Nano Banana Pro + Kling 4.0 - a pygmy hippo brings the bag, outfit from one product photo
A real pygmy hippo brings a burgundy quilted bag, with the outfit taken from one on-model photo
Tested by Nouamane BenbrahimDisclaimer: 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
My fire phoenix spot flopped, so for this one I went back to real animals. The pick: a pygmy hippo, the little round one Moo Deng made famous, trotting into a white studio with a handbag in its mouth. In today's "animal frames" series I did a test spot styled on Miu Miu's look. Miu Miu isn't a client, this was just a test.
Here's my exact process.
1. The empty room
First I made the studio from a prompt alone: white sweep, tall window on the left, long shadows across the floor. Then I ran it again with that image as the reference and asked for a white floor, nothing else changed.
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.
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 from the brand's own photo
I pulled the real product photos from Miu Miu's site, starting with a fuzzy chartreuse lime-green wool cardigan from their fall/winter 2026 collection. My plan was lime head to toe, with a lime skirt and knee-high boots. Then I looked at how Miu Miu actually styles it. On their model it's worn over a pale butter-yellow knit, with an ivory linen skirt and dark brown mules. The skirt and boots in my plan were stuff I made up, so I dropped them and used their outfit.
Three references: a frame of the studio for the room and where she stands (I told the model to ignore the person in it), Miu Miu's on-model photo for the whole outfit, and a close-up of the cardigan for the colour and the brushed texture. Their model wears a trapper hat and carries a fur bag, so I wrote no hat and no bag, and kept her hands empty for later.
Using their on-model photo got me the skirt and shoes from one image, so I didn't have to hunt down a product photo for every piece.
And listen, she came out bigger in the frame than the rest of this series. I kept it anyway, the hippo only comes up to her hip.
Exact prompt
Create a new photorealistic image. This is a photograph taken natively inside the white studio from the first reference, not a composite: one unified natural window light falls on the woman and the room alike, with shared highlights and real cast shadows. Use the first reference ONLY for the room, the camera position and framing, and where the model stands; IGNORE the person and clothing in it. THE VIBE: Quiet, offbeat Miu Miu girlishness in a hushed, expensive empty studio. A single soft-chartreuse figure against acres of white, poised and a little nonchalant, like the opening beat of a fashion film just before something strange walks in. THE SUBJECT: One woman in her early twenties, slim, with a chin-length tousled light-brown bob, fresh bare-skinned face, light natural brows. She wears the exact outfit from the second reference, reproduced faithfully: a fitted brushed-wool cardigan in a fuzzy chartreuse lime green (true colour: a yellow-leaning lime green with a soft halo of brushed fibres), buttoned all the way down with small pale mother-of-pearl buttons, cuffs slightly long over the wrists, worn over a pale butter-yellow fine knit whose hem peeks out below the cardigan; a straight knee-length ivory linen skirt with a subtle tonal texture; dark brown leather slip-on mules with a chunky, slightly rubbery sole. Take the cardigan's exact colour, brushed texture and button detail from the third reference. NO hat, NO bag, NO fur, nothing in her hands: both hands are empty. ONE pose: standing with her weight on one leg, one hand resting loosely at her side and the other lightly touching her cardigan hem, head turned slightly toward the window light, a calm, faintly aloof expression. THE FACE: Natural skin texture with fine pores and slight unevenness, no plastic smoothing, no heavy makeup. THE SETTING: Exactly the studio from the first reference: a seamless matte-white cyclorama sweeping into a continuous matte-white floor with a soft satin sheen, faint painted-plaster texture, empty except for her. A tall window just out of frame on the LEFT. Generous empty white floor to the right of her. THE LIGHT: KEY: soft directional daylight raking in low from the tall window on the left, lighting her left side and front, soft-edged, about half a stop under the brightest patch of floor; her right side falls into gentle grey shade. FIELD: the white wall and floor bright, with long clean geometric window-frame and mullion shadows stretching across the floor to the right; a rectangle of window light on the floor where she stands. Her own soft shadow falls to the right along the floor, matching the window shadows. Cool-neutral white balance with a faint warmth where the sun lands; the chartreuse cardigan reads fresh and saturated in the light, slightly deeper olive-lime on the shaded side. Naturalistic grade, deep focus. THE KEY DETAILS: the fuzzy brushed halo of the cardigan catching the window light; the butter-yellow hem peeking out; the ivory skirt; the dark brown mules grounded on the white floor with a contact shadow. THE MOOD: Restrained, curious, quietly playful luxury; the calm before an absurd delivery. THE COMPOSITION: 16:9 wide frame matching the first reference. The woman full body, SMALL, standing in the LEFT THIRD (about one third in from the left edge) inside the window-light patch, occupying roughly the same height in frame as the person in the first reference. Vast empty white floor and wall to the right for an animal to enter later; open airy space above. THE CAMERA: Cinematic editorial fashion still, eye level, locked-off, natural perspective, deep focus, no strobe, lit only by the window.
3. Get the hippo's size right
I looked up the real size first. An adult pygmy hippo is about 75 cm to 1 m at the shoulder, so its back lands around her hip. I wrote "about 80 cm tall at the shoulder" into the prompt, plus "not cartoonish, not oversized".
Two references: her pose frame first, so she and the room stay put, and Miu Miu's photo of the Arcadie bag in burgundy. The hippo itself is text: round barrel body, short legs, dark slate-grey skin with pink on the cheeks and belly, holding the bag by its two rolled handles in its mouth. She bends down, takes the handles and pats its head. I picked burgundy so the bag stands out against her chartreuse.
Two things aren't perfect here. The handles sit at its lips more than in its mouth, and the hippo barely has a shadow next to hers. I kept it.
Exact prompt
Create a new photorealistic image. This is the same photograph as the first reference, taken a moment later in the same white studio, not a composite: the woman, her outfit, her size in frame, the camera, the room and the window light are preserved exactly from the first reference, and a real pygmy hippopotamus now stands in the room, lit by the same window light with real cast shadows. THE VIBE: An absurd, tender delivery in a hushed luxury studio. A small, round, real pygmy hippo has just trotted in carrying a designer handbag in its mouth, and the woman in chartreuse accepts it as if this happens every day. Deadpan, charming, quietly impossible. IDENTITY LOCK: The woman from the first reference, preserved exactly: chin-length tousled light-brown bob, fresh bare-skinned face, slim build. THE SUBJECT: She wears exactly the outfit from the first reference: the fuzzy brushed chartreuse lime-green cardigan buttoned with small pale buttons, the butter-yellow knit hem peeking out, the knee-length ivory linen skirt, the dark brown leather mules. She stands in the same spot in the left third, turned slightly toward the hippo on her right side of the frame, bending a little at the waist and reaching down with one hand to take the bag's top handles, her other hand resting gently on top of the hippo's head. A soft, amused half-smile. THE ANIMAL: A real adult pygmy hippopotamus at true natural size: about 80 cm tall at the shoulder and 1.6 m long, its back reaching roughly her hip height; barrel-shaped round body, short sturdy legs, small rounded ears, narrow head with a soft muzzle. Smooth, faintly glossy hairless skin, true colour a dark greenish slate-grey with warmer pinkish-grey tones on the cheeks, chin, belly and in the skin folds. It stands on the floor on the RIGHT of her (viewer's right), facing left toward her, head lifted, gently holding the bag by its two rolled top handles in its mouth and offering it up to her hand. Real-looking, not cartoonish, not oversized. THE BAG: The exact handbag from the second reference, matched exactly: a small burgundy top-handle bowling bag in gathered matelassé nappa leather with deep soft pleats, two rolled leather top handles, a gold zip along the top, gold metal "miu miu" logo lettering stacked on two lines on the front, gold hardware, and a small hanging leather logo tag. Deep burgundy, a bold contrast against her chartreuse cardigan. THE SETTING: Exactly the studio from the first reference: seamless matte-white cyclorama, continuous white floor with a soft satin sheen, tall window on the LEFT, empty otherwise. THE LIGHT: KEY: the same soft directional daylight from the window on the left falls on her and on the hippo's left flank and face, soft-edged; the hippo's right side and far flank fall into soft grey shade, its glossy skin catching a gentle highlight along the back. FIELD: the same bright white wall and floor with the same long window-frame shadows stretching to the right. The hippo casts a soft contact shadow under its feet and a longer shadow to the right along the floor, matching hers. Cool-neutral white balance, faint warmth where the sun lands, naturalistic grade, deep focus. THE KEY DETAILS: the bag's handles held gently between the hippo's lips; her fingers closing on the handles; her other hand on the top of its head; the gold "miu miu" lettering readable on the bag. THE MOOD: Deadpan, sweet, scroll-stopping; a fashion moment with an animal that should never be there. THE COMPOSITION: 16:9, same camera and framing as the first reference. She stays at exactly the same size and position as in the first reference, in the left third. The hippo sits just to her right, both figures in the lower part of the frame, with generous empty white floor and wall to the right and above. THE CAMERA: Cinematic editorial fashion still, eye level, locked-off, deep focus, lit only by the window.
4. The wordmark
Empty room plus the real Miu Miu wordmark as a reference. Quick warning: Wikimedia blocked my download, so I grabbed a clean PNG of the logo from a logo site instead. I wrote that the wordmark shows up exactly once, and it came out clean on the first pass.
Exact prompt
Create a new photorealistic image: a minimalist title card. This is the same photograph as the first reference, taken from the same camera in the same white studio after everyone has left: the room, framing and window light are preserved exactly from the first reference, but the woman is gone and the studio is completely empty. THE VIBE: The quiet full stop at the end of a fashion film. An empty, sunlit white room and one crisp black wordmark on the wall, calm and expensive. THE SUBJECT: The exact logo from the second reference, reproduced precisely and unchanged in letter shapes, spacing and proportion: the "miu miu" wordmark in bold, rounded, stencil-cut black lowercase letters, the two words side by side on one line. Render the wordmark EXACTLY ONCE: there is exactly one line of "miu miu" in the whole image, no duplicate, no echo, no second copy, no reflection of it on the floor. Flat solid black, as if printed or painted directly onto the white wall, perfectly level, sharp and centred horizontally on the back wall at roughly eye height, about one third of the frame width. THE SETTING: Exactly the studio from the first reference: seamless matte-white cyclorama sweeping into a continuous matte-white floor with a soft satin sheen and faint painted-plaster texture. No person, no animal, no bag, no props. Nothing else in the frame except the wordmark. THE LIGHT: KEY on the wall: the same soft directional daylight from the tall window on the LEFT, the wordmark sitting flat in the same light as the wall around it. FIELD: the bright white wall and floor with the same long, clean geometric window-frame and mullion shadows stretching across the floor to the right, exactly as in the first reference; keep the window light and its floor shadows, do not flatten to plain white. Cool-neutral white balance, faint warmth where the sun lands, naturalistic grade, deep focus. THE KEY DETAILS: the single black wordmark; the window-light shadows across the empty floor. THE MOOD: Restrained, clean, editorial end card. THE COMPOSITION: 16:9, same camera and framing as the first reference, with the room empty and the wordmark centred on the back wall. THE CAMERA: Cinematic editorial architectural still, eye level, locked-off, deep focus, lit only by the window.
5. She walks in
Now the clips. For the first frame I used an empty frame of the same room, with her pose as the last frame. She walks in from the right and settles in the window light. The prompt opens with "ONE single woman only", and only one of her showed up.
Exact prompt
Create a new video where, in an empty sunlit white studio, a young woman with a tousled light-brown bob, wearing a fuzzy chartreuse lime-green cardigan, an ivory knee-length linen skirt and dark brown mules, walks in from the right side of the frame, crosses the white floor toward the tall window on the left and settles into a calm, poised standing pose in the left third. Static locked camera, soft natural window daylight, quiet editorial fashion-film mood. ONE single woman only: exactly one person in the frame at all times, no other people, no duplicates, no clones, no reflections of people. [SCENE 1] THE STARTING FRAME: the empty white studio exactly as in the first frame, a tall window on the left, long window-frame shadows across the white wall and floor, nobody in the room. Video animates FROM this position. THE SETTING (UNCHANGED FROM FRAME): the white cyclorama, the floor, the window light and its shadows remain static. Only animate the woman. Almost immediately she steps in from the RIGHT edge of the frame, walking forward toward the left with a relaxed, unhurried, natural stride, her real feet planted on the floor with each step, walking forward, NOT backward, not sliding, not drifting. [SCENE 2] She crosses the floor into the rectangle of window light in the left third, slows, and settles into her pose: weight on one leg, one hand loose at her side, the other lightly touching her cardigan hem, head turned slightly toward the window. She lands in the exact pose, position and size of the final frame only on the very last frame of the clip, then holds. Her soft shadow falls to the right along the floor, matching the window shadows. The fuzzy chartreuse cardigan, ivory skirt and brown mules stay exactly the same throughout. Camera locked, no camera movement, deep focus.
6. The hippo brings the bag
Pose frame to delivery frame. The hippo trots in from the right with the bag in its mouth the whole way. I said it keeps its real size and never shrinks or grows, and that the bag never drops.
One tip: make the hand-off land on the very last frame. I wrote that she doesn't take the bag early and doesn't hand it back. I've had clips in this series do the hand-off early and then undo it. This was the best clip of the three.
Exact prompt
Create a new video where, in a sunlit white studio, a young woman with a tousled light-brown bob in a fuzzy chartreuse lime-green cardigan, ivory linen skirt and dark brown mules stands calmly by the window, and a real pygmy hippopotamus trots in from the right carrying a small burgundy quilted leather handbag by its top handles in its mouth. It stops beside her, lifts its head and offers the bag; she bends down, takes the handles with one hand and pats the top of its head with the other, smiling. Static locked camera, soft natural window daylight, deadpan and sweet. ONE single woman and ONE pygmy hippo only: no duplicate figures, no clones. [SCENE 1] THE STARTING FRAME: the woman standing in the window light in the left third, weight on one leg, one hand at her cardigan hem, the right side of the room empty. Video animates FROM this position. THE SETTING (UNCHANGED FROM FRAME): the white cyclorama, the floor, the window light and its long shadows remain static. Almost immediately a real adult pygmy hippopotamus enters from the RIGHT edge of the frame, trotting forward toward her on its short sturdy legs with a heavy, waddling, grounded gait, feet planted on the floor, walking forward, NOT backward, not sliding, not drifting. It is about 80 cm tall at the shoulder, round barrel body, smooth dark slate-grey skin with pinkish tones on the cheeks and belly, and it keeps exactly this real size the whole time: it never shrinks or grows. It carries the burgundy gathered-leather handbag with gold hardware by its two rolled top handles gently in its mouth the entire time it walks; the bag never drops. The woman turns her head and watches it come. [SCENE 2] The hippo slows and stops just to her right, side-on, facing left toward her, and lifts its head to offer the bag. She bends slightly at the waist, reaches down and closes one hand on the bag's handles at the hippo's mouth, and rests her other hand gently on top of its head, with a soft amused smile. This hand-off completes exactly on the very last frame of the clip and holds; she does not take the bag early and does not hand it back. The hippo casts a soft shadow on the floor to the right, matching hers. Her outfit and the bag stay exactly the same throughout. Camera locked, no camera movement, deep focus.
7. Turn first, then walk off
Delivery frame to the end card. The hippo starts out facing her, so I had it turn around to face right first. Then they walk out side by side and the wordmark pops on.
And listen, this one isn't perfect. Halfway through, the camera pushes in on her even though I asked for a locked camera. She walks out ahead of the hippo instead of next to it, and the wordmark pops on while its back end is still in frame. I kept it anyway since it goes by fast. If I wanted it cleaner, this is the clip I'd re-run.
Exact prompt
Create a new video where, in a sunlit white studio, a young woman with a tousled light-brown bob in a fuzzy chartreuse lime-green cardigan, ivory linen skirt and dark brown mules has just taken a small burgundy quilted handbag from a real pygmy hippopotamus; she straightens up with the bag in hand, the hippo turns around, and the two of them walk off together out of the right side of the frame. Once the room is empty, the black "miu miu" wordmark appears on the white wall all at once. Static locked camera, soft natural window daylight, calm editorial ending. ONE single woman and ONE pygmy hippo only: no duplicate figures, no clones. [SCENE 1] THE STARTING FRAME: the woman bent slightly toward the pygmy hippo on her right, one hand holding the burgundy bag by its handles, the other hand on the hippo's head; the hippo side-on, facing left toward her. Video animates FROM this position. THE SETTING (UNCHANGED FROM FRAME): the white cyclorama, the floor, the window light and its long shadows remain static, and the back wall stays completely blank and white during this scene, with no text and no logo. She straightens up holding the bag by its handles at her side. She keeps wearing the SAME chartreuse cardigan, ivory skirt and brown mules throughout; the outfit never changes. The hippo TURNS AROUND on the spot to face the RIGHT, so it faces the same way she is heading. [SCENE 2] Then the woman and the hippo walk off together toward the RIGHT side by side, both moving forward in the same direction, unhurried: the hippo waddles forward naturally on its short legs, NOT backward, not sliding, not drifting, and keeps exactly its real size (about 80 cm at the shoulder), never shrinking or growing. They walk fully out of the right edge of the frame, leaving the studio completely empty. [SCENE 3] Only after both have fully left the frame, the black "miu miu" wordmark (bold rounded stencil-cut lowercase letters, one line) appears on the back wall ALL AT ONCE in a single instant, fully formed, flat black, level and centred, NOT fading or dissolving in. Render the wordmark ONCE: exactly one line of it, no echo, no duplicate. It holds perfectly still and sharp on the empty white wall to the final frame, matching the last frame. Camera locked, no camera movement, deep focus.
8. Join the clips
I asked Emero to combine the three clips in order. Any editor works too.
Exact prompt
Combine the clips in order
Why it works
After the phoenix flopped, I wanted an animal that's real but still feels wrong in a fashion studio. A pygmy hippo is a real animal at its real size, doing a job it would never do. And because I used the brand's own outfit photo, I didn't have to guess what Miu Miu would put her in.
Your turn: before you write an outfit from scratch, check how the brand styles that piece on their own model.
Emero writes the prompts for you and remembers your brand's products for the next spot, 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
5,920 generations tested so far
More workflows
See all
Nano Banana Pro + Kling 3.0 - an ostrich delivers a red barrel bag
An ostrich hands over a recoloured monogram bag, built from one product sheet
Nano Banana Pro, Kling 3.0 · 14 min render
Omni 1.1 vs MiniMax H3 - Animating an Old PS2 Game Character
Same prompt and character through two AI video models, and only one kept the old game look
Nano Banana Pro, Omni 1.1, MiniMax H3 · 4 min render
Nano Banana Pro + Kling 3.0 - keeping a fire Phoenix lit for a whole clip
A Phoenix made of fire delivers a cream cap, using real product photos from the brand's site
Nano Banana Pro, Kling 3.0 · 11 min render