Disclaimer: This is an independent creative test made with AI, for demonstration only. It isn't an ad for any brand shown or named, and isn't affiliated with, sponsored or endorsed by them. All trademarks belong to their owners
Nano Banana Pro + Kling 3.0 - a chestnut horse carries a tan bag by its top handle
A chestnut horse brings a tan top-handle bag to a woman in oxblood, told as numbered scenes
Tested by Nouamane Benbrahim
In today's "animal frames" series I did a test spot styled on Hermès' look. A woman in head-to-toe oxblood leather walks into a white studio, a chestnut horse walks in holding a tan Kelly bag by its handle, and they leave together before the logo snaps on. Hermès isn't a client, just a test. The thing I want to show here is how I wrote the clips: as short numbered scenes, with every hand and every handle spelled out.
Here's my exact process.
1. An empty room
The studio started as a prompt with nothing else: white curved wall, pale floor, tall window on the left.
Exact prompt
Create a new photorealistic image. This is a photograph taken inside a minimalist white studio from the start — not a composite. Shoot the whole space natively, with a single unified natural light source across every surface. THE VIBE: Austere, hushed, expensive emptiness — the pared-back quiet-luxury minimalism of a high-fashion campaign set before anything is placed in it. The room feels intellectual and cool, precise but not sterile, where the quality of light and the fall of a shadow are the only events. Stillness and generous negative space. THE SETTING: A clean, modern white studio — a seamless matte-white cyclorama sweep curving gently from floor to wall with no visible seam, its surface carrying the faintest real texture and tonal variation so it reads as painted plaster, not a flat digital void. A polished pale microcement floor with a soft satin sheen, subtle and almost imperceptible reflections. One tall floor-to-ceiling window just out of frame to the left. Architectural, uncluttered, refined proportions. THE LIGHT: Soft directional daylight raking in low from the left through the unseen window, casting long, clean, elongated geometric shadows across the white sweep and floor — the crisp diagonal of a window frame and mullions stretched across the wall. Gentle falloff from bright highlight to soft grey shadow, smooth gradients, no harsh clipping. Cool-neutral white balance with the faintest warmth where the sun lands. THE KEY DETAILS: The natural window-cast shadows are the subject — long, soft-edged diagonal bars and a rectangle of light on the floor. Delicate dust motes suspended in the light shaft. Subtle tonal gradation across the seamless wall. THE MOOD: Editorial, muted, cold-clinical calm with a breath of warmth. Restrained luxury. A clean neutral grade, whites held just off pure white, soft grey shadows, nothing oversaturated. THE COMPOSITION: Wide architectural frame, eye level, straight-on and balanced. Vast negative space with the shadows placed on a rule-of-thirds diagonal as the leading lines; low emphasis, open airy upper frame. THE CAMERA: Cinematic editorial architectural still — wide framing, eye-level straight position, deep focus with everything sharp edge to edge, lit exclusively by the single window daylight source with no studio strobes and no artificial separation, a clean cool-neutral naturalistic grade in the vein of Roger Deakins' understated natural light. Light falls off gently toward the frame edges. Hyperreal, tactile, every surface present.
Then a second pass of the same room with the floor turned white.
Exact prompt
Create a new photorealistic image, but the floor is now white. Preserve everything else from the reference exactly — the seamless matte-white cyclorama wall, the soft low directional daylight from the left, the long clean geometric window-cast shadows, the composition, framing, grade and mood all stay identical. THE FLOOR (CHANGED): The floor is now a clean matte white, continuous with the seamless white cyclorama sweep so wall and floor read as one unbroken white surface, no visible seam. A soft satin sheen with subtle, almost imperceptible reflections, the faintest real texture and tonal variation so it reads as painted plaster rather than a flat digital void — never pure clipped white. THE SETTING (LOCKED): The minimalist white studio, the seamless curving cyclorama, the tall floor-to-ceiling window just out of frame to the left. Do NOT redesign the environment. THE LIGHT (LOCKED): Soft directional daylight raking in low from the left, casting long, clean, elongated geometric window-frame and mullion shadows across the white sweep and now the white floor, with gentle falloff to soft grey and smooth gradients. Cool-neutral white balance with the faintest warmth where the sun lands. Delicate dust motes in the light shaft. THE MOOD (LOCKED): Editorial, muted, cold-clinical calm with a breath of warmth, restrained luxury, clean neutral grade, whites held just off pure white. THE COMPOSITION (LOCKED): Wide architectural frame, eye level, straight-on, vast negative space, the shadows on a rule-of-thirds diagonal as leading lines, open airy upper frame. THE CAMERA (LOCKED): Cinematic editorial architectural still, deep focus everything sharp edge to edge, lit exclusively by the single window daylight source, clean cool-neutral naturalistic grade, gentle edge falloff. Hyperreal and tactile.
2. Dress her for riding
No product photos here, the whole look is written out. I went for an equestrian, twilight mood in a deep oxblood palette: a narrow oxblood leather coat cinched with a slim belt, slim dark jodhpurs tucked into tall glossy cognac riding boots, cognac gloves, and a silk scarf knotted at the throat in navy, oxblood and mustard. The empty room is the only reference.
I asked for no brand text or logos on any garment and kept her hands empty, since the bag comes later.
Exact prompt
Create a new photorealistic image. This is a photograph taken inside the same minimalist white studio from the start — not a composite. A woman stands in the space dressed head-to-toe in Hermès Fall/Winter 2026 equestrian-luxe style; rebuild the whole scene as if shot natively here, one unified natural light source across her and the room. THE VIBE: Austere, hushed, expensive minimalism meets nocturnal equestrian elegance — a high-fashion campaign frame. Twilight-mood luxury, dusky and enigmatic, quietly powerful. She is the single rich event in a vast field of white negative space. IDENTITY LOCK: A woman in her late twenties, tall and statuesque with an elegant editorial build. Deep warm brown skin with a natural luminous sheen. Dark hair slicked back sleek and understated into a low, polished chignon, barely-there and severe-chic, not a strand loose. Dark brown almond eyes, elegant high cheekbones, full soft neutral lip. After-hours beauty: smoky charcoal-taupe eye makeup softly blended, subtle contour, faint under-eye dimension, matte skin — editorial but not heavy. THE SUBJECT: She wears a cohesive head-to-toe Hermès FW26 look in a deep oxblood palette — a sleek, narrow, aerodynamic oxblood leather coat, mid-length and impeccably tailored, with subtle spiraling zip detailing and a slim leather belt cinching the waist over slim dark jodhpur-style riding trousers, tucked into tall glossy cognac-brown leather thigh-high riding boots. Fine supple leather gloves in matching cognac. A silk carré scarf knotted softly at her throat in a muted twilight print of navy, oxblood and glints of mustard. No handbag, hands empty. No visible brand text or logos on any garment. She stands in a poised, confident equestrian editorial stance: weight on her right leg, left knee softly bent, left hand resting on her hip, right arm relaxed at her side, shoulders squared and angled a few degrees off the lens, chin lifted, gaze sent just off-camera to the left toward the light. Composed, commanding, effortless. THE FACE: Natural skin texture, no airbrushing, no plastic or waxy skin, real skin with subtle tonal variation, fine peach-fuzz catching the soft light, faint natural sheen on the cheekbones. Eyes with a natural catchlight and individual lashes. Soft organic light. THE SETTING (LOCKED, from the reference): The clean modern white studio — the seamless matte-white cyclorama sweep curving unbroken into the continuous matte-white floor, wall and floor as one white surface with faint painted-plaster texture and a soft satin floor sheen, the tall window just out of frame to the left. Do NOT redesign the environment. THE LIGHT (LOCKED, from the reference): Soft directional daylight raking in low from the left through the unseen window, casting long, clean, elongated geometric window-frame and mullion shadows across the white floor. That same single source lights the woman — soft key from her left, gentle falloff across the oxblood leather to soft shadow on her right, her own long soft-edged shadow cast to the right, aligned with the existing window shadows. Cool-neutral white balance with the faintest warmth where the sun lands; the warm oxblood and cognac glow against the cool white. Delicate dust motes in the light shaft. THE MOOD: Editorial, muted, cold-clinical calm warmed by the rich oxblood and cognac leather. Restrained twilight luxury, quiet power. Clean neutral grade, whites held just off pure white, deep saturated oxblood, soft grey shadows. THE COMPOSITION: Wide architectural frame, eye level, straight-on. She stands off-centre on the left rule-of-thirds line, full length in frame with generous headroom and vast open white negative space filling the rest, the window shadows leading diagonally toward her. Airy, balanced, unhurried. THE CAMERA: Cinematic editorial fashion still — wide-to-medium framing, eye-level straight position, deep focus with subject and space sharp, lit exclusively by the single window daylight source with no studio strobes and no artificial rim separation, a clean cool-neutral naturalistic grade in the vein of Roger Deakins' understated natural light. Gentle light falloff toward the frame edges. Hyperreal, tactile, present.
3. Add the horse and the bag
One reference again: her pose frame, which keeps her, the outfit and the room. The horse and the bag both come from words. The bag is a tan Kelly with its front flap, two straps meeting a turn-lock and gold hardware, and its warm tan echoes her boots.
She stands on the left, the horse on the right with its head lowered toward her. Her right hand strokes its muzzle and her left holds the bag forward, like she just took it. I also asked for the horse's shadow to fall the same way as hers, so it sits in the room instead of looking pasted in.
Fitting detail: the Hermès logo itself is a horse and carriage.
Exact prompt
Create a new photorealistic image. This is a photograph taken inside the same minimalist white studio — not a composite. The same woman is posed petting a calm chestnut horse that stands beside her, having just delivered her a Hermès Kelly handbag, which she holds. Rebuild the whole scene natively in the space with one unified light source across the woman, the horse, and the room. THE VIBE: Austere, hushed, expensive minimalism with a surreal, tender, equestrian edge — a high-fashion Hermès campaign frame. Twilight-luxe warmth against an all-white void. The story reads instantly: her horse has brought her the bag. IDENTITY LOCK: Preserve the woman exactly from the first reference — late twenties, tall and statuesque, deep warm brown skin with a luminous sheen, dark hair slicked into a sleek low chignon, dark almond eyes, smoky after-hours eye makeup, soft neutral lip. She wears the identical head-to-toe oxblood Hermès FW26 look: the sleek narrow oxblood leather coat cinched with a slim belt over slim dark jodhpurs tucked into tall glossy cognac thigh-high riding boots, matching cognac leather gloves, and the knotted silk carré scarf in a muted navy-oxblood-mustard twilight print. Do NOT source her face, hair, or outfit from anywhere else, and keep no brand text or logos on the garments. THE SUBJECT: She stands on the LEFT of the frame beside the horse on her right, body angled toward it with an elegant soft lean. Her right hand (the one nearest the horse, on the right side of the frame) reaches up and gently strokes the horse's muzzle mid-caress. Her left hand holds a structured Hermès Kelly handbag by its single top handle, held slightly forward as though just received. Her head tilts toward the horse with a soft, serene, affectionate expression and a faint calm smile. Poised and effortless. THE FACE: Natural skin texture, no airbrushing, no plastic or waxy skin, subtle tonal variation, fine peach-fuzz in the soft light, natural catchlight and individual lashes. Soft organic light. THE KEY DETAILS: The handbag — a classic Hermès Kelly, structured trapezoidal top-handle bag in rich tan-cognac leather with the signature front flap, two straps meeting a turn-lock closure, gold-toned hardware, holding its crisp architectural shape. Held in her left hand, its warm tan echoing her boots. THE HORSE: A beautiful full-grown chestnut horse — warm reddish-brown coat with a glossy sheen, flaxen-to-dark mane, gentle dark eyes — stands calmly close beside her on the RIGHT of the frame, its body angled slightly into the frame, head lowered and turned toward her hand as it is petted, ears soft and forward, composed and serene. Realistic coat texture with individual hairs and soft directional sheen catching the window light along its neck and flank. It is photographed in the same studio under the same window daylight, casting its own long soft-edged shadow to the right that matches the direction and softness of the woman's shadow — fully grounded in the space, sharing her light, not pasted in. THE SETTING (LOCKED, from the first reference): The seamless matte-white cyclorama sweep curving unbroken into the continuous matte-white floor, faint painted-plaster texture, soft satin floor sheen, the tall window just out of frame to the left. Do NOT redesign the environment. THE LIGHT (LOCKED, from the first reference): Soft directional daylight raking in low from the LEFT, long clean window-frame and mullion shadows falling to the RIGHT across the white floor. One source lights woman, horse and room; gentle falloff to soft grey; cool-neutral white balance with the faintest warmth where the sun lands; the oxblood, cognac and chestnut glowing warm against the cool white. Delicate dust motes in the light shaft. THE MOOD: Editorial, muted, cold-clinical calm warmed by rich oxblood, cognac and chestnut, with a surreal tender edge. Restrained twilight luxury, quiet power. Clean neutral grade, whites just off pure white, soft grey shadows. THE COMPOSITION: Wide architectural frame, eye level, straight-on. The woman on the LEFT, the chestnut horse filling the RIGHT, the two forming one intimate unified group across the lower-centre of the frame, the tan Kelly on her left as the warm focal accent. Generous open white negative space above; the window shadows lead diagonally across. Balanced, airy, cinematic. THE CAMERA: Cinematic editorial fashion still — wide framing, eye-level straight position, deep focus with woman, horse and space sharp, lit exclusively by the single window daylight source with no studio strobes and no artificial rim separation, a clean cool-neutral naturalistic grade in the vein of Roger Deakins' understated natural light. Gentle edge falloff. Hyperreal, tactile, present.
4. The logo card
The empty room plus a file of the Hermès logo, the carriage above the HERMÈS PARIS wordmark, in solid black, level and centred.
Exact prompt
Create a new photorealistic image — a minimalist luxury fashion-film end-card. Take the empty white studio scene from the first reference and place the black Hermès logo from the second reference onto it as a clean, crisp graphic title. THE VIBE: Austere, hushed, expensive minimalism — a high-fashion campaign sign-off frame. Vast white emptiness, one dark logo lockup, nothing else. Restrained, iconic, still. THE SETTING (from the first reference): The clean modern white studio — the seamless matte-white cyclorama sweep curving unbroken into the continuous matte-white floor, faint painted-plaster texture, soft satin floor sheen. Preserve it exactly. THE LOGO (from the second reference): The Hermès logo lockup — the Duc carriage motif (a horse drawing a light carriage with a standing coachman) above the serif capital wordmark HERMÈS with PARIS beneath it — the exact artwork, letterforms, spacing and proportions from the second reference, reproduced precisely and legibly with clean sharp edges. Rendered in solid deep black, perfectly level and horizontal, centred left-to-right, sitting in the clean upper-middle white space of the frame at an elegant restrained scale (roughly a third of the frame width), like a crisp printed campaign title laid over the scene. Do NOT distort, restyle, misspell, redraw, or add any other text or elements. THE LIGHT (from the first reference): Soft directional daylight raking in low from the left, long clean window-frame and mullion shadows falling to the right across the lower white floor. Cool-neutral white balance with the faintest warmth. Delicate dust motes in the light shaft. THE MOOD: Editorial, muted, cold-clinical calm with a breath of warmth. Restrained luxury. Clean neutral grade, whites held just off pure white, the logo deep solid black. THE COMPOSITION: Wide frame, eye level, straight-on, symmetrical. The black logo centred in the upper-middle white negative space; the soft window shadows across the lower floor as the only other element; generous open white all around. Balanced, airy, iconic. THE CAMERA: Cinematic editorial still — wide framing, eye-level straight position, deep focus everything sharp, lit exclusively by the single window daylight source, clean cool-neutral naturalistic grade. Gentle edge falloff. The logo itself is a flat crisp graphic, not lit or textured. Hyperreal, tactile studio; sharp clean logo.
5. Walk-in, in four scenes
For this spot I wrote all three clips as numbered scenes. For the walk-in: hold a beat on the empty room, she enters from the right edge with a slow riding stride, she arrives and eases into her pose, she holds it while the scarf settles.
Exact prompt
Create a new video where an elegant woman in a head-to-toe oxblood Hermès equestrian look walks slowly and smoothly into an empty minimalist white studio from the right and settles into a poised, confident stance, lit throughout by soft daylight from the left. Refined, unhurried, editorial, calm slow motion. [SCENE 1] THE STARTING FRAME: the empty white studio — seamless white wall-and-floor sweep, soft directional daylight raking from the left, long clean window-shadows across the floor. Video animates FROM this empty frame. Hold a calm beat — the setting static, light and shadows steady. [SCENE 2] The woman enters gracefully from the right edge — oxblood leather coat cinched at the waist, slim jodhpurs tucked into tall cognac riding boots, silk scarf at her throat — walking with a slow, elegant, unhurried equestrian stride across the open white space, her long soft shadow gliding with her, aligned with the window light. [SCENE 3] She arrives off-centre on the left and eases naturally into a poised contrapposto — weight settling onto her right leg, left hand coming to rest on her hip, right arm relaxed, chin lifting, gaze drifting just off-camera to the left toward the light. [SCENE 4] She holds the pose, serene and still — a soft breath, the oxblood leather and silk scarf settling, a few dust motes drifting through the light shaft. The frame is locked; no camera movement.
6. The handoff, hand by hand
Five scenes this time. The horse walks in from the right holding the Kelly by its top handle in its mouth. It settles beside her, she turns toward it, takes the bag with her left hand, then strokes its muzzle with her right.
One tip: I named the hand for every move and the handle the horse holds, so nothing about the handoff is left open.
Exact prompt
Create a new video where a calm chestnut horse walks slowly into a minimalist white studio carrying a tan Hermès Kelly bag gently in its mouth and delivers it to an elegant woman in an oxblood Hermès look, who takes the bag and softly strokes the horse's muzzle. Soft daylight from the left throughout, refined and unhurried, warm tones glowing against the white, calm slow motion. [SCENE 1] THE STARTING FRAME: the woman stands off-centre on the left in a poised stance — oxblood leather coat, cognac riding boots, weight on her right leg, left hand on her hip, gaze off to the left. Video animates FROM this position. Hold a beat. The white studio and its window-shadows stay static. [SCENE 2] A chestnut horse enters slowly and smoothly from the right, holding a structured tan Kelly handbag by its top handle in its mouth, and walks calmly toward her right side, its long soft shadow gliding with it, aligned with the window light. [SCENE 3] The horse arrives and settles beside her; she turns gracefully toward it, her gaze softening as she notices the bag. [SCENE 4] She reaches out unhurried and takes the tan Kelly from the horse's mouth with her left hand, drawing it gently to her side. [SCENE 5] She lifts her right hand and softly strokes the horse's muzzle, tilting her head toward it with a warm, serene expression as it settles calmly beside her. The frame is locked; no camera movement.
7. Walk-off and the logo snap
She lowers her hand and the two of them walk off to the right. On my black puma spot the wordmark faded up. Here I switched to a snap: the logo appears all at once while they're still mid-stride, not fading in, and holds still while they leave.
Exact prompt
Create a new video where a woman in an oxblood Hermès look and a chestnut horse walk off together to the right across a white studio, and the black Hermès logo snaps on all at once as a flat title overlay, holding crisp and static like a clean edit. Soft daylight from the left throughout, unhurried and elegant. [SCENE 1] THE STARTING FRAME: the woman stands on the left stroking the chestnut horse's muzzle, a tan Hermès Kelly in her other hand. Video animates FROM this position. Hold a calm beat. The white studio and window-shadows stay static. [SCENE 2] She lowers her hand from the horse, and together the woman and the horse turn and begin walking smoothly toward the RIGHT side of the frame, moving slow and unhurried side by side. [SCENE 3] They continue walking right across the open white space, their long soft shadows gliding with them, heading toward the frame edge. [SCENE 4] While they are still mid-stride walking right, the black Hermès logo — the Duc carriage motif above the HERMÈS PARIS wordmark — appears ALL AT ONCE in a single instant, snapping into place fully formed and centred over the frame as a flat crisp black title graphic, NOT fading or dissolving in, and holds perfectly still and sharp as the pair finish walking out to the right, resolving to the clean white studio with the logo centred. The frame is locked; no camera movement.
8. Join
Emero joined the three clips for me, walk-in, handoff, walk-off. Any editor does the same thing.
Exact prompt
Combine the clips in order
Why it works
Each clip starts and ends on a still I already approved, so the horse, the bag and her hands all have to land where the delivery frame put them. Writing the clip as numbered scenes just lays out the beats in between, one per line.
Your turn: take one clip you've already made and rewrite its prompt as three or four numbered scenes. Compare the two.
Emero writes these scene prompts for you and remembers your look between chats, at cost.
Get one of these every day
I test new workflows daily and send them with the exact prompts, the models and the costs
5,976 generations tested so far
More workflows
See all
Nano Banana Pro + Kling 3.0 - a cassowary hands over a red bag
A woman in a red gown gets her bag from a cassowary that walks in mid-clip, built from stills
Nano Banana Pro, Kling 3.0 · 8 min render
Nano Banana Pro + Kling 3.0 - four framings to get a flamingo hand-off right
A flamingo brings a hot-pink bucket hat, and the four framings it took to land the shot
Nano Banana Pro, Kling 3.0 · 9 min render
Nano Banana Pro + Kling 3.0 - telling a black cougar which side of the frame to sit on
A black cougar brings a woman in white her handbag, and the left and right fix that set up the shot
Nano Banana Pro, Kling 3.0 · 9 min render