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 - shrinking a giant penguin back to real size
A giant penguin pass gets cut down to real size, then the hat handoff gets cut to one reach
Tested by Nouamane Benbrahim
In today's "animal frames" series I did a test spot styled on Original Penguin's look. A guy in a sky-blue polo and orange trousers stands in a white studio, an emperor penguin waddles in with a yellow bucket hat in its beak, he takes it, puts it on and they walk off. Original Penguin isn't a client, I was just testing. Their logo is Pete the Penguin, and this spot taught me two things: keep the penguin at its real size, and keep the handoff to one move.
Here's my exact process.
1. Set up the studio
First image is prompt only: white walls, tall window on the left, long mullion shadows. The second pass swapped the pale cement floor for white.
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. Preppy golf colors
I based the palette on Original Penguin's spring 2026 "Pete's Original Book Club" capsule and pulled the colorway names and hex codes. He wears a Malibu-blue short-sleeve knit polo (#2BA4DB), melon-orange flat-front trousers (#F26B3A) and white leather sneakers. The Sun-Washed Yellow (#F2D04B) is for the hat later. I asked for a retro golf feel, small in the left third, no props, no text and no animals yet.
Exact prompt
Create a new photorealistic image. This is a photograph taken in the white studio from the reference from the start — not a composite. Rebuild the entire scene as if shot natively here, with unified lighting across subject and environment. THE VIBE: A bright, clean, playful preppy-golf campaign moment — mid-century retro cool brought current. Airy and confident, lots of calm white space, the kind of frame that lets one pop of saturated color carry the whole image. IDENTITY LOCK: A man in his mid-20s, short neat dark hair, clean-shaven, warm medium skin tone, athletic build. THE SUBJECT: He stands in the LEFT THIRD of the room in a relaxed, natural stance — weight on one leg, one hand tucked in his trouser pocket, the other loose at his side, shoulders turned a few degrees toward the open room, chin level, an easy half-smile, gaze sent slightly off-camera into the empty space. True colours under neutral white light: a bright Malibu-blue short-sleeve knit polo (saturated azure sky-blue, #2BA4DB), melon-orange tailored flat-front trousers (warm coral-orange, #F26B3A), clean bright-white leather sneakers. Preppy retro-golf styling, well-fitted. THE FACE: Natural skin texture, no airbrushing, no plastic or waxy skin, real skin with subtle tonal variation, soft organic light. THE SETTING (UNCHANGED): Preserve the studio from the reference exactly — the tall window on the left, the soft daylight pouring in, and the long geometric mullion-grid shadows cast across the smooth white floor. Large empty negative space filling the right side of the room. Do NOT redesign the room, and do NOT remove or flatten the window light and floor shadows to plain even white. THE LIGHT: Soft natural daylight from the window on the left, gentle directional falloff — warm on his lit side, soft shadow on the far side; crisp mullion shadows stretching across the floor. THE KEY DETAILS: No props, no text, no logos, no animals — just the man standing in the empty studio. THE MOOD: A clean, upbeat sportswear campaign still; warm-nostalgic but modern, punchy single-color accent. THE COMPOSITION: Wide framing, the man small in the left third with generous negative space to his right, full-length, head in the upper-middle of the frame with comfortable headroom, matching the wide locked framing and camera distance of the reference. Do NOT zoom in. THE CAMERA: Editorial campaign capture — a clean full-length fashion frame, eye-level, deep enough focus that the room and floor shadows stay sharp, neutral balanced daylight. 16:9.
3. The giant penguin I threw out
My first delivery frame went big. I asked for a giant emperor penguin, larger than life and taller than him, leaning in with the hat in its beak. I rejected it.
Exact prompt
Create a new photorealistic image. This is a photograph taken in the same white studio from the start — not a composite. Rebuild the entire scene as if shot natively here, with unified lighting across both subjects and the environment. THE VIBE: A bright, playful, slightly surreal preppy-golf campaign beat — a larger-than-life penguin arriving to hand off the hat. Clean white space, warm and upbeat, the saturated color pops carrying the frame. IDENTITY LOCK: Preserve the man exactly, from the first reference — same mid-20s face, short neat dark hair, clean-shaven, warm medium skin tone, athletic build, same bright Malibu-blue short-sleeve knit polo and melon-orange tailored trousers and white sneakers. Do NOT source his face, hair, skin, or outfit from anything else. THE SUBJECTS: The man stands in the LEFT THIRD, same relaxed stance, now turned slightly toward the penguin with a delighted easy smile, reaching one hand out to receive the hat. Entering from the RIGHT is a giant emperor penguin, scaled larger-than-life — taller than the man — standing upright: sleek black back and head, crisp white belly, soft golden-yellow ear patches blending down into a pale lemon upper chest, a long black-and-orange beak. It leans toward the man and extends the gift: a Sun-Washed Yellow bucket hat (warm buttery golden-yellow, #F2D04B) held forward in the tip of its beak, offered across the gap between them. THE FACE: Natural skin texture, no airbrushing, no plastic or waxy skin, real skin with subtle tonal variation, soft organic light. THE SETTING (UNCHANGED): Preserve the studio from the reference exactly — tall window on the left, soft daylight, long geometric mullion-grid shadows across the smooth white floor, large open negative space. Do NOT redesign the room, and do NOT remove or flatten the window light and floor shadows to plain even white. THE LIGHT: Soft natural daylight from the window on the left; both the man and the penguin lit by the same source — warm on their lit sides, soft shadow on the far sides, each casting a real soft shadow onto the white floor; crisp mullion shadows preserved. THE KEY DETAILS: The Sun-Washed Yellow bucket hat is the hero prop, clearly readable, held in the penguin's beak. No text, no logos. THE MOOD: A clean, joyful sportswear campaign still — whimsical, premium, punchy color accents against white. THE COMPOSITION: Wide framing matching the reference — the man small in the left third, the giant penguin filling the right third, generous space between and around them, both full-length with comfortable headroom. Do NOT zoom in; hold the reference's camera distance and scale. THE CAMERA: Editorial campaign capture — clean full-length fashion frame, eye-level, deep focus so the room and floor shadows stay sharp, neutral balanced daylight. 16:9.
4. Back to real size
So I rewrote it with a real number. A real-size emperor penguin, about 1.1 to 1.2 metres tall, roughly waist-to-thigh height on him, not giant, not oversized. It stands on the floor and tilts its head up to offer the yellow bucket hat from the tip of its beak, and he bends a little and reaches down for it. The only reference was the pose frame.
Exact prompt
Create a new photorealistic image. This is a photograph taken in the same white studio from the start — not a composite. Rebuild the entire scene as if shot natively here, with unified lighting across both subjects and the environment. THE VIBE: A bright, playful preppy-golf campaign beat — a penguin waddling over to hand off the hat. Clean white space, warm and upbeat, saturated color pops carrying the frame. IDENTITY LOCK: Preserve the man exactly, from the first reference — same mid-20s face, short neat dark hair, clean-shaven, warm medium skin tone, athletic build, same bright Malibu-blue short-sleeve knit polo and melon-orange tailored trousers and white sneakers. Do NOT source his face, hair, skin, or outfit from anything else. THE SUBJECTS: The man stands in the LEFT THIRD, same relaxed stance, turned slightly toward the penguin with a delighted easy smile, bending slightly and reaching one hand down to receive the hat. Entering from the RIGHT is a REAL-SIZE emperor penguin at TRUE natural scale — a normal-sized penguin roughly waist-to-thigh height on the man (about 1.1–1.2 metres tall), NOT giant, NOT oversized. Standing upright on the floor: sleek black back and head, crisp white belly, soft golden-yellow ear patches blending into a pale lemon upper chest, long black-and-orange beak. It tilts its head up and extends the gift: a Sun-Washed Yellow bucket hat (warm buttery golden-yellow, #F2D04B) held forward in the tip of its beak, offered up toward the man's reaching hand. THE FACE: Natural skin texture, no airbrushing, no plastic or waxy skin, real skin with subtle tonal variation, soft organic light. THE SETTING (UNCHANGED): Preserve the studio from the reference exactly — tall window on the left, soft daylight, long geometric mullion-grid shadows across the smooth white floor, large open negative space. Do NOT redesign the room, and do NOT remove or flatten the window light and floor shadows to plain even white. THE LIGHT: Soft natural daylight from the window on the left; both the man and the penguin lit by the same source — warm on their lit sides, soft shadow on the far sides, each casting a real soft shadow onto the white floor; crisp mullion shadows preserved. THE KEY DETAILS: The Sun-Washed Yellow bucket hat is the hero prop, clearly readable, held in the penguin's beak. No text, no logos. THE MOOD: A clean, joyful sportswear campaign still — whimsical, premium, punchy color accents against white. THE COMPOSITION: Wide framing matching the reference — the man small in the left third with generous negative space, the real-size penguin a small figure lower-right on the floor, correctly dwarfed by the tall room. Both full-length. Do NOT zoom in; hold the reference's camera distance and scale. THE CAMERA: Editorial campaign capture — clean full-length fashion frame, eye-level, deep focus so the room and floor shadows stay sharp, neutral balanced daylight. 16:9.
5. Wordmark card
The empty studio with the "Original Penguin" script wordmark on the back wall, solid black. Logo file for the lettering, pose frame for the room.
Exact prompt
Create a new photorealistic image. This is a photograph taken in the same white studio from the start — not a composite. Rebuild the scene as if shot natively here, with unified lighting across the wall and the environment. THE VIBE: A clean, confident brand end-card — the empty studio with the logo settled onto the back wall. Minimal, premium, calm. THE SETTING (UNCHANGED): Preserve the studio from the second reference exactly — the tall window on the left, soft daylight, the long geometric mullion-grid shadows across the smooth white floor, the large empty room. No people, no animals. Do NOT redesign the room, and do NOT remove or flatten the window light and floor shadows to plain even white. THE LABEL: Centered on the clean white back wall, render the exact "Original Penguin" wordmark from the first reference — the script "Penguin" with the small "original" set above it, solid matte black, reproduced precisely in that exact lettering and proportion. Crisp, sharp, legible, flat against the wall as if cleanly applied vinyl. Do NOT redraw, restyle, or re-letter it; match the first reference exactly. THE LIGHT: Soft natural daylight from the window on the left; gentle falloff across the wall, crisp mullion shadows preserved on the floor. THE MOOD: A premium minimalist brand sign-off frame. THE COMPOSITION: Wide framing matching the second reference's camera distance — the wordmark centered on the upper-middle of the back wall at a tasteful size, generous white space around it, floor and window shadows visible below. Do NOT zoom in. THE CAMERA: Editorial campaign capture — clean, eye-level, deep focus so the wall text and floor shadows stay sharp, neutral balanced daylight. 16:9.
6. Walk-in
Empty room to pose. He walks in from the right side, crosses to the left third and puts a hand in his pocket. One man, grounded steps, no sliding.
Exact prompt
Clean white photo studio, tall window on the left, soft daylight, long mullion-grid shadows on the floor — hold the room, light and shadows constant throughout. The room starts empty. A man in a bright Malibu-blue polo, melon-orange trousers and white sneakers walks IN from the RIGHT side of frame, crosses toward the LEFT THIRD, and settles into a relaxed standing pose with one hand in his pocket, as in the final frame. ONE single man, no clones, no duplicates. Natural confident walk, grounded footsteps, no sliding, no backward motion, no camera push. Wide framing held.
7. One clean reach
My earlier takes of this clip had him take the hat and then pet the penguin. For the one I kept, I cut it down to a single move: the penguin waddles in and raises the hat, he leans and reaches, and his hand only closes on the hat at the very end of the clip. No grabbing early, no handing it back and forth, no petting. One man, one penguin.
Exact prompt
Start exactly on the first bound frame and end exactly on the second bound frame — hold the same man (same face, Malibu-blue polo, melon-orange trousers, white sneakers), the same room, light, scale and his position in the left third throughout. Do not redesign, morph, or warp anything. ONE simple continuous motion: a real-size emperor penguin (about waist-high, NOT giant) waddles IN from the RIGHT toward the man while carrying a Sun-Washed Yellow bucket hat in the tip of its beak, and raises the hat up toward him. The man slowly leans and reaches his hand down toward the hat as the penguin approaches. He does NOT grab it early — his hand only meets and closes around the hat at the very END of the clip, finishing exactly on the second frame. No taking the hat and giving it back, no handing it back and forth — a single clean reach that lands at the end. No petting. ONE man and ONE penguin only, no clones, no duplicates, no extra limbs. The man stays planted in the left third; only the penguin moves in from the right. Grounded weight, no sliding, no backward motion, no camera push.
8. Hat on, walk off
Now he puts the hat on, gives the penguin a quick pat, and they both turn right and walk off side by side. Once the room is empty, the wordmark snaps on. I numbered the actions in the prompt so they happen in that order.
Exact prompt
Clean white photo studio, tall window on the left, soft daylight, mullion floor shadows — hold the room, light and shadows constant. Start on the man (Malibu-blue polo, melon-orange trousers, white sneakers) holding the Sun-Washed Yellow bucket hat beside the real-size emperor penguin. Action, in order: (1) the man puts the bucket hat on his head and gives the penguin a last friendly pat; (2) the man and the penguin both TURN to face RIGHT and walk off together toward the right edge of frame, same direction, side by side, exiting the shot — no backward or sideways sliding; (3) the room is now empty and the "Original Penguin" script wordmark snaps on all at once, solid black, centered on the white back wall, locked and sharp. Hold the window light and floor shadows throughout. No camera push.
9. Combine
I asked Emero to stitch the three clips. You can do it in an editor.
Exact prompt
Combine the clips in order
Why it works
A real-size penguin next to a grown man is already funny, it doesn't need to be huge. And a handoff that lands exactly on the final frame gives the clip one job.
Your turn: give your animal a real height in the prompt, in metres or against the person's body, before you make the delivery frame.
Emero writes these prompts and remembers the fixes that worked, 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 allNano Banana Pro + Kling 3.0 - a surreal knitted wool world in three clips
Build a surreal world made of wool, dress a character to match and animate three short clips
Nano Banana Pro, Kling 3.0 · 10 min render
Nano Banana Pro + Kling 3.0 - a leopard brings a leopard-print bag, and the print comes off her
A leopard delivers a leopard-print bag, and the print comes off her dress
Nano Banana Pro, Kling 3.0 · 13 min render
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