NOVA — the prompts.

The brand board is generated in one go, with four already-produced visuals as reference: the model redraws nothing, it composes. Logo, palette, type and imagery come out on a single page — this is the piece that makes a series of images read as a brand.

Design a single BRAND IDENTITY BOARD for the fictional brand NOVA, presented as one flat designed page seen perfectly straight on, filling the whole frame. This is a graphic design layout, NOT a photograph of a physical board — no desk, no hands, no perspective.

USE THE FOUR ATTACHED PHOTOGRAPHS AS THE ACTUAL IMAGE TILES OF THE BOARD. Place them unmodified inside clean rectangular frames: image 1 as the large hero tile, images 2, 3 and 4 as supporting tiles. Do not redraw them and do not replace them with other pictures — crop them only if the layout needs it.

LAYOUT — a strict editorial grid with generous margins on a flat neutral background from the palette:
· top left, the wordmark NOVA very large, set in a precise industrial sans for the wordmark and a condensed sans for captions
· under it, the descriptor OVER-EAR STUDIO in small letter-spaced caps
· the four photographs as a clean asymmetric grid, one large and three smaller
· a horizontal PALETTE row of five solid colour chips, each with its name and hex code in small caps beneath: INDIGO #1E2A5A, CHARCOAL #2E3134, STEEL #9AA1A8, BONE #E8E6E1, ACCENT #4C7BF0
· a TYPOGRAPHY block showing A B C D E F G and 0 1 2 3 4 5 in the brand typeface, with the type names labelled
· small section labels in tiny letter-spaced caps: LOGOTYPE, PALETTE, TYPOGRAPHY, IMAGERY

MOOD — engineered, nocturnal, audiophile. Every colour comes from the palette above and from the photographs. Spell every word correctly. Crisp vector-clean typography, high resolution, professional brand guidelines aesthetic. No watermark, no lorem ipsum, no extra logos.

Design a single BRAND IDENTITY BOARD for the brand [BRAND NAME], presented as one flat designed page seen perfectly straight on, filling the whole frame. This is a graphic design layout, NOT a photograph of a physical board — no desk, no hands, no perspective.

USE THE FOUR ATTACHED PHOTOGRAPHS AS THE ACTUAL IMAGE TILES OF THE BOARD. Place them unmodified inside clean rectangular frames: image 1 as the large hero tile, images 2, 3 and 4 as supporting tiles. Do not redraw them and do not replace them with other pictures — crop them only if the layout needs it.

LAYOUT — a strict editorial grid with generous margins on a flat neutral background from the palette:
· top left, the wordmark [BRAND NAME] very large, set in [TYPEFACE FOR THE WORDMARK] and [TYPEFACE FOR THE CAPTIONS]
· under it, the descriptor [PRODUCT DESCRIPTOR] in small letter-spaced caps
· the four photographs as a clean asymmetric grid, one large and three smaller
· a horizontal PALETTE row of five solid colour chips, each with its name and hex code in small caps beneath: [COLOUR 1 #HEX], [COLOUR 2 #HEX], [COLOUR 3 #HEX], [COLOUR 4 #HEX], [COLOUR 5 #HEX]
· a TYPOGRAPHY block showing A B C D E F G and 0 1 2 3 4 5 in the brand typeface, with the type names labelled
· small section labels in tiny letter-spaced caps: LOGOTYPE, PALETTE, TYPOGRAPHY, IMAGERY

MOOD — [THREE ADJECTIVES THAT DEFINE THE BRAND]. Every colour comes from the palette above and from the photographs. Spell every word correctly. Crisp vector-clean typography, high resolution, professional brand guidelines aesthetic. No watermark, no lorem ipsum, no extra logos.

The starting point of the whole campaign: the product, generated on its own on a neutral background. It's the one you then pass in as a reference in every visual — the set changes, the headphones never move. Notice how much material detail there is: “fine brushed grain”, “protein leather”. That is what stops the model inventing some generic plastic.

Ultra high-end commercial packshot of a pair of over-ear headphones in three-quarter view, centred, on a seamless deep indigo backdrop with a soft graduated falloff. The headphones have matte charcoal aluminium earcups with a fine brushed grain, soft memory-foam earpads in dark grey protein leather, a slim brushed-steel headband arc, and a small polished NOVA wordmark etched into the outer face of the left cup. Studio lighting: one large softbox from the upper left raking across the brushed aluminium, a tight cool rim light along the headband arc, a soft contact shadow beneath. Photorealistic, 8K, macro-level detail, premium advertising aesthetic, immaculate reflections. No other text, no watermark, no hands.

Ultra high-end commercial packshot of a [PRODUCT TYPE] in three-quarter view, centred, on a seamless [BACKGROUND COLOUR] backdrop with a soft graduated falloff. The [PRODUCT] has [MATERIAL 1 + ITS TEXTURE], [MATERIAL 2 + ITS TEXTURE], [STRUCTURAL DETAIL], and a small [BRAND NAME] wordmark [HOW IT IS APPLIED] on [WHERE EXACTLY]. Studio lighting: one large softbox from the [DIRECTION] raking across the [MAIN MATERIAL], a tight [WARM/COOL] rim light along [THE EDGE THAT MUST READ], a soft contact shadow beneath. Photorealistic, 8K, macro-level detail, premium advertising aesthetic, immaculate reflections. No other text, no watermark, no hands.

The shot that sets the brand's world. The headphones hang from a mic stand, the faders glow behind them out of focus: the set tells you what it's for without ever stealing the show from the product.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — a dim recording studio: the headphones hanging on a mic stand, faders glowing behind and out of focus, one cool key light. Moody, tech, cinematic.

Capture using a Hasselblad H6D-400c multi-shot with an HC 120mm Macro lens, ISO 64, f/11, focus stacking, cross-polarised HDR studio lighting, 16-bit colour workflow, industrial-design retouching, ultra-high-resolution 4K product photography with the anodised aluminium micro-grain and protein-leather texture razor-sharp.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — a dim [PROFESSIONAL SPACE]: the [PRODUCT] [HOW IT IS PLACED THERE], [WHAT GLOWS BEHIND] glowing behind and out of focus, one cool key light. Moody, tech, cinematic.

Capture using a [CAMERA BODY] with a [LENS], ISO [ISO], f/[APERTURE], focus stacking, [LIGHTING SETUP], 16-bit colour workflow, [RETOUCHING STYLE] retouching, ultra-high-resolution 4K product photography with the [YOUR MATERIAL 1] and [YOUR MATERIAL 2] texture razor-sharp.

The shot that sells build quality. A raking light crosses the brushed grain, the engraved logo stays sharp. In product advertising, it's the material that justifies the price, not the shape.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — an extreme macro across the brushed aluminium earcup, a hard highlight travelling the grain, the etched wordmark sharp. 100mm macro, raking light.

Capture using a Hasselblad H6D-400c multi-shot with an HC 120mm Macro lens, ISO 64, f/11, focus stacking, cross-polarised HDR studio lighting, 16-bit colour workflow, industrial-design retouching, ultra-high-resolution 4K product photography with the anodised aluminium micro-grain and protein-leather texture razor-sharp.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — an extreme macro across the [MATERIAL] [PART OF THE PRODUCT], a hard highlight travelling the grain, the [LOGO OR ENGRAVED DETAIL] sharp. 100mm macro, raking light.

Capture using a [CAMERA BODY] with a [LENS], ISO [ISO], f/[APERTURE], focus stacking, [LIGHTING SETUP], 16-bit colour workflow, [RETOUCHING STYLE] retouching, ultra-high-resolution 4K product photography with the [YOUR MATERIAL 1] and [YOUR MATERIAL 2] texture razor-sharp.

The shot that shows what it's for. Eyes closed, the landscape streaking past behind: you're selling isolation, not headphones. One gesture, one emotion — the Module 1 rule.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — a passenger wearing the headphones by a train window, eyes closed, landscape streaking past out of focus. Natural window light, calm, 85mm.

Capture using a Hasselblad H6D-400c multi-shot with an HC 120mm Macro lens, ISO 64, f/11, focus stacking, cross-polarised HDR studio lighting, 16-bit colour workflow, industrial-design retouching, ultra-high-resolution 4K product photography with the anodised aluminium micro-grain and protein-leather texture razor-sharp.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — a passenger [USING THE PRODUCT] by a [WINDOW OR VEHICLE], eyes closed, [WHAT PASSES BEHIND] streaking past out of focus. Natural window light, calm, 85mm.

Capture using a [CAMERA BODY] with a [LENS], ISO [ISO], f/[APERTURE], focus stacking, [LIGHTING SETUP], 16-bit colour workflow, [RETOUCHING STYLE] retouching, ultra-high-resolution 4K product photography with the [YOUR MATERIAL 1] and [YOUR MATERIAL 2] texture razor-sharp.

The calm, lived-in version: walnut wood, a closed laptop, a mug. The product isn't staged, it's just sitting there — and that's what makes the image believable on a product page.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — the headphones resting on a walnut desk beside a closed laptop and a cup, morning light from the left. Clean, lived-in, editorial.

Capture using a Hasselblad H6D-400c multi-shot with an HC 120mm Macro lens, ISO 64, f/11, focus stacking, cross-polarised HDR studio lighting, 16-bit colour workflow, industrial-design retouching, ultra-high-resolution 4K product photography with the anodised aluminium micro-grain and protein-leather texture razor-sharp.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — the [PRODUCT] resting on a [SURFACE MATERIAL] desk beside [EVERYDAY OBJECT 1] and [EVERYDAY OBJECT 2], morning light from the left. Clean, lived-in, editorial.

Capture using a [CAMERA BODY] with a [LENS], ISO [ISO], f/[APERTURE], focus stacking, [LIGHTING SETUP], 16-bit colour workflow, [RETOUCHING STYLE] retouching, ultra-high-resolution 4K product photography with the [YOUR MATERIAL 1] and [YOUR MATERIAL 2] texture razor-sharp.

No set, one colour, one hard shadow. This shot exists for exactly one thing: holding up as a thumbnail on an Instagram grid or a banner, where a busy photo becomes unreadable.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — the headphones suspended against a flat deep-indigo wall by invisible wire, one hard shadow behind. Minimal, graphic, saturated.

Capture using a Hasselblad H6D-400c multi-shot with an HC 120mm Macro lens, ISO 64, f/11, focus stacking, cross-polarised HDR studio lighting, 16-bit colour workflow, industrial-design retouching, ultra-high-resolution 4K product photography with the anodised aluminium micro-grain and protein-leather texture razor-sharp.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — the [PRODUCT] suspended against a flat [SATURATED BRAND COLOUR] wall by invisible wire, one hard shadow behind. Minimal, graphic, saturated.

Capture using a [CAMERA BODY] with a [LENS], ISO [ISO], f/[APERTURE], focus stacking, [LIGHTING SETUP], 16-bit colour workflow, [RETOUCHING STYLE] retouching, ultra-high-resolution 4K product photography with the [YOUR MATERIAL 1] and [YOUR MATERIAL 2] texture razor-sharp.

Comfort can't be photographed — except like this. A thumb presses into the foam, the leather creases. You're showing a physical sensation, which no spec sheet ever does.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — an extreme macro of the memory-foam earpad compressing under a thumb, the protein leather creasing. Macro, soft light, tactile.

Capture using a Hasselblad H6D-400c multi-shot with an HC 120mm Macro lens, ISO 64, f/11, focus stacking, cross-polarised HDR studio lighting, 16-bit colour workflow, industrial-design retouching, ultra-high-resolution 4K product photography with the anodised aluminium micro-grain and protein-leather texture razor-sharp.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — an extreme macro of the [SOFT PART] compressing under a thumb, the [SURFACE MATERIAL] creasing. Macro, soft light, tactile.

Capture using a [CAMERA BODY] with a [LENS], ISO [ISO], f/[APERTURE], focus stacking, [LIGHTING SETUP], 16-bit colour workflow, [RETOUCHING STYLE] retouching, ultra-high-resolution 4K product photography with the [YOUR MATERIAL 1] and [YOUR MATERIAL 2] texture razor-sharp.

Flat light, no effects, a boarding pass next to it. Deliberately the least pretty shot in the series: it's there as breathing space between two polished images, and it makes the whole set believable.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — the headphones half out of an open canvas weekend bag on an airport bench, boarding pass and passport beside. Documentary, flat light.

Capture using a Hasselblad H6D-400c multi-shot with an HC 120mm Macro lens, ISO 64, f/11, focus stacking, cross-polarised HDR studio lighting, 16-bit colour workflow, industrial-design retouching, ultra-high-resolution 4K product photography with the anodised aluminium micro-grain and protein-leather texture razor-sharp.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — the [PRODUCT] half out of an open [BAG TYPE] on a [PUBLIC PLACE] bench, [CONTEXT OBJECT 1] and [CONTEXT OBJECT 2] beside. Documentary, flat light.

Capture using a [CAMERA BODY] with a [LENS], ISO [ISO], f/[APERTURE], focus stacking, [LIGHTING SETUP], 16-bit colour workflow, [RETOUCHING STYLE] retouching, ultra-high-resolution 4K product photography with the [YOUR MATERIAL 1] and [YOUR MATERIAL 2] texture razor-sharp.

The closing shot: strict symmetry, a 45° shadow, the everyday objects that live alongside the product. A series needs one image that closes it — and this one doubles as the cover visual.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — a strict overhead flat lay on deep indigo: the headphones dead centre flat, surrounded by a coiled cable, a phone, a notebook and a pen. Hard shadow at 45 degrees, symmetry.

Capture using a Hasselblad H6D-400c multi-shot with an HC 120mm Macro lens, ISO 64, f/11, focus stacking, cross-polarised HDR studio lighting, 16-bit colour workflow, industrial-design retouching, ultra-high-resolution 4K product photography with the anodised aluminium micro-grain and protein-leather texture razor-sharp.

Place the product from the reference image into the scene below EXACTLY AS-IS. Its shape, its colours, its materials, its finish and every letter of its text must be 100% identical to the reference — do not recreate it, do not redesign it, do not restyle its typography, and never add any word that is not already on it. Only integrate it naturally into the scene, at true real-world scale, with lighting and reflections that match the scene.

SCENE — a strict overhead flat lay on [BACKGROUND COLOUR]: the [PRODUCT] dead centre flat, surrounded by [OBJECT 1], [OBJECT 2], [OBJECT 3] and [OBJECT 4]. Hard shadow at 45 degrees, symmetry.

Capture using a [CAMERA BODY] with a [LENS], ISO [ISO], f/[APERTURE], focus stacking, [LIGHTING SETUP], 16-bit colour workflow, [RETOUCHING STYLE] retouching, ultra-high-resolution 4K product photography with the [YOUR MATERIAL 1] and [YOUR MATERIAL 2] texture razor-sharp.

Ten seconds, ten shots, nobody in frame. The product floats and turns, only the background changes at each cut — always inside the same palette. It's the most profitable format going: no casting, no location, and it works on any product.

SCENE CONTEXT
A 10-second vertical kinetic product spot for NOVA, over-ear studio headphones. No people, no location. A single indigo and steel colour world, the headphones levitating and rotating in every shot, roughly one second per shot, the backdrop changing on every cut inside the indigo and steel palette.

ACTIVE REFERENCES
@image1 - the NOVA headphones. Over-ear headphones with matte charcoal aluminium earcups in a fine brushed grain, soft memory-foam earpads in dark grey protein leather, a slim brushed-steel headband arc, and a small polished NOVA wordmark etched into the outer face of the left cup. 100% matches the reference.

LOCATION MAP
Seamless studio colour fields only, no floor line and no horizon until the final beat, when a mirror black reflective mirror floor enters frame. Each shot uses one backdrop from the indigo and steel palette: smooth indigo gradient, cool steel bokeh, crossing electric blue light bars, drifting cold haze, or a near-black field.

FIRST FRAME / BLOCKING
Frame opens in extreme macro on the brushed aluminium grain of an earcup, a deep indigo glow behind it.

FORMAT MODE
Timed multishot, eleven shots. Cuts only at the specified points, the camera does not cut on its own.

OPTICS
Physical cine lens, 180 degree shutter motion blur, macro-capable rendering.

CAMERA
0.0-0.8s - 12 degree FOV. Accelerating macro creep across the brushed aluminium micro-grain.
0.8s HARD CUT
0.8-1.6s - 18 degree FOV. Fast 90 degree orbit around the headphones levitating and rotating on a deep indigo gradient.
1.6s SMASH CUT
1.6-2.4s - 12 degree FOV. High-speed macro, a shockwave of fine dust blowing outward from the earcup past the lens.
2.4s HARD CUT
2.4-3.2s - 29 degree FOV. Push-in as the steel headband arc rotates open around the levitating headphones on steel bokeh.
3.2s WHIP CUT
3.2-4.0s - 18 degree FOV. Fast arc, the headphones levitating between crossing electric blue light bars.
4.0s WHIP CUT
4.0-4.8s - 12 degree FOV. Whip into extreme macro on the etched NOVA wordmark, a mirror highlight crossing its letters.
4.8s SMASH CUT
4.8-5.4s - 107 degree FOV. Whip pan through drifting cold haze, the headphones flashing past.
5.4s HARD CUT
5.4-6.2s - 12 degree FOV. Locked macro, a thumb pressing into the memory-foam earpad and the leather springing slowly back.
6.2s SMASH CUT
6.2-7.0s - 18 degree FOV. Fast tilt up the headphones, the steel headband arc filling frame.
7.0s MATCH CUT
7.0-7.8s - 29 degree FOV. The electric blue of the light bar matches into a electric blue light bar, camera arcing at 30 km/h across a near-black void.
7.8s HARD CUT
7.8-10.0s - 47 degree FOV. The headphones descends and lands on a mirror black reflective mirror floor, settling with its reflection, camera pushing in steadily.

ACTION
Aluminium grain fills frame. The headphones levitate and rotate. A dust shockwave blows outward. The headband arc rotates open. A highlight crosses the etched wordmark. The earpad compresses and springs back. The headphones land on a mirror floor and settle.

PHYSICS
The headphones are roughly 300 grams. The memory foam compresses under pressure and recovers slowly. The steel arc has real spring tension. Brushed aluminium reflects with a directional anisotropic highlight.

LIGHTING
Hard specular key from camera-left at 5400K raking across the headphones, a tight rim light on the right edge, electric blue practicals in the background. White balance fixed at 5400K. Atmospheric haze at 20%.

COLOR GRADE
60:30:10 - deep indigo dominant, charcoal secondary, steel accent.

AUDIO
Non-diegetic kinetic design: sharp whooshes on each cut, a low sub sweep, a soft leather compression, a metallic ring, a low sub hit on the final landing.

STYLE
Photorealistic commercial cinematography, 24fps smooth motion, fine film grain, 8K detail, high-energy kinetic pacing.

OUTPUT SETTINGS
9:16 vertical, total duration 10 seconds.

POSITIVE LOCKS
The headphone design stays identical to @image1 in every shot: matte charcoal brushed aluminium earcups, dark grey protein-leather earpads, slim brushed-steel headband arc, and the polished etched NOVA wordmark on the left cup, legible. The set contains only seamless colour fields and, in the final beat, the mirror floor. Every shot contains visible camera movement.

SCENE CONTEXT
A 10-second vertical kinetic product spot for [BRAND NAME], [PRODUCT TYPE]. No people, no location. A single [COLOUR 1] and [COLOUR 2] colour world, the [PRODUCT] levitating and rotating in every shot, roughly one second per shot, the backdrop changing on every cut inside the [PALETTE] palette.

ACTIVE REFERENCES
@image1 - the [BRAND NAME] [PRODUCT]. [FULL PRODUCT DESCRIPTION — every material, every finish, every word written on it]. 100% matches the reference.

LOCATION MAP
Seamless studio colour fields only, no floor line and no horizon until the final beat, when a [FINAL SURFACE] enters frame. Each shot uses one backdrop from the palette: [BACKDROP 1], [BACKDROP 2], [BACKDROP 3], [BACKDROP 4], or a near-black field.

FIRST FRAME / BLOCKING
Frame opens in extreme macro on [THE MATERIAL DETAIL THAT SELLS THE PRODUCT], a [COLOUR] glow behind it.

FORMAT MODE
Timed multishot, eleven shots. Cuts only at the specified points, the camera does not cut on its own.

OPTICS
Physical cine lens, 180 degree shutter motion blur, macro-capable rendering.

CAMERA
0.0-0.8s - 12 degree FOV. Accelerating macro creep across [THE MATERIAL].
0.8s HARD CUT
0.8-1.6s - 18 degree FOV. Fast 90 degree orbit around the [PRODUCT] levitating and rotating on a [COLOUR] gradient.
1.6s SMASH CUT
1.6-2.4s - 12 degree FOV. High-speed macro, [A PARTICLE EFFECT COMING FROM THE PRODUCT] past the lens.
2.4s HARD CUT
2.4-3.2s - 29 degree FOV. Push-in as [A MOVING PART OF THE PRODUCT] opens around it on [BACKDROP].
3.2s WHIP CUT
3.2-4.0s - 18 degree FOV. Fast arc, the [PRODUCT] levitating between [LIGHT ELEMENTS].
4.0s WHIP CUT
4.0-4.8s - 12 degree FOV. Whip into extreme macro on the [LOGO OR PRINTED NAME], a mirror highlight crossing its letters.
4.8s SMASH CUT
4.8-5.4s - 107 degree FOV. Whip pan through [AN ATMOSPHERE: haze, dust, steam], the [PRODUCT] flashing past.
5.4s HARD CUT
5.4-6.2s - 12 degree FOV. Locked macro, [THE ONE GESTURE THAT PROVES THE MATERIAL — a press, a pour, a stretch].
6.2s SMASH CUT
6.2-7.0s - 18 degree FOV. Fast tilt up the [PRODUCT], [ITS MOST GRAPHIC PART] filling frame.
7.0s MATCH CUT
7.0-7.8s - 29 degree FOV. [A COLOUR IN THE PRODUCT] matches into [THE SAME COLOUR IN THE SET], camera arcing across a near-black void.
7.8s HARD CUT
7.8-10.0s - 47 degree FOV. The [PRODUCT] descends and lands on [THE FINAL SURFACE], settling with its reflection, camera pushing in steadily.

ACTION
[THE SAME ELEVEN BEATS, RETOLD IN ONE PLAIN PARAGRAPH — this is what the model actually follows].

PHYSICS
The [PRODUCT] weighs roughly [WEIGHT]. [HOW ITS MAIN MATERIAL BEHAVES: what compresses, what springs back, what pours, what shatters]. [ITS SURFACE] reflects with a [TYPE] highlight.

LIGHTING
Hard specular key from camera-left at [COLOUR TEMPERATURE] raking across the [PRODUCT], a tight rim light on the right edge, [PRACTICAL LIGHTS] in the background. White balance fixed. Atmospheric haze at 20%.

COLOR GRADE
60:30:10 - [DOMINANT COLOUR] dominant, [SECONDARY] secondary, [ACCENT] accent.

AUDIO
Non-diegetic kinetic design: sharp whooshes on each cut, a low sub sweep, [THE ONE PHYSICAL SOUND THE PRODUCT ITSELF MAKES], a low sub hit on the final landing.

STYLE
Photorealistic commercial cinematography, 24fps smooth motion, fine film grain, 8K detail, high-energy kinetic pacing.

OUTPUT SETTINGS
9:16 vertical, total duration 10 seconds.

POSITIVE LOCKS
The [PRODUCT] design stays identical to @image1 in every shot: [REPEAT THE MATERIALS AND THE EXACT TEXT], legible. The set contains only seamless colour fields and, in the final beat, [THE FINAL SURFACE]. Every shot contains visible camera movement.

The exact opposite of hyper motion: camera on a dolly, never handheld, four beats of two and a half seconds. One place, one person, one progression. This is what you sell for the most, because it looks like a real ad.

SCENE CONTEXT
A 10-second vertical commercial spot for NOVA, over-ear studio headphones. Night in a small home studio as someone works on a track. Composed camera on a dolly and a crane, never handheld. Four beats in a structured arc, roughly two and a half seconds each.

ACTIVE REFERENCES
@image1 - the NOVA headphones. Over-ear headphones with matte charcoal brushed aluminium earcups, dark grey protein-leather memory-foam earpads, a slim brushed-steel headband arc, and a polished NOVA wordmark etched into the left cup. 100% matches the reference.

LOCATION MAP
A small home studio: a desk with a monitor and a controller, foam panels on one wall, a window with city lights, one desk lamp. The set contains only what is listed here.

FIRST FRAME / BLOCKING
Frame opens on the city lights through the window, the room dark, the monitor glowing.

FORMAT MODE
Timed multishot, four shots. Cuts only at the specified points, the camera does not cut on its own.

OPTICS
Physical cine lens, 180 degree shutter motion blur, clean spherical rendering.

CAMERA
0.0-2.5s ESTABLISHING - 63 degree FOV. Slow dolly from the window across the dark room toward the desk at 2 km/h, the monitor glow growing.
2.5s HARD CUT
2.5-5.0s PRODUCT IN USE - 47 degree FOV. Slow push-in as a man in his twenties lifts the headphones off the desk and settles them onto his ears with both hands.
5.0s HARD CUT
5.0-7.5s LIFESTYLE - 29 degree FOV. Slow lateral dolly as he works the controller with his eyes closed, the earcup catching the monitor light in the foreground.
7.5s HARD CUT
7.5-10.0s HERO - 63 degree FOV. Slow crane rise pulling back, the headphones back on the desk beside the controller, the etched wordmark catching the lamp, the city still behind.

ACTION
City lights through a window, a monitor glowing. A man lifts the headphones and settles them on. He works with his eyes closed. The headphones return to the desk.

PERFORMANCE
He moves absorbed and unselfconscious, small adjustments, eyes closed for long stretches. Nobody performs for the lens.

PHYSICS
The headphones are roughly 300 grams. The memory foam compresses onto the ears and recovers. The steel arc has real spring. Brushed aluminium catches a directional highlight.

LIGHTING
Monitor glow at 6500K from camera-front, one warm desk lamp at 3000K from the right, city lights bokeh behind. Atmospheric haze at 15%.

COLOR GRADE
60:30:10 - deep indigo dominant, charcoal secondary, monitor-blue accent.

AUDIO
Diegetic only: a faint muffled beat from the cups, a controller fader, a chair creak, distant traffic. No dialogue, no subtitles.

STYLE
Photorealistic commercial cinematography, 24fps smooth motion, fine film grain, 8K detail, unhurried editorial pacing.

OUTPUT SETTINGS
9:16 vertical, total duration 10 seconds.

POSITIVE LOCKS
The headphone design stays identical to @image1 in every shot: matte charcoal brushed aluminium earcups, dark grey earpads, slim steel headband arc, and the etched NOVA wordmark legible. The people keep the same faces, hair and clothing across every cut. Every shot contains visible camera movement. ABSOLUTELY NO PACKSHOT: the headphones is never shown isolated on a studio backdrop and never appears without a person in the scene.

SCENE CONTEXT
A 10-second vertical commercial spot for [BRAND NAME], [PRODUCT TYPE]. [TIME OF DAY] in [THE PLACE] as someone [WHAT THEY ARE DOING]. Composed camera on a dolly and a crane, never handheld. Four beats in a structured arc, roughly two and a half seconds each.

ACTIVE REFERENCES
@image1 - the [BRAND NAME] [PRODUCT]. [FULL PRODUCT DESCRIPTION — every material, every finish, every word written on it]. 100% matches the reference.

LOCATION MAP
[THE SET, DESCRIBED ONCE AND FOR ALL: the furniture, the light sources, what is on the walls, what is visible through the window]. The set contains only what is listed here.

FIRST FRAME / BLOCKING
Frame opens on [THE ESTABLISHING DETAIL], the room dark, [THE ONE THING THAT GLOWS] glowing.

FORMAT MODE
Timed multishot, four shots. Cuts only at the specified points, the camera does not cut on its own.

OPTICS
Physical cine lens, 180 degree shutter motion blur, clean spherical rendering.

CAMERA
0.0-2.5s ESTABLISHING - 43 degree FOV. Slow dolly from [WHERE] toward [WHAT], the [LIGHT SOURCE] growing.
2.5s HARD CUT
2.5-5.0s PRODUCT IN USE - 47 degree FOV. Slow push-in as the person [THE SINGLE GESTURE WITH THE PRODUCT — one movement, nothing else].
5.0s HARD CUT
5.0-7.5s LIFESTYLE - 29 degree FOV. Slow lateral dolly as they [THE WIDER MOMENT THAT SHOWS THE LIFE AROUND THE PRODUCT].
7.5s HARD CUT
7.5-10.0s HERO - 63 degree FOV. Slow crane rise pulling back, the [PRODUCT] [WHERE IT ENDS UP], [WHAT STAYS BEHIND].

ACTION
[THE FOUR BEATS RETOLD IN ONE PLAIN PARAGRAPH — this is what the model actually follows].

PERFORMANCE
[HOW THE PERSON BEHAVES: absorbed, unhurried, never acting for the camera. Small gestures, no eye contact with the lens].

PHYSICS
The [PRODUCT] weighs roughly [WEIGHT]. [HOW IT MOVES, SETTLES, POURS OR RESISTS IN A REAL HAND].

LIGHTING
[THE MOTIVATED SOURCES: which lamp, which window, which screen]. Practical lights only, no visible film lighting. White balance fixed at [COLOUR TEMPERATURE].

COLOR GRADE
60:30:10 - [DOMINANT COLOUR] dominant, [SECONDARY] secondary, [ACCENT] accent.

AUDIO
Diegetic only: [THE TWO OR THREE REAL SOUNDS OF THE ROOM], and the one sound the product itself makes. No music, no voice-over.

STYLE
Photorealistic commercial cinematography, 24fps, fine film grain, 8K detail, composed and unhurried.

OUTPUT SETTINGS
9:16 vertical, total duration 10 seconds.

POSITIVE LOCKS
The [PRODUCT] stays identical to @image1 in every shot: [REPEAT THE MATERIALS AND THE EXACT TEXT], legible. No on-screen text, no subtitles, no logo overlay. Every shot is on a dolly or a crane, never handheld.

You never generate a UGC video in one go. You build this still image first in GPT Image 2, you approve it, and only then do you animate it. Getting the still wrong costs $0.20; getting the video wrong costs seven times more.

The whole prompt is working to kill the pretty: no background blur, no colour grade, no studio light, sensor noise, framing that misses, unretouched skin. It's the exact opposite of the eight visuals before it — and that's why it's written in prose, not JSON.

Use the attached image as the exact product reference.

THIS IS A FRAME GRABBED FROM A PHONE VIDEO, not a photograph. Vertical phone video, the phone propped on a tripod so BOTH of their hands stay free — there is never a phone in their hands.

A young man in his twenties, fade haircut, wearing a plain black tee. They are mid-sentence, caught talking — mouth open on a word, eyebrows slightly raised, eyes locked on the lens. Not smiling, not posing.

SETTING — his desk setup at night, a monitor glow behind him, cables and a keyboard in frame. It looks real and lived-in, not styled for a shoot, with ordinary everyday things around them.

FRAMING — a real front-camera selfie: the head fills most of the frame with the wide-angle distortion of a selfie lens. The crop is imperfect, the top of the head lightly cut by the frame edge, something intruding at the bottom corner. Slightly off-centre.

IMAGE QUALITY — raw front-camera video still: slightly soft, visible sensor noise, heavy phone HDR flattening the contrast, a window or lamp blown out to white. No cinematic depth of field, no colour grading, no studio light.

SKIN — real and unretouched: shine on the forehead and nose, visible pores, uneven tone, stray flyaway hairs. No beauty filter, no smoothing.

THE PRODUCT — they are wearing the headphones around their neck, then lift them onto their ears with both hands. It keeps exactly the shape, the colours, the materials and every letter of the text of the reference image, at true real-world scale.

The image is the bare video frame itself: no interface, no icons, no counters, no buttons, no progress bar, no timecode, no captions, no watermark.

Use the attached image as the exact product reference.

THIS IS A FRAME GRABBED FROM A PHONE VIDEO, not a photograph. Vertical phone video, the phone propped on a tripod so BOTH of their hands stay free — there is never a phone in their hands.

[THE PERSON: age, hair, plain unbranded clothing]. They are mid-sentence, caught talking — mouth open on a word, eyebrows slightly raised, eyes locked on the lens. Not smiling, not posing.

SETTING — [A REAL ROOM WHERE THIS PRODUCT ACTUALLY LIVES], [WHAT IS VISIBLE AROUND THEM]. It looks real and lived-in, not styled for a shoot, with ordinary everyday things around them.

FRAMING — a real front-camera selfie: the head fills most of the frame with the wide-angle distortion of a selfie lens. The crop is imperfect, the top of the head lightly cut by the frame edge, something intruding at the bottom corner. Slightly off-centre.

IMAGE QUALITY — raw front-camera video still: slightly soft, visible sensor noise, heavy phone HDR flattening the contrast, a window or lamp blown out to white. No cinematic depth of field, no colour grading, no studio light.

SKIN — real and unretouched: shine on the forehead and nose, visible pores, uneven tone, stray flyaway hairs. No beauty filter, no smoothing.

THE PRODUCT — [THE ONE GESTURE THEY MAKE WITH IT — a single movement, nothing else]. It keeps exactly the shape, the colours, the materials and every letter of the text of the reference image, at true real-world scale.

The image is the bare video frame itself: no interface, no icons, no counters, no buttons, no progress bar, no timecode, no captions, no watermark.

The approved still becomes the first frame of the video. The phone stays on a tripod, both hands free, a single unbroken take — and the person says exactly two lines: one at the start, one at the end. In between, she says nothing. That silence is what stops the model inventing dialogue.

Continue this phone video from the exact frame shown. The phone stays propped on a tripod the whole time, so BOTH of their hands stay free — there is never a phone in their hands. ONE SINGLE CONTINUOUS TAKE, no cuts, no scene changes.

They speak ONLY these two lines, each said ONCE and never repeated:
Line 1, at the very start: "I've tried every pair under three hundred."
Line 2, at the very end: "These are the ones I actually keep on all day."
Between the two lines they say NOTHING at all — silent, only acting.

Beat 1 — already mid-sentence, delivering line 1 straight into the lens with a small eyebrow raise.
Beat 2 — SILENT: they lift the headphones off their neck with both hands and turn one earcup toward the lens so the etched NOVA wordmark catches the light. Eye contact kept, lips pressed together, no words.
Beat 3 — SILENT: they settle the headphones onto their ears with both hands and give a small nod.
Beat 4 — leans back, shrugs one shoulder and delivers line 2 with a small closed-mouth smile.

Keep the raw look of the frame: the head stays large with selfie wide-angle distortion, the crop stays imperfect, the window stays blown out white, the image stays slightly soft with phone HDR flatness and sensor noise. Natural body sway throughout, never still. Real unretouched skin.

The product stays exactly as in the frame in every beat: the brushed charcoal aluminium earcups, the dark grey earpads, the steel headband and the etched NOVA wordmark, sharp and unchanged, never distorted, never resized and never losing its text.

Close-mic phone audio with the voice up front, faint room tone, no music. Raw iPhone footage, TikTok storytime energy, no-filter realism. Vertical 9:16. NO SUBTITLES, NO TEXT OR EMOJIS ON SCREEN.

Continue this phone video from the exact frame shown. The phone stays propped on a tripod the whole time, so BOTH of their hands stay free — there is never a phone in their hands. ONE SINGLE CONTINUOUS TAKE, no cuts, no scene changes.

They speak ONLY these two lines, each said ONCE and never repeated:
Line 1, at the very start: "[THE OBJECTION THE VIEWER ALREADY HAS IN MIND — what they have tried, what disappointed them]"
Line 2, at the very end: "[WHAT THEY KEPT DOING WITH IT — a fact about their life, never a slogan]"
Between the two lines they say NOTHING at all — silent, only acting.

Beat 1 — already mid-sentence, delivering line 1 straight into the lens with a small eyebrow raise.
Beat 2 — SILENT: [THE FIRST GESTURE — they pick up or open the product and turn it so its name catches the light]. Eye contact kept, lips pressed together, no words.
Beat 3 — SILENT: [THE SECOND GESTURE — they actually use it, once, the way anyone would] and give a small nod.
Beat 4 — leans back, shrugs one shoulder and delivers line 2 with a small closed-mouth smile.

Keep the raw look of the frame: the head stays large with selfie wide-angle distortion, the crop stays imperfect, the window stays blown out white, the image stays slightly soft with phone HDR flatness and sensor noise. Natural body sway throughout, never still. Real unretouched skin.

The product stays exactly as in the frame in every beat: [REPEAT ITS MATERIALS, ITS COLOURS AND EVERY LETTER OF ITS TEXT], sharp and unchanged, never distorted, never resized and never losing its text.

Close-mic phone audio with the voice up front, faint room tone, no music. Raw iPhone footage, TikTok storytime energy, no-filter realism. Vertical 9:16. NO SUBTITLES, NO TEXT OR EMOJIS ON SCREEN.