather reins connected to the saddle and remains seated throughout the entire sequence. The rider does not suddenly appear, mount, dismount or change clothing. During the first shot, the rider is naturally hidden behind the dragon’s large head, neck and folded wings. ENVIRONMENT AND LIGHTING: The sequence takes place inside a gigantic ancient mountain cave. The cave contains rough black rock walls, enormous stone formations, drifting mist, scattered bones and faint glowing embers between cracks in the ground. The far interior is almost black, but the dragon must remain readable through soft amber reflections and cold blue rim light entering from the cave mouth. The cave entrance opens from a high mountain cliff into a vast dramatic landscape of jagged mountains, deep valleys, distant waterfalls, rolling clouds and pale stormy daylight. Maintain a cinematic cold-blue and muted-amber colour palette with deep shadows, volumetric light rays and realistic atmospheric haze. Dark and mysterious, but never so underexposed that the dragon or rider becomes blurry or invisible. SHOT 1 — DRAGON EMERGES, 0–5 SECONDS: Begin with a symmetrical low frontal wide shot positioned near the cave entrance, facing deep into the darkness. The camera slowly tracks backward toward the entrance as the enormous dragon walks forward out of the black cave interior. The dragon’s wings remain completely folded against both sides of its body. Its glowing amber eyes appear first, followed by its horned head, shoulders and powerful forelegs becoming visible through the mist. Each heavy footstep shakes the cave floor and dislodges small stones and dust from the ceiling. The dragon exhales dense vapour from its nostrils and releases a deep restrained growl. Its head moves naturally with the weight of each step. The dragon looks directly past the camera toward the cave opening. The rider is already seated but remains hidden behind the dragon’s head and neck. Do not reveal the rider clearly during this shot. SHOT 2 — RIDER REVEAL, 5–9 SECONDS: Clean hard cut to a low three-quarter side tracking shot beside the moving dragon. Begin close to the dragon’s horned head and sharply detailed scales. Track smoothly backward along the dragon’s neck and folded wing while the dragon continues walking toward the cave entrance. As the camera reaches the dragon’s shoulder, reveal the single armoured rider seated in the saddle between the folded wings. Hold the composition long enough to clearly show the rider’s silver armour, helmet, dark cloak and both hands gripping the reins. The rider looks toward the bright cave exit and leans slightly forward in preparation for takeoff. The dragon and rider remain in continuous forward motion. Do not show a separate rider anywhere else in the cave. SHOT 3 — REAR TAKEOFF AND FLIGHT, 9–15 SECONDS: Clean hard cut to an epic wide rear view positioned behind and slightly above the dragon and rider. The bright cave mouth and vast mountain landscape fill the background ahead of them. The dragon accelerates into a powerful run toward the cave opening while its wings remain folded enough to pass safely through the cave. The dragon reaches the cliff edge and makes one forceful leap completely out of the cave. Only after clearing the rock opening, it spreads both enormous wings to their full symmetrical width. The sudden wing expansion pushes mist, dust and loose stones outward from the cave entrance. The rider leans forward, grips the reins and remains firmly attached to the saddle. The dragon performs one enormous downward wingbeat, catches the air and transitions naturally into stable forward flight. Loose stones fall from the cliff beneath it. The camera rapidly follows from behind as the dragon and rider soar away over the deep valley between jagged mountain peaks. The long tail streams naturally behind the dragon and the rider’s cloak whips in the wind. End on a majestic wide rear silhouette of the dragon flying into the open mountain landscape as sunlight breaks through the storm clouds. CAMERA AND MOTION: Premium cinematic camera movement with realistic scale and parallax. Shot one is a controlled backward dolly. Shot two is a smooth low side-tracking reveal. Shot three is a dynamic rear pursuit shot that follows the takeoff out of the cave. Use natural motion blur only during the leap and wingbeat. Keep the dragon’s movement heavy on the ground and powerful but graceful in the air. No shaky chaotic framing and no extreme close-ups that obscure the action. CINEMATIC QUALITY: Big-budget photorealistic dark-fantasy visual effects, highly detailed scales and armour, realistic creature muscles beneath the skin, physically accurate wing membranes, believable foot contact, convincing dust and falling-rock physics, volumetric cave mist, dramatic rim lighting, strong depth, atmospheric perspective and stable character consistency. AUDIO: No dialogue and no music. Deep dragon breathing, restrained growl, heavy echoing footsteps, claws scraping stone, armour movement, leather saddle creaking, falling pebbles, rushing cave wind, powerful wingbeat and a deep dragon roar as it enters open air. STRICT CONSISTENCY: Exactly one dragon and one rider. The rider is seated on the dragon from the beginning and never disappears. No additional people, dragons or creatures. No dragon transformation or colour change. No extra heads, horns, tails, wings, legs or riders. The wings remain folded inside the cave and open only after the dragon has completely cleared the cave mouth. The wings must not clip through the cave walls. The rider must not float above the saddle or merge into the dragon. No fire breathing, combat, dialogue, text, logos, blood or visible injuries.

MadMax

13,880 views • 1 month ago

PROMPT: Generate a continuous 15-second premium live-action broadcast TV commercial for a high-performance family kitchen blender, designed as an energetic, polished consumer-appliance advertisement emphasizing FAST BLENDING POWER. The commercial must tell a complete miniature visual story within exactly 15 seconds: a busy family needs breakfast quickly, fresh ingredients enter the blender, one touch unleashes powerful high-speed blending, a thick mixture transforms almost instantly into a perfectly smooth fruit smoothie, the family enjoys the result, and the commercial ends on a clean hero product shot with the promise: “Smooth in Seconds.” Maintain a consistent high-end contemporary commercial visual style throughout the entire sequence: photorealistic food photography, tactile ingredient detail, premium appliance surfaces, energetic but controlled camera movement, crisp natural highlights, appetizing freshness, believable family warmth, and polished broadcast-advertising finish. Shoot as if captured on an ARRI Alexa 35 cinema camera using a coordinated set of 24mm, 35mm, 50mm, 85mm, and 100mm macro cinema lenses. Preserve realistic perspective, physically plausible motion, natural depth of field, smooth highlight roll-off, subtle cinematic contrast, clean skin tones, rich food texture, controlled motion blur, and sharp product detail. The entire commercial takes place during one continuous bright weekday morning in the SAME modern family kitchen. The kitchen has warm off-white cabinetry, pale natural-oak counters, a large sunlit window frame-left, brushed stainless-steel fixtures, a small breakfast table in the background, subtle family-life details, and a clean uncluttered countertop. Warm morning sunlight enters consistently from frame-left at approximately 5200K, supplemented by soft interior fill, producing gentle directional shadows and bright natural reflections. Maintain the same architecture, counter layout, window position, furniture, appliances, background objects, lighting direction, and color palette throughout every shot. New camera angles reveal different perspectives of the same physical kitchen and must never create a different-looking location. LOCKED PRODUCT: one premium family countertop blender with a compact matte-silver motor base, black control panel, one illuminated circular speed control, large clear 1.8-liter blending pitcher, black fitted lid, stainless-steel blade assembly, sturdy black handle, and subtle unbranded front badge area. The blender’s shape, proportions, materials, controls, pitcher geometry, lid, handle, blade assembly, reflections, scale, and countertop position remain identical throughout every shot. It begins centered on the main kitchen counter and never changes location. LOCKED INGREDIENTS: fresh strawberries, banana pieces, blueberries, mango chunks, Greek yogurt, milk, and several ice cubes. Ingredients must retain recognizable colors and textures before entering the pitcher. Once added, object permanence must be respected: ingredients cannot reappear outside the blender. During blending, the mixture must transform physically and continuously from visibly chunky fruit and ice into a uniform thick pink-red smoothie. LOCKED FAMILY: a mother in her mid-30s with shoulder-length dark brown hair wearing a soft beige knit top and blue jeans; a father in his late-30s with short dark hair wearing a pale blue casual shirt; an approximately eight-year-old daughter with dark brown hair in a ponytail wearing a muted yellow T-shirt; and an approximately six-year-old son with short brown hair wearing a light green T-shirt. Preserve their exact ages, facial identity, hairstyle, wardrobe, body proportions, and appearance whenever visible. Their expressions progress naturally from hurried anticipation to impressed surprise to relaxed enjoyment. Avoid surreal food behavior, floating ingredients, impossible liquid physics, teleporting objects, changing blender geometry, inconsistent pitcher fill levels, duplicated fruit, warped hands, extra fingers, changing wardrobe, altered kitchen architecture, random background changes, excessive lens distortion, unreadable product geometry, fake plastic food textures, excessive camera shake, oversaturated grading, artificial CGI appearance, flickering light, exposure shifts, continuity resets, jumpy object positions, text artifacts, random labels, logos, watermarks, or unrelated products. 00:00–00:02.0 — OPENING PROBLEM / FAMILY MORNING RUSH. Begin with a dynamic 24mm wide establishing shot from approximately countertop height, looking diagonally across the kitchen while preserving a left-to-right spatial axis. The mother moves briskly toward the counter from frame-left as the two children wait near the breakfast area in the background, visibly eager and short on time. The father passes behind them preparing to leave. Morning sunlight streaks naturally through the frame-left window. The locked blender is already visible on the counter as the visual anchor, positioned prominently but naturally in the foreground-right. Use a smooth fast dolly-in toward the blender rather than a hard zoom. Small breakfast details suggest a busy school morning without cluttering the frame. Sound begins with subtle morning kitchen ambience, quick footsteps, a chair movement, and upbeat rhythmic music immediately establishing urgency. No spoken dialogue. 00:02.0–00:04.0 — INGREDIENT SPEED MONTAGE. Match-cut into a rapid sequence of three extremely concise food-preparation inserts totaling exactly two seconds. First, a 100mm macro close-up catches vivid strawberries and blueberries dropping into the clear pitcher, with realistic gravity, bounce, moisture, and fruit texture. Cut to banana pieces and mango chunks entering from above, maintaining the exact pitcher position and increasing fill level logically. Cut to a tight side insert as Greek yogurt, milk, and ice cubes enter last. Use crisp impact sounds synchronized with each ingredient: thump, splash, clink. Each insert changes visual information and advances the preparation; never repeat the same composition. Camera movement is minimal and precise so the speed comes primarily from editorial cutting. The blender remains OFF throughout these inserts. 00:04.0–00:05.2 — ONE-TOUCH ACTIVATION. Cut to an 85mm close-up from a low three-quarter front angle of the blender control panel. The mother’s right index finger enters naturally from frame-left and presses the illuminated circular control exactly once. Show believable fingertip compression against the control. The instant contact occurs, the control illumination brightens and the motor begins. Add a precise tactile click followed immediately by a confident rising electric motor sound. Use a subtle fast push-in timed to activation. The hand exits naturally; do not show multiple presses. 00:05.2–00:08.2 — POWER DEMONSTRATION / HERO BLENDING MOMENT. Cut to a dramatic but physically realistic 50mm close three-quarter view of the entire pitcher. The motor accelerates rapidly. Ice cubes and fruit initially tumble downward toward the stainless-steel blades, then form a powerful controlled vortex. Show the transformation continuously: recognizable strawberries, blueberries, banana, mango, yogurt, milk, and ice become progressively smaller and more integrated until the mixture turns into a completely smooth, thick pink-red smoothie. The action must communicate exceptional blending speed without supernatural physics. Condensation begins subtly on the outside of the pitcher. Tiny droplets and believable internal turbulence catch the frame-left morning light. During this three-second power demonstration, execute a controlled semicircular camera move of approximately 35 degrees around the front of the blender without crossing the established spatial axis. Begin slightly frame-left of the product and finish near frontal three-quarter. Maintain the blender base completely stable on the countertop with no unrealistic vibration or sliding. Use one brief 100mm macro insert lasting approximately 0.5 seconds to reveal the high-speed vortex and disappearing final fruit fragment, then return immediately to the matching three-quarter product angle. Sound design intensifies with a strong smooth motor whirr synchronized to the vortex, layered with the upbeat music. At approximately 00:07.6, the last visible fruit fragment disappears into the vortex. By 00:08.2 the mixture is visibly uniform, silky, and completely smooth. This transformation is the commercial’s core proof point: FAST BLENDING POWER. 00:08.2–00:09.5 — INSTANT RESULT. The motor stops cleanly. Cut to a 100mm macro beauty shot looking through the clear pitcher wall at the perfectly smooth smoothie surface settling from a gentle spiral into a glossy, uniform texture. A small central swirl collapses naturally. No chunks remain. Condensation beads on the exterior catch bright highlights. Use shallow depth of field while retaining enough pitcher edge detail to identify the product. Sound drops from the motor into a satisfying soft stop, followed by a subtle musical accent. A confident female voice-over begins: “Powerful blending…” 00:09.5–00:11.5 — POUR AND PROOF. Match the circular smoothie motion into a 50mm close-up of the mother tilting the same pitcher and pouring the thick smoothie into two clear family drinking glasses on the same countertop. The liquid forms a smooth continuous ribbon with realistic viscosity and no splashing errors. The pitcher’s remaining fill level decreases correctly. Camera tracks gently with the pour from left to right. The daughter and son appear softly out of focus beyond the glasses, watching with excited expressions. As the glasses fill, rack focus briefly from the flowing smoothie to the children’s delighted reaction. Voice-over completes: “…smooth results in seconds.” 00:11.5–00:13.0 — FAMILY PAYOFF. Cut to a warm 35mm medium shot at the breakfast counter. The two children each take one synchronized first sip from their filled glasses, then immediately exchange impressed smiles. The mother stands behind them with a relaxed satisfied expression while the father takes a filled travel cup and moves toward frame-right, suggesting the blender has saved valuable morning time. Keep performances natural rather than exaggerated. The blender remains visible in the background on its original counter position, recognizable and unchanged. Morning sunlight and the same warm neutral palette continue without variation. The music opens into a bright satisfying resolution. The daughter gives a quick authentic smile and says: “That was fast!” 00:13.0–00:15.0 — PRODUCT HERO / BRAND END FRAME. Use a clean visual match cut from the child’s smoothie glass to the locked blender standing alone in a polished hero composition on the SAME kitchen counter. Shoot on an 85mm lens at slightly below pitcher midpoint for a confident premium product perspective. The blender occupies the center-right of frame while a freshly poured smoothie glass, two strawberries, several blueberries, and one mango slice form a restrained ingredient arrangement in the lower foreground-left. These garnish ingredients are separate presentation ingredients introduced only for the hero composition and must not imply that previously blended ingredients have magically reappeared. Create a slow controlled 5% push-in during the final two seconds. Frame-left morning sunlight creates a clean edge highlight along the clear pitcher and matte-silver motor base. Maintain realistic reflections, exact product geometry, and crisp separation from the softly defocused kitchen background. At 00:13.3, introduce a clean broadcast-safe text overlay in the negative space on frame-left: “FAST BLENDING POWER” At 00:14.0, transition cleanly to the primary campaign line: “SMOOTH IN SECONDS.” Below it, smaller: “POWER FOR EVERY FAMILY MORNING.” Typography is modern, bold, minimal sans-serif, perfectly legible, horizontally aligned, broadcast-safe, with no distorted letters and no unnecessary graphical effects. Keep all typography outside the physical blender silhouette. Voice-over, confident and warm: “Fast power. Smooth mornings.” End exactly at 00:15.0 on a perfectly stable hero frame with the blender sharply resolved, smoothie glass visible, campaign line readable, music landing on a clean sonic logo accent. CAMERA AND EDITING RULES: Use motivated cuts whenever subject, visual information, camera position, action, or emotional emphasis changes. Maintain energetic medium-fast commercial pacing: wider contextual opening, rapid ingredient inserts, tactile activation close-up, high-energy blending demonstration, sensory result macro, fluid pouring shot, human reaction payoff, then a slower premium hero landing. Preserve the established 180-degree axis throughout. No camera crosses the axis unless visibly motivated, and no silent changes in object placement occur between cuts. Maintain consistent camera height for matching shot types. Screen direction remains left-to-right for preparation and family movement. Every shot must introduce new action, information, perspective, reaction, or product proof. AUDIO DESIGN: Begin with subtle morning kitchen ambience under upbeat modern percussive music. Synchronize fruit impacts, ice clinks, control click, motor acceleration, vortex intensity, motor stop, smoothie pour, drinking sounds, and final sonic logo precisely to picture. The blender motor must sound powerful but refined rather than harsh. Duck music naturally beneath the voice-over and daughter’s dialogue. No audio clipping or abrupt ambience resets between cuts. VISUAL COLOR SYSTEM: warm off-white, pale natural oak, matte silver, fresh strawberry red, blueberry blue, mango golden-yellow, and creamy smoothie pink-red. Preserve natural skin tones and realistic food saturation. Use a premium contemporary commercial grade with moderate contrast, soft highlight roll-off, clean whites, controlled blacks, and no teal-orange exaggeration. MOVEMENT AND PHYSICS: All hands interact correctly with objects. Ingredients obey gravity. Liquid volume remains continuous. The pitcher fill level increases when ingredients are added, decreases when smoothie is poured, and never resets between shots. The blender stays physically planted on the counter during operation. The motor vortex follows plausible fluid dynamics. Hair, clothing, reflections, condensation, shadows, and liquid motion react naturally. Maintain strict character consistency, product consistency, object permanence, environment continuity, lighting continuity, and forward-only time progression across the full sequence. Render the final commercial at 24 fps, 16:9 broadcast aspect ratio, UHD 3840×2160 resolution, high-bitrate cinematic master quality, natural 180-degree shutter motion blur, realistic cinema-lens behavior, subtle fine sensor texture, clean compression, no visible digital artifacts, no temporal flicker, no frame interpolation artifacts, and photorealistic high-end commercial rendering. Preserve sharp product edges and legible end-frame typography while allowing natural depth-of-field falloff. The entire finished sequence must be EXACTLY 15 seconds long. Do not extend or shorten any beat. The central visual message must be immediately understandable without dialogue: a busy family morning becomes easier because this family blender turns whole ingredients and ice into a perfectly smooth drink with exceptional speed. The emotional progression is urgency → activation → power → instant proof → family satisfaction → premium product promise. Final audience takeaway: FAST BLENDING POWER. SMOOTH IN SECONDS.

Gumvue Studio

20,808 views • 2 months ago

Seedance 2.0 on Higgsfield AI The visual fidelity and scene consistency bring this pirate adventure to life like never before.Every cut feels intentional immersive and ready for the big screen. Full open sourced prompts & assets below: SCENE CONTEXT Bright day at sea aboard a sailing galleon. Captain Eduardo bursts out of the sterncastle door onto the deck; his scarlet macaw lands on his LEFT shoulder mid-stride. He runs up to the quarterdeck where a lookout crewman watches the horizon through a brass spyglass, takes the spyglass and looks himself: a distant island, and a violent optical crash zoom finds a small futuristic hard case on the beach. Then a second crewman runs up, grabs his arm and points the OTHER way, astern — Eduardo turns: a black-sailed pirate ship very far behind them, a speck on the horizon. He does not raise the spyglass — he just stands and stares at the distant black sails, holding the look. ACTIVE REFERENCES >> — lean pirate captain, dark curly hair falling free from under a dusty mustard-yellow cloth bandana, a small white shark tooth pinned to the front of the bandana above his temple, thin moustache, gold hoop earrings, cream linen shirt under a worn brown leather waistcoat, cloth sash and leather belts. 100% matches the reference; studio sheet layout NOT inherited. >> — scarlet macaw, red body, blue-and-yellow wing feathers, small leather shoulder harness. 100% matches the reference; it flies in and rides Eduardo's left shoulder. >> — weathered pirate crewmen from the reference group (bandana, rough shirt, vest). 100% match the reference; TWO of them appear: the lookout at the quarterdeck rail, and a second runner who arrives in CUT 4 pointing astern. >> — collapsible brass spyglass with dark leather-wrapped barrel sections. 100% matches the reference; starts in the lookout's hands, ends at Eduardo's eye. >> — Eduardo's galleon: pale square sails, tall wooden sterncastle, raised quarterdeck. 100% matches the reference; controls hull, deck, masts and rigging only. >> — calm bright sea, glittering sun path, hazy horizon. Controls water and sky atmosphere only. >> — small lone island: dense dark-green jungle cover, a curved white-sand beach on one side, grey rocky cliff edges, turquoise shallows ringing the shore. 100% matches the reference; it is the island seen on the horizon and inside the spyglass view. >> — small futuristic hard case: matte-black armored corners, neon acid-green side panels, brushed-steel top plate with a glowing green star-shaped button. 100% matches the reference; it appears ONLY inside the zoomed spyglass view of CUT 3, lying on the beach. >> — enemy pirate galleon: black sails, acid-green skull-and-crossed-swords on the mainsail, dark carved hull. 100% matches the reference; revealed VERY far astern in CUT 4 as a tiny silhouette on the horizon — never seen closer in this beat. LOCATION MAP >> under sail on >>, open bright sea. The sterncastle door opens onto the main deck; a short wooden stair leads up to the quarterdeck at the stern. The lookout stands at the quarterdeck rail on the forward side, spyglass raised toward the horizon screen-right. Far on that horizon, 2–3 km out: >> — dense green jungle mass, the white-sand beach catching the sun on its near side, turquoise water at its shore. In the OPPOSITE direction, astern of the ship screen-left: open sea where >> rides VERY FAR OFF — 4–5 km out, right on the horizon line, a tiny dark silhouette almost dissolved in the haze — present in the world from the start, revealed to the camera only in CUT 4. Haze visible at the horizon distance. Sun high, sea glitter everywhere. FIRST FRAME / BLOCKING First frame: the sterncastle door already swinging open, >> mid-stride through it onto the deck, body angled toward the quarterdeck stair screen-right. Crew activity in the background of the deck. The lookout is visible up on the quarterdeck at the rail, spyglass already at his eye, pointed screen-right toward the horizon. FORMAT MODE Sequence of cuts, no timecodes — cuts only at the specified points, the camera does not cut on its own. CUT 1 — 63° handheld follow: the door bursts open, Eduardo comes out in a strange hurried scurry — up on TIPTOE, quick tiny mincing steps, both arms half-raised in front of him with elbows out, hands hovering at chest height, shoulders slightly hunched — comically odd, but FAST, covering the deck at 10 km/h. >> sweeps in from off-frame upper-right, wings braking, and lands on his left shoulder without breaking the scurry. He tiptoe-rushes across the deck and up the quarterdeck stair; the camera chases behind-left, half a beat late. CUT 2 — MS, 47°, on the quarterdeck: the lookout at the rail with >> raised. Eduardo arrives frame-left, the scarlet macaw >> sitting clearly visible ON HIS LEFT SHOULDER through the whole cut. With his RIGHT hand he grabs the spyglass out of the lookout's hands in one firm motion and raises it right-handed to his RIGHT eye toward the horizon screen-right, left eye squeezing shut. The lookout yields a step. CUT 3 — SPYGLASS POV, MONOCULAR: one single round image — the view through ONE lens of a telescope, a single circle centered in frame, black around it. This is a one-eyed spyglass view, never the twin overlapping circles of binoculars. Extreme telephoto image swaying with a hand-held tremor, compressed haze layers stacking toward the island. Distant >> sits small in the circle: dark-green jungle, the curved white-sand beach, turquoise shallows, heat haze. Hold 1 second — then a RAPID CRASH ZOOM, one continuous accelerating optical dive down to the waterline of the beach: >> lying on the wet sand, black-and-acid-green case, steel top plate, green star button glinting. The zoom lands and locks on the case filling half the circle. Hold. CUT 4 — MS, 47°: Eduardo lowering the spyglass, macaw on his left shoulder — a second crewman from >> runs into frame from screen-left, grabs Eduardo's arm and jabs his finger the OTHER way, astern, screen-left, shouting over the wind: "CAP'N! BEHIND US!" — and the macaw on Eduardo's shoulder instantly screams it back in a harsh parrot voice: "BEHIND US! BEHIND US!", wings half-flaring. Eduardo whips around following the point; the camera racks past his shoulder — REVEAL deep in the frame: >> VERY far astern, a TINY black silhouette sitting right on the horizon line — smaller in the frame than Eduardo's fist, under 5% of the frame height, barely bigger than a speck, half-swallowed by haze — but the black sails read unmistakably. Vast empty water fills everything between the rail and that distant speck. Eduardo does NOT raise the spyglass — it stays lowered in his right hand. He simply STANDS and STARES at the tiny black sails, motionless, eyes locked on the horizon. The cut ends on his long look toward the enemy ship against the empty sea. OPTICS CUT 1: 63° observational wide, handheld. CUT 2: 47° neutral. CUT 3: monocular spyglass optics — ONE single circular image (a one-lens telescope, never the twin circles of binoculars), tele compression as at 8°, soft edge inside the circle; the crash zoom is purely optical, horizon compressing, haze layers stacking. CUT 4: 47° neutral with a rack to the deep background on the reveal, then holding on Eduardo's profile against the horizon. No drift mid-segment. CAMERA Handheld operator character throughout the real-world cuts: chases the run at deck level in CUT 1 with visible footstep energy, settles to a 1–2 cm breath on the quarterdeck. Camera stays on the shadow side of Eduardo, sun working across from screen-right. The POV cut carries a hand-tremor sway of 1–2 cm that calms when the zoom locks on the case. ACTION Door kicks open from inside. Eduardo's gait in CUT 1 is deliberately odd: he rushes on the balls of his feet, heels never touching the planks, tiny fast tiptoe steps, arms half-raised with hands floating in front of his chest — hurried and urgent, never slow, sash swaying with the quick mincing rhythm, boot toes tapping the deck. The macaw's landing is physical: wings flare to brake, claws grip the leather waistcoat's shoulder, one small balance flap as he keeps scurrying. The spyglass handover is brisk, captain's-right, two hands to one. In the POV the island rises gently with the ship's sway until the crash zoom pins the case. PERFORMANCE Urgency without panic: breath fast through the nose, eyes fixed forward during the run. At the eyepiece his face stills completely — squint tightens, lips part a fraction when the case appears. In CUT 4 the runner's grip snaps him out of it — head whip, eyes refocusing to the far black sails — then he goes still: eyes fixed on the distant ship, a slow exhale, jaw tightening a fraction — the look held long, unreadable, no words at all. Pore-level skin realism, sun catch-lights, spray-damp sheen on the temples. PHYSICS Ship heels gently on a calm swell; rigging sways against the sky. The parrot has real bird mass — landing compresses the shoulder slightly. Cloth reacts to the run wind. In the POV, heat haze wobbles the island image and glitter fires irregularly off the water; the case sits with real weight in the wet sand, a shallow water film sliding around its base. LIGHTING High bright sun, 5600K daylight, hard key from screen-right with sea-bounce fill from below. Deck in full sun, crisp short shadows. Inside the spyglass POV the image is brighter and milkier — long air column, haze density rising toward the horizon; the case's acid-green panels and glowing star button read as the only saturated color on the pale beach. AUDIO Wind over the deck, sails snapping, boots on planks, macaw squawk on landing, gulls distant. On the POV: the world's sound thins to wind and a faint ring of focus. On the crash zoom a low whoosh rising in pitch, landing on near-silence with only the surf of the far beach, thin and distant. CUT 4: deck sound returns — running boots, the crewman's urgent shout over the wind: "CAP'N! BEHIND US!", answered at once by the macaw's harsh screeching echo: "BEHIND US! BEHIND US!" — then only the wind, a slow exhale, and the creak of the deck. No spoken line from Eduardo. STYLE Photoreal live-action, bright maritime daylight, fine film grain, crisp highlights with gentle roll-off, 8K master. POSITIVE LOCKS >> appears only inside the spyglass POV of CUT 3, lying on the beach at the waterline, star button glowing green in every frame it exists. The island always matches >>: green jungle, white-sand beach, turquoise shallows — and stays screen-right, ahead; the enemy ship stays astern, screen-left, in the opposite direction from the island. The spyglass POV (CUT 3) is MONOCULAR: one single round telescope image per frame. Eduardo handles the spyglass with his RIGHT hand at his RIGHT eye in every cut where he uses it. >> keeps black sails and the green skull mainsail in every appearance and stays VERY FAR AWAY the whole beat — naked-eye, she is only a tiny silhouette on the horizon, under 5% of the frame height in CUT 4; she never gets closer than the horizon line. After the reveal Eduardo keeps the spyglass LOWERED — he never raises it at the enemy ship; he speaks no line and makes no gesture — he simply stands looking at the distant ship, and the beat ends on that look; no cannons and no gunfire anywhere in this beat. Eduardo's head: mustard-yellow bandana with the small white shark tooth at the front, hair loose. In CUT 1 Eduardo moves only in the tiptoe scurry: heels off the deck, quick small steps, arms half-raised at chest height — fast and urgent the whole way. The macaw sits on Eduardo's LEFT shoulder continuously from its landing in CUT 1 through the end of the beat, clearly visible in CUTS 2 and 4. The spyglass is in the lookout's hands in CUT 2's first frame and in Eduardo's hands from then on. Same sun direction, same sea state, same wardrobe in every cut. Cuts only at the specified points.

Nawal

18,336 views • 2 months ago

Made with seedance 2.5 Prompt: Create ONE continuous 12-second, 9:16, ultra-photorealistic LIVE-ACTION luxury fashion film. IMPORTANT REFERENCE MAPPING: REFERENCE Image = PRIMARY CHARACTER. Use the FIRST uploaded reference image of the woman. REFERENCE image2 = ENVIRONMENT. Use the SECOND uploaded reference image of the square. REFERENCE David Carbon = HERO OBJECT. Use the THIRD uploaded reference image of the sunglasses. Do NOT refer to these images as Image, image2 or David Carbon. Use the reference images according to their upload order. CHARACTER — REFERENCE IMAGE 1 Preserve the exact woman from REFERENCE IMAGE 1 throughout the entire video: same facial identity, facial structure, natural eyes, hairstyle, body proportions, skin appearance, clothing, footwear, jewelry, accessories and overall appearance. Do not copy the original background from REFERENCE IMAGE 1. The protagonist is the ONLY main character. ENVIRONMENT — REFERENCE IMAGE 2 Use REFERENCE IMAGE 2 only for visual language: architecture, atmosphere, warm sunset lighting, materials, monumental scale and cobblestone character. Create a NEW believable cinematic pedestrian space inspired by it. Do NOT reproduce its exact composition, exact camera angle or exact street layout. Provide enough open pedestrian space for natural walking and the collision. Respect real-world spatial logic: pedestrians remain in pedestrian areas, architecture has realistic scale and perspective, no impossible geometry. HERO OBJECT — REFERENCE IMAGE 3 The sunglasses shown in REFERENCE IMAGE 3 are the ONE and ONLY HERO OBJECT. Preserve their recognizable: shape, proportions, oversized shield silhouette, dark continuous lens, thin metallic/gold frame, temples, hinge construction, surface details, colour and material. The SAME physical sunglasses must remain recognizable: when worn by the protagonist, when released, during bullet-time macro inspection, and after landing. Do not redesign, replace, duplicate or regenerate the sunglasses. EXACT OBJECT COUNT Exactly: ONE protagonist. ONE secondary passing person. ONE Labrador. ONE leash. ONE pair of sunglasses from REFERENCE IMAGE 3. ONE takeaway paper coffee cup. ONE plastic drinking lid. ONE silver-grey OPEN clamshell flip phone. No duplicate objects or people. PERSISTENT PHONE There is exactly ONE phone in the entire video. It is a compact early-2000s silver-grey OPEN clamshell flip phone. Upper half: small illuminated display and speaker. Lower half: physical numeric keypad, navigation buttons and microphone. Visible central mechanical hinge. LOCK its appearance throughout: same silver-grey colour, same dimensions, same thickness, same hinge, same display, same keypad, same buttons, same open angle. The same phone is seen in wide, medium and macro shots. It never transforms into another phone. PERSISTENT COFFEE Exactly ONE medium disposable PAPER coffee cup with ONE lightweight plastic drinking lid and dark coffee inside. Same cup, same lid, same coffee and same proportions throughout. Before collision the lid is properly attached. Coffee remains inside until a real physical opening appears. HAND OWNERSHIP Before collision: RIGHT HAND = ONE OPEN flip phone held to the RIGHT ear. LEFT HAND = ONE coffee cup. Sunglasses = naturally worn by the protagonist. After collision: RIGHT HAND = COMPLETELY EMPTY. LEFT HAND = COMPLETELY EMPTY. Nothing replaces the phone or cup. Nothing remains attached to either palm. 0.0–2.0s — CINEMATIC CHARACTER REVEAL Begin with an extreme low close-up of the protagonist’s black leather heeled boots walking naturally across the pedestrian space. Camera performs ONE elegant continuous movement: smooth crane upward + gentle backward tracking. Reveal progressively: boots → legs → ripped light-blue baggy jeans → black corset → white tank top → jewelry/accessories → sunglasses → face → nearly full body. The protagonist wears the SAME sunglasses from REFERENCE IMAGE 3. She holds the SAME OPEN silver-grey flip phone to her RIGHT ear and the SAME coffee cup in her LEFT hand. She is actively having a phone conversation. Show subtle realistic speech: natural lip movement, jaw movement and mouth articulation. Maintain exact identity from REFERENCE IMAGE 1. Premium live-action fashion cinematography. 2.0–3.7s — WALKING / SECONDARY PERSON Maintain smooth frontal tracking. The protagonist continues walking naturally through the pedestrian area. Exactly ONE secondary person approaches from the opposite direction. That person holds exactly ONE leash attached to exactly ONE Labrador. The Labrador walks slightly ahead and gently pulls the person forward. They remain background/supporting elements. Maintain: stable protagonist identity, stable hairstyle, stable clothing, stable sunglasses, same phone, same coffee. 3.7–4.4s — ACCIDENTAL COLLISION As they pass each other, the secondary person’s ELBOW accidentally clips the protagonist’s arm/upper torso. Small, accidental, believable contact. The protagonist naturally recoils backward. This SAME collision causes THREE physical release events. SUNGLASSES The sunglasses from REFERENCE IMAGE 3 receive ONE short realistic outward impulse. They separate naturally from the protagonist’s face. They travel only a short physically believable distance. They do NOT fly toward the camera. COFFEE The SAME coffee cup leaves the LEFT hand. It receives one short outward/downward rotational impulse. The cup tilts and rotates. Because of the rotation and liquid inertia, ONE EDGE of the lightweight plastic lid partially pops loose from the cup rim. The lid does not disappear and does not explode away. A real physical gap forms between lid and rim. ONLY THEN does dark coffee begin escaping through this opening. Initial liquid movement is restrained. PHONE The SAME OPEN clamshell phone leaves the RIGHT hand. It receives one short outward/upward impulse. It keeps the SAME open angle and physical design. The instant it separates from the fingers: RIGHT HAND = EMPTY. The instant the cup separates: LEFT HAND = EMPTY. FACE / HAIR CONTINUITY Preserve the exact face from REFERENCE IMAGE 1 during the entire collision. The natural human eyes already exist behind the sunglasses. When the sunglasses separate, reveal the SAME normal eyes: stable pupils, eyelids, gaze direction, brows, nose, cheekbones and facial symmetry. Do not regenerate or alter the face. Hair remains stable with only subtle realistic inertia. No sudden hairstyle change. 4.4–5.2s — BULLET-TIME ESTABLISHMENT Time decelerates dramatically to approximately 2–3% normal speed. DO NOT immediately go into macro. FIRST show a clear medium-wide frozen view of the entire accident. The protagonist is beginning to fall backward. BOTH HANDS ARE EMPTY. Establish fixed WORLD-SPACE anchors: • sunglasses suspended near their release position; • coffee cup suspended lower and toward the LEFT-hand release side; • partially detached lid still connected to or immediately beside the cup; • restrained coffee beginning to escape through the opening; • OPEN flip phone suspended toward the RIGHT-hand release side. Objects move only microscopically. They do NOT move toward the camera. The CAMERA is the main moving element. 5.2–6.8s — SUNGLASSES HERO INSPECTION The sunglasses remain almost completely stationary at their existing world-space position. CAMERA physically dollies toward them. The sunglasses become larger ONLY because the camera gets closer. Once close, slow the camera dramatically. HOLD. Perform a restrained 20–30 degree camera orbit/parallax around the almost-stationary sunglasses. Reveal: dark shield lens, thin metallic/gold frame, temples, hinges, edges, material thickness, surface reflections, tiny manufacturing details. Use shallow photographic macro depth of field. The protagonist and sunset environment remain softly recognizable in the background. The sunglasses must look like a real luxury fashion accessory photographed with a macro cinema lens, NOT CGI product animation. Complete the inspection before moving away. 6.8–8.3s — COFFEE / LIQUID INSPECTION Only after completing the sunglasses inspection, the CAMERA leaves them at their existing world-space position. Travel diagonally through the frozen scene toward the SAME coffee cup. THE CUP DOES NOT MOVE TOWARD THE CAMERA. Hold a photographic macro close-up. Show: same paper cup, same lightweight plastic lid, ONE partially detached lid edge, clear physical gap, dark coffee escaping ONLY through that gap. Real restrained liquid physics: thin irregular stream, imperfect liquid sheet, several differently sized droplets, realistic surface tension, natural reflections. No explosive splash. No decorative CGI liquid. No perfect artificial shapes. Coffee advances only microscopically during bullet time. Perform a small restrained lateral/parallax camera movement around the cup, lid and droplets. HOLD long enough to see paper texture, plastic texture, liquid thickness and individual droplets. 8.3–9.8s — FLIP PHONE INSPECTION Only after coffee inspection, the CAMERA travels away from the cup. The cup, lid and droplets remain at their existing world-space positions. CAMERA moves through the same frozen scene toward the SINGLE OPEN silver-grey clamshell phone. THE PHONE DOES NOT MOVE TOWARD THE CAMERA. First establish the complete phone silhouette: same silver-grey housing, same upper display, same lower keypad, same central hinge, same open angle. Then CAMERA physically approaches the existing upper display. Extreme photographic macro close-up. The illuminated display reads: BOSS with one small realistic phone number underneath. HOLD. Show: real housing material, hinge, keypad texture, small scratches, surface wear, screen reflections. The phone does NOT transform to reveal its screen. It is the SAME phone seen from the beginning. The protagonist’s RIGHT HAND remains completely EMPTY in the background. 9.8–10.4s — COMPLETE FROZEN TABLEAU After phone inspection, CAMERA performs a fast but perfectly smooth dolly backward. All objects remain at their existing world-space positions. Reveal: same protagonist falling backward, both hands empty, same sunglasses, same coffee cup, same partially detached lid, same suspended coffee droplets, same OPEN flip phone, exactly one secondary person, exactly one Labrador. All positions must remain spatially consistent with the original collision and release trajectories. No object follows the camera. No object teleports. No object regenerates. Brief HOLD on the complete frozen tableau. 10.4–12.0s — TIME RETURNS / PHYSICAL PAYOFF Time suddenly snaps back to normal speed. Gravity and existing momentum resume simultaneously. Every object continues FROM ITS EXISTING WORLD-SPACE POSITION. The protagonist completes her backward fall naturally. The sunglasses continue from their suspended position and land according to their existing momentum and gravity. The coffee cup continues from its own separate position, impacts the cobblestone ground, the partially detached lid reacts naturally, and remaining coffee spills irregularly through the real opening and impact point. The OPEN flip phone continues from its own separate position, hits the ground and makes ONE small physically believable bounce. Objects land at DIFFERENT plausible locations. They do NOT suddenly converge beside the protagonist. CAMERA rapidly tilts/drops toward ground level to follow the final impacts. Finish with a cinematic low-angle composition showing the fallen protagonist and the scattered objects within the same believable sunset environment. Hard cut. BULLET-TIME CAMERA RULE — NON-NEGOTIABLE BULLET TIME = ALMOST-FROZEN PHYSICAL WORLD + FREELY MOVING CAMERA. Objects stay in WORLD SPACE. Camera moves through WORLD SPACE. Close-up is created ONLY by reducing camera-to-object distance. Never: move objects toward the lens, artificially enlarge objects, teleport objects, regenerate macro versions. STRICT CAMERA ROUTE: FULL FROZEN TABLEAU → CAMERA DOLLIES TO SUNGLASSES → HOLD → 20–30° CAMERA ORBIT → CAMERA TRAVELS TO COFFEE → HOLD → SMALL CAMERA PARALLAX → CAMERA TRAVELS TO PHONE → ESTABLISH COMPLETE PHONE → MOVE TO DISPLAY → HOLD → CAMERA DOLLIES BACK TO COMPLETE TABLEAU → TIME RETURNS CONTINUITY / CAUSALITY Wide shot → medium shot → macro shot = SAME physical object viewed from different camera distances. Sunglasses: same object, same design, same trajectory, same world-space identity. Coffee: same cup, same lid, same coffee, same rotation, same world-space identity. Phone: same open clamshell phone, same housing, hinge, keypad, display, open angle and world-space identity. Every visible change must have a physical cause. Collision causes recoil. Collision momentum separates sunglasses. Finger release changes phone position. Hand release + collision momentum rotates cup. Cup rotation/liquid inertia partially opens lid. Coffee escapes only through the physical gap. Camera movement creates apparent object scale. Gravity resumes final fall. Treat the entire sequence as ONE continuous practical-effects event photographed with a motion-control cinema camera. IDENTITY / PROP LOCK ONE protagonist. ONE secondary person. ONE Labrador. ONE leash. ONE pair of sunglasses. ONE coffee cup. ONE lid. ONE OPEN flip phone. Before collision: RIGHT HAND = phone. LEFT HAND = coffee. Sunglasses = worn. After collision: RIGHT HAND = EMPTY. LEFT HAND = EMPTY. Sunglasses = separated. No second phone. No second cup. No second sunglasses. No additional dog. No additional person. No unexplained props. No duplication. No teleportation. No unexplained scale changes. VISUAL PRIORITY 1. exact protagonist identity from REFERENCE IMAGE 1 2. natural eyes and facial anatomy 3. stable hairstyle and body proportions 4. exact clothing and accessories 5. exact sunglasses from REFERENCE IMAGE 3 6. stable phone geometry 7. empty hands after release 8. continuous physical trajectories 9. realistic environment inspired by REFERENCE IMAGE 2 PHOTOGRAPHIC REALISM Ultra-photorealistic LIVE-ACTION. High-budget international luxury fashion campaign. Real human anatomy. Natural skin pores. Natural facial micro-expressions. Detailed realistic hair. Real manufactured sunglasses. Real paper cup. Real plastic lid. Real liquid coffee. Real early-2000s flip phone. Real object mass, inertia, gravity, momentum and surface tension. ARRI Alexa 35 cinematic character. Premium cinema optics. Motivated sunset lighting inspired by REFERENCE IMAGE 2. Controlled highlights. Natural skin tones. Realistic optical depth of field. Shallow macro depth of field during object inspections. Subtle 35mm film texture. Restrained luxury editorial colour grade. Natural colours. Sharp optical clarity. Cinematic photographic texture. Bullet-time must feel like REAL high-speed practical photography with a motion-control cinema camera, NOT CGI product animation. 4K / Ultra HD. Maximum facial detail. Maximum hair detail. Maximum material fidelity. Stable identity. Stable geometry. Stable prop continuity.

Oogie

18,923 views • 21 days ago