Sabitlenmiş Tweet
Patrick | Velokey
307 posts

Patrick | Velokey
@velokey9
operator at Velokey. I test text, image, and video models, share the workflows behind the results, and write about API routing, reliability, and tradeoffs.
Katılım Haziran 2026
107 Takip Edilen38 Takipçiler

@kawaii_ai_zoo What sells the size is the speed gap — the whale barely drifts while the doves whip spirals around it, and big things moving slow is the one rule AI usually breaks. Was that rise speed in your prompt or Grok's own instinct?
English

@heris252 Gm Heris! Watched to the end — the gold fish parking in front of his face flips the whole Dalí scene into a Magritte gag. Don't know if that was planned but it's the best part.
English

@Lianaalane The prompt you posted only covers the kitchen scene, but the video gives her a whole morning — the two gents at breakfast, the guard at the revolving door. Did you storyboard the rest separately, or did the model invent it on its own?
English

A confident businesswoman, timeless elegance, and a luxurious modern interior come together to create a cinematic visual that feels both sophisticated and inspiring. Every frame is designed with realistic lighting, smooth camera movement, and premium fashion aesthetics.
Created this 14-second cinematic businesswoman story using Seedance 2.0 on @wavespeed_ai.
Prompt:
A stunning young businesswoman stands in a luxurious, sunlit modern kitchen with white marble countertops, sleek cabinetry, and minimalist interior design. She wears a perfectly tailored navy blazer and matching pencil skirt over a crisp white blouse, carrying a small black leather handbag with gold hardware. Her dark brown hair is styled in a soft low bun with loose face-framing curls. She looks down with a gentle, confident smile, then slowly raises her gaze toward the camera while elegantly adjusting her handbag. She takes a few graceful steps forward with natural body movement, relaxed shoulders, and poised posture. Warm golden-hour sunlight streams through the large windows, creating soft highlights and cinematic shadows. The camera begins with a medium shot and performs a slow cinematic dolly-in, maintaining shallow depth of field with creamy background bokeh. Ultra-realistic skin texture, subtle facial expressions, realistic fabric physics, natural hand movements, smooth walking animation, premium luxury lifestyle aesthetic, photorealistic, HDR, 4K, 24fps, soft color grading, high-end commercial fashion advertisement, stable camera, no flickering, no distortion, no extra fingers, no artifacts.
English

@wilzap Clocked the shelves in the last shot — the baskets are already full, so this clearly wasn't his first run. Forget the mousetraps, at this point he's got squatter's rights.
English

@johnAGI168 The bit after the splash is what sold me — she comes up, wipes her eyes, grins, and most AI dives would've ended at entry. Was the underwater glide the same gen or stitched, and yes, I'll take that prompt.
English

@velokey9 Locking the first and last frame instead of describing motion is smart.
English

Still shot on nothing. Now it moves.
Yesterday's two stills became a 10-second video. The trick isn't
describing the motion — it's locking the first and last frame and
writing a timestamped shot list for the space between. The dance
is entirely invented.
Full prompt + breakdown in the replies.
Patrick | Velokey@velokey9
Shot on nothing. Expired film look, entirely prompted. The trick isn't asking for "film grain" — it's asking for the failures: pushed two stops, blacks that never reach black, halation bleeding into every highlight, nothing in critical focus. Full prompt + model in the replies.
English

@St_Godwins If you'd like, you can check out my homepage; it has a free quota, so you can try it out first.
English

@SimplyAnnisa @itsPolloAI Mixing a cartoon tomato into photoreal food is the part I'd expect to fall apart — either the pasta goes plastic or the tomato stops being expressive. Did you have to dial one of them back to make them coexist?
English

Created with seedance 2.0 on @itsPolloAI
Style:
Live-action + ultra-photorealistic food comedy. Every ingredient is a tiny anthropomorphic food character with miniature human arms, legs, expressive eyes, and funny facial expressions while keeping realistic food textures. Bright modern home kitchen, warm morning sunlight, cinematic shallow depth of field, handheld camera, realistic shadows, steam, reflections, ultra-HD 8K, vertical 9:16, fast comedic pacing.
Duration:
15 seconds.
00:00–00:02 | Pasta Arrives
A cute spaghetti dough character with tiny human arms and legs proudly walks onto a white ceramic plate carrying a bundle of fresh spaghetti on its back. It smiles confidently, jumps into the centre of the plate, and instantly transforms into a neat nest of fresh spaghetti.
00:02–00:04 | Tomato Sauce Splash
A cheerful tomato character climbs onto a tiny wooden platform above the plate. It takes a deep breath and squeezes itself, shooting a thick stream of rich tomato sauce from its mouth directly onto the spaghetti below. The glossy sauce spreads naturally while the tomato proudly wipes its mouth.
00:04–00:06 | Meatball Drop
A chunky meatball character hangs upside down from a stainless-steel kitchen rod using both hands. It swings back and forth, then lets go, landing perfectly on top of the pasta with a soft bounce. Steam rises naturally as the meatball smiles proudly.
00:06–00:08 | Mushroom Acrobat
A smiling mushroom character performs an elegant flip through the air. During the flip, its cap gently separates and lands perfectly beside the meatball while the tiny body lands safely on the plate and bows toward the camera.
00:08–00:10 | Parmesan Shower
A happy parmesan cheese block character climbs onto a miniature cheese grater. It slides itself across the grater, creating a beautiful snowfall of freshly grated parmesan over the pasta. The character laughs happily while becoming slightly smaller.
00:10–00:12 | Basil Finale
A tiny basil leaf character jumps from a spoon handle like a diving board, spins gracefully in slow motion, and lands perfectly on top of the meatball as the final garnish. Steam rises dramatically from the completed spaghetti.
00:12–00:15 | Victory Celebration
The completed spaghetti looks restaurant-quality with glossy tomato sauce, juicy meatballs, fresh basil and grated parmesan. All the tiny ingredient characters gather around the plate, cheering, waving at the camera, giving thumbs-up and celebrating proudly while the camera slowly pushes in toward the finished dish. Freeze frame during the last 0.3 seconds.
English

@Goodmanprotocol The negative space is what makes this work, and MJ usually fights you on that — it wants to fill every corner. Did you have to keep pushing to keep it that empty, or did v8.2 just give you the restraint?
English

Minimalist watercolor illustration of children joyfully playing in summer splash fountains.🌊
Midjourney v8.2
Prompt:
Minimalist watercolor illustration on textured cold press handmade paper, 3:4 vertical, large negative space, delicate ink line art, translucent washes, wet on wet blooms, pigment granulation, floating droplets, cozy slice of life warmth, elegant editorial quality, museum quality, 8K.
PALETTE: cobalt/cerulean sky, bare white paper for clouds, warm grey granite, lemon yellow and mint green accents.
SCENE: A single Korean elementary school boy walks out of an arching fountain jet tunnel at Gwanghwamun Plaza, Seoul, on a bright summer day soaked, grinning wide, shoulders lifted, one hand brushing water from his face, rubber sandals splashing wet stone. Pure childlike delight.
COMPOSITION: Eye level frontal perspective. Boy small in lower middle third. Arching jets form a receding ink arc tunnel converging to a soft vanishing point behind him. Single cohesive moment.
ENVIRONMENT: Anchor = arching jets + wet granite only. Boy and nearest jets ~60% resolved; distant buildings/trees dissolve into pale blue grey washes, broken graphite, pigment blooms, untouched paper. Sky nearly empty.
WARDROBE: lemon yellow t shirt, mint green shorts, pale blue rubber clogs, soaked hair pushed back, tiny realistic droplets on face and fabric.
LIGHT/WATER: Strong warm midday sun. Jets rendered as fine ink lines breaking into dots and comma shaped droplets, dry brush spray at landing, pale cerulean pooling on granite. Large untouched ivory paper areas preserved. No text, captions, signage, logos, watermarks, duplicated figures, extra limbs, distorted hands, crowded background, dark digital painting, heavy outlines, or glossy 3D rendering.



English

@0xbisc @dreamina_ai Saw you said it was detailed shot descriptions, not storyboards. Does the model sheet actually feed into the gens to keep him on-model, or is it more just a reference for you while writing those descriptions? Curious where the consistency really comes from.
English

@meng_dagg695 @higgsfield You listed 47mm and an 18° ECU — do those actual numbers change the output for you, or does the model mostly just read them as "shoot this tight and cinematic"? Always wondered if precise optics specs land or get flattened.
English

Created with Seedance 2.0 on @higgsfield
Promot: Style: 8K photorealistic, anamorphic 2.39:1, high-fashion beauty commercial grade, soft pastel tones, creamy highlight roll-off, fine grain.
Lighting: soft wraparound beauty key from camera-front, gentle warm rim from camera-left, diffused fill, muted sage-grey background falling soft; delicate light catching the butterfly wings translucent.
Color: muted sage-grey background and pale silver garment as the dominant, warm peach skin and soft rose lips as the accent, iridescent pastel butterfly wings, silver jewelry glinting cool.
Camera: anamorphic cine optics, very shallow depth, slow floating macro move that eases to a halt, real motion blur on the butterfly.
Skin: pore-level realism — fine peach-fuzz catching the rim, dewy sheen, soft blush flush, glossy lip texture, real catch-lights in the eyes.
Acting: serene and still — a soft knowing half-smile, eyes following the butterfly, breath held gentle as it lands, lips barely parting.
Physics: the butterfly flutters with real lightweight erratic flight, wings translucent and trembling, settling with featherlight contact; hair and the chain shift with the faintest air.
Composition: butterfly leads the frame in flight, then face fills the frame as it settles on the lips, depth from soft foreground to creamy background bokeh.
Continuity: same woman, same silver jewelry, same butterflies, same soft sage-grey beauty set across all cuts.
Technical: 24fps, ultra high detail, smooth floating-to-still motion, total continuous flow.
Audio: diegetic and atmospheric — soft airy ambient pad, the faint flutter of butterfly wings, a single soft breath.
SCENE CONTEXT
A high-fashion beauty spot: the camera floats behind a pale iridescent butterfly drifting through the air toward a serene woman, slowing to a halt as the butterfly settles on her lips, ending on a close beauty hold of her lips and silver jewelry.
ACTIVE REFERENCES
: the woman and the look — a woman with warm fair skin, long light-brown hair with straight bangs in a high ponytail, soft natural makeup with rose lips, a small silver beaded choker and a thin silver chain necklace, a silver drop earring, a pale silver-blue halter top; pale iridescent butterflies drifting in the air, soft muted sage-grey background. 100% matches the reference.
LOCATION MAP
Foreground: the drifting butterfly nearest camera. Midground: the woman's face and bare shoulder. Background: soft sage-grey studio falling to creamy bokeh, a few more butterflies floating in depth. Camera floats through the air on the butterfly's path, soft key from front. Movement glides forward then eases to a stop at her lips.
FIRST FRAME / BLOCKING
A pale iridescent butterfly mid-air filling the foreground, the woman soft-focus beyond it, head slightly turned, beginning a gentle smile, more butterflies drifting in the background.
FORMAT MODE
One continuous shot, the camera does not cut on its own — a single floating follow that eases to a halt.
OPTICS
WS 47° opening on the butterfly in flight, easing to MCU 29° as it nears her, settling to ECU 18° on her lips and jewelry. No hard cuts; FOV tightens smoothly with the move.
CAMERA
A slow floating operator gliding behind the butterfly at a natural following distance, drifting and bobbing gently with its erratic flight, decelerating smoothly as the butterfly approaches her face, coming to a complete gentle halt as it lands on her lips, then holding perfectly still on the close beauty frame.
ACTION
The camera floats forward behind the pale butterfly as it drifts through the air toward the woman, her face soft beyond it, a knowing half-smile forming and her eyes tracking it. The butterfly weaves closer, the camera slowing with it, depth racking onto her face. As it nears her mouth the camera eases almost to a stop; the butterfly settles featherlight on her lower lip, wings trembling once and stilling. The camera halts completely, holding the close frame
English

@kingofdairyque @itsPolloAI The cheese texture is so satisfying but it still reads as a living thing, which feels like a narrow line. How'd you decide when to stop pushing the cheese detail before it just became a block that moves?
English

Created with seedance 2.0 on @itsPolloAI
Duration: 15 Seconds
Style:
Ultra-photorealistic live-action food commercial. Bright modern Italian kitchen with warm natural morning sunlight. Every ingredient is a tiny anthropomorphic food character with miniature human arms, legs, expressive eyes, and funny personalities while preserving completely realistic food textures. Macro food photography, cinematic lighting, shallow depth of field, handheld premium commercial camera, ultra-realistic physics, 8K HDR, vertical 9:16.
Maintain the exact same kitchen, lighting, camera angle, color grading, and character identities throughout. Every ingredient keeps the same appearance from beginning to end. Fast, satisfying, premium commercial pacing.
────────────────────────
00:00–00:02 | Shot 1 – Dough Builder
A soft pizza dough character happily climbs a miniature metal ladder beside a wooden pizza board. Reaching the top, it turns around and fresh pizza dough smoothly expands from its back, perfectly forming a round pizza base on the board. The character proudly dusts flour from its hands and smiles.
SFX:
Tiny footsteps.
Soft dough stretching.
────────────────────────
00:02–00:04 | Shot 2 – Tomato Sauce Artist
A cheerful tomato character stands on a tiny wooden platform above the dough. It takes a deep breath and smoothly sprays rich tomato sauce from its mouth in a perfect spiral, covering the pizza evenly. It finishes with a proud thumbs-up.
SFX:
Smooth sauce pouring.
────────────────────────
00:04–00:06 | Shot 3 – Cheese Shower
A happy mozzarella cheese block climbs a miniature stainless-steel grater. Sliding down the grater, hundreds of fresh cheese strands rain beautifully over the pizza until it is fully covered. The cheese character laughs proudly.
SFX:
Fresh cheese grating.
────────────────────────
00:06–00:08 | Shot 4 – Pepperoni Delivery
A tiny pepperoni character swings from a hanging kitchen rail like a gymnast. At the perfect moment, circular pepperoni slices pop naturally from its back one after another, landing perfectly across the cheese. It lands safely beside the pizza and salutes the camera.
SFX:
Whoosh.
Soft topping drops.
────────────────────────
00:08–00:10 | Shot 5 – Mushroom Acrobat
A smiling mushroom character performs a graceful flip from a miniature springboard. During the flip, perfectly sliced mushroom pieces gently fall from beneath its cap, spreading evenly across the pizza before it lands and bows proudly.
SFX:
Tiny flip.
Soft landing.
────────────────────────
00:10–00:12 | Shot 6 – Basil Finale
A fresh basil leaf character slides down a polished metal spoon like a playground slide. Reaching the bottom, beautiful basil leaves naturally appear from its back and land neatly across the pizza. The basil character throws both hands into the air in celebration.
SFX:
Gentle slide.
Soft leaf landing.
────────────────────────
00:12–00:15 | Shot 7 – Oven Magic Finale
The fully assembled pizza slides into a glowing stone pizza oven. Through the oven opening, bubbling cheese, sizzling pepperoni, and golden crust are visible as heat waves shimmer realistically. The finished pizza slides back onto the wooden board, steaming beautifully. All tiny ingredient characters gather around it, clapping, dancing, waving at the camera, and celebrating proudly.
Final 0.3 seconds:
Freeze frame on the finished restaurant-quality pizza with bubbling melted cheese, crispy golden crust, realistic steam, cinematic lighting, macro food photography, and all ingredient characters smiling around the pizza.
English

@CaliraVal I expected the liquid splash to be the nightmare part, but honestly the semi-transparent juice texture while it's blending looks harder to nail. Did that give you more grief than the droplets?
English

From bean to masterpiece—every pour tells a cinematic story.
Crafted with AI, brewed to perfection.
Prompt:
Ultra-realistic cinematic food commercial of a premium iced coffee being crafted from scratch in a luxurious modern kitchen. Extreme macro close-up as glossy roasted coffee beans slowly pour from a black container onto a polished white marble countertop in slow motion. Smooth match cuts show beans being freshly ground, rich espresso flowing from a professional machine, creamy milk poured over crystal-clear ice cubes inside a tall transparent glass coated with dark chocolate syrup. Silky espresso cascades into the glass, creating mesmerizing swirling layers of coffee and milk. Thick velvety foam rises to the top, finished with a light dusting of cocoa powder. Warm golden morning sunlight streams through the window, soft reflections on the glass, shallow depth of field, cinematic bokeh, ultra-detailed textures, realistic liquid physics, elegant camera movement, luxury café aesthetic, premium commercial lighting, HDR, 4K, photorealistic, smooth transitions, high-end beverage advertisement, satisfying ASMR visual style.
Camera: Macro Close-up, Top-down, Overhead, Slow Push-in, Orbit Shot, Tracking Shot, Extreme Close-up, Slow Motion (120fps feel).
Style Tags: Luxury Coffee Commercial, Food Cinematography, Photorealistic, Hyper Detailed, Golden Hour Lighting, Creamy Texture, Chocolate Drizzle, Café Aesthetic, Ultra Smooth, Premium Product Ad.
English

@Ciri_ai @itsPolloAI That low angle is what sells it, feels like the camera is about to get stepped on. Curious whether the ground-level framing or the speed of the roll gave you more trouble.
English

Crafted with Seedance 2.0 + GPT Image 2 @itsPolloAI
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
English

@Just_sharon7 @Flovaai which part typically needs the most iterations — keeping the character's face consistent across cuts
English

How much cleaning is too much cleaning?
Make your video like this using Product commercial skill on @Flovaai
Model used: Seedance 2.0
prompt
A 60-second 3D Pixar-style animated commercial for 7UP Extra Fizz. Bright, vibrant, highly expressive cartoon rendering with smooth exaggerated animation, big emotional faces, soft rounded shapes, rich saturated colors, and cinematic lighting. Vertical smartphone aspect ratio with dynamic camera moves (sweeping low angles, playful tracking shots, extreme close-ups on expressions). *Setting:* A sunny, modern Western suburban home with open-plan living spaces, light wooden floors, white walls with geometric wood accent panels, large windows letting in golden afternoon light, and a cozy, slightly cluttered family feel. *Characters:* • Mom: Mid-50s Western woman, warm but dramatic, short stylish brown hair with a few gray streaks, wearing a soft beige cardigan over a patterned blouse and jeans. • Daughter: Early-20s, long reddish-brown hair in a high ponytail, wearing an olive-green polo shirt, gold heart necklace, and baggy light-wash jeans. Highly expressive Pixar-style face that goes from annoyed → exhausted → pure joy. *Scene breakdown:* 0–6s: Close-up of a vintage green rotary phone on a glossy side table. Mom appears in the background holding the handset, eyes wide with urgency, waving her free hand dramatically as she speaks in English: “The guests are coming in an hour! Honey, hurry up! Clean every single fan blade, one by one — please, please, go go go!” 6–12s: Cut to the daughter on the living-room sofa, scrolling on a peach smartphone. Her face scrunches into a classic Pixar annoyed expression (eyebrows knitted, mouth twisted). She lets out a big exaggerated sigh. 12–22s: Mom marches in holding a green-handled mop, gesturing wildly. Daughter climbs a bright red stepladder and starts cleaning a dark wooden ceiling fan. She meticulously wipes each blade with a white cloth, her face showing increasing determination mixed with irritation. Camera circles around her as dust motes float in the light. She then dusts the geometric wooden wall panels with a long grey duster, dramatically wiping sweat from her forehead with a big cartoonish gesture. 22–32s: Daughter now wears bright yellow rubber gloves. She crouches inside a wide-open stainless-steel refrigerator, vigorously scrubbing the white interior walls and shelves with a green microfiber cloth. Several green 7UP bottles are clearly visible on the door shelves. Her expression is pure focused effort, tongue slightly sticking out in concentration. 32–42s: Outside on the front porch steps under a soft evening sky. Mom stands in the doorway still urging. Daughter holds the mop, shoulders slumped, and complains with big exaggerated exhaustion: “Mom, the stairs too?! This is getting a little extra!” She continues, voice rising: “I’m completely wiped from all this extra cleaning!” 42–52s: Extreme close-up of the daughter’s tired face. She reaches for a cold green 7UP Extra Fizz bottle. With a satisfying twist and loud fizzy “PSSSHT!” sound effect, she opens it. Bubbles and tiny water droplets spray in a playful Pixar-style flourish. She takes a long, refreshing drink. Her entire face transforms — eyes light up, cheeks glow, a huge genuine smile spreads as energy returns to her body. She does a little joyful bounce. 52–60s: Dynamic heroic product shot. The icy-cold 7UP Extra Fizz bottle rises against a bright blue sky. Dramatic water splash and exploding bubbles surround it in exaggerated, sparkling 3D animation. Bold, playful on-screen text pops in with a bounce: “INTRODUCING 7UP EXTRA FIZZ” next to the classic 7UP logo. Soft upbeat music swells into a fresh, fizzy climax. *Overall tone & style:* Warm, relatable, slightly comedic family chaos that feels like a Pixar short, transitioning into pure refreshing joy. Exaggerated facial expressions, squash-and-stretch animation, vibrant green product highlights, smooth camera movement, clear English dialogue, and upbeat background music that builds from stressed household energy to sparkling refreshment.
#FlovaBrandstormand
English

@umesh_ai The timing sync between both views is the wild part — did you generate them as one split-screen prompt, or render each side separately and manually align the rope pull and bike lift in post?
English

Flux 3 is incredible at split screen generations!
Prompt : 15-second split-screen video, two equal vertical halves, one continuous take, no cuts. Both cameras show the same event at the same time, perfectly frame-synchronized. Scene: Calm lake at dusk. An old fisherman in a small wooden rowboat pulls a rope from the water. Left: Water-level camera from another boat. Show only the fisherman, boat, rope above water, ripples, and splashes. Nothing below the waterline is visible. Right: Underwater camera looking up. The rope leads to a sunken bicycle tangled in glowing green weeds, surrounded by small silver fish. 0–6s: The fisherman pulls. Left: he strains and the boat rocks. Right: the bicycle rises with every matching tug. 6–11s: A violent jolt. Left: he nearly falls backward. Right: a wheel catches on a rock, then pops free on the exact same frame. Fish scatter. 11–15s: The bicycle crosses the surface continuously. It must appear above water on the left only when that exact part crosses the waterline on the right. Both halves must match its height, angle, motion, rope tension, splashes, and timing frame by frame. Once fully raised, the fisherman stares, then laughs. No duplicate bicycle, broken rope, teleporting, timing offset, or camera change.
Upscaled with Topaz Astra.
@bfl_ai
English

I'm building Velokey: one API for leading text, image, video, and
audio models.
velokey.ai
Stills or motion — which one keeps the illusion better?
English







