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 - getting a sea turtle to its real size
How I got a sea turtle to real size for a fashion spot, and which reference controls scale
Tested by Nouamane Benbrahim
In today's "animal frames" series I did a spot for Vilebrequin. Their whole thing is turtles, so a real sea turtle walks into the studio with a turtle-print bucket hat balanced on its shell. Not a client, just a test. The hard part wasn't the turtle, it was the size: it took me 6 tries to get one that didn't look like a monster movie.
Here's my exact process.
1. The room
Same white studio I use for the whole series: built from a prompt alone, then one pass to turn the floor 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. The resort look
I wrote the outfit from scratch, based on Vilebrequin's turtle print: small coral, yellow, teal and white turtles on a deep ocean-blue base. White linen camp shirt open over a white tee, the turtle-print swim trunks, and bare feet, because nobody wears sneakers to the beach.
Exact prompt
Create a new photorealistic image: a male fashion model standing in a clean white studio, styled in vibrant resort swimwear, positioned in the left third of the frame. THE VIBE: a high-end summer resort campaign — St. Tropez luxury, sun-drenched, confident and relaxed. THE SUBJECT: a handsome, fit male model in his late 20s, standing relaxed with weight on one hip, body angled slightly toward the open right side of the room, looking toward camera with an easy confident expression. THE FACE: natural, friendly, sun-kissed skin, light stubble, short tousled dark hair. THE OUTFIT: a crisp white linen camp-collar shirt worn open over a plain white tee, and vibrant swim trunks in Vilebrequin's signature print — small multicolored turtle motifs (coral, yellow, teal, white) scattered across a deep ocean-blue base. Barefoot. The deep-blue trunks with their colorful turtle print are the saturated color hit against the white room. THE SETTING (UNCHANGED): the exact same seamless white studio from the reference — same white floor, same soft daylight spilling from the left, same long window-light shadows. The model occupies the left third; the rest of the room is open, empty negative space to the right. THE LIGHT: clean bright studio daylight from the left, soft flattering shadows. THE COMPOSITION: wide shot, the model small in the left third, large white negative space filling the right two-thirds. 16:9. THE CAMERA: straight-on, eye-level, no distortion.
3. The turtle (6 tries)
This one burned me. My early passes kept making the turtle giant, like a shell you could sit on. So I spelled out the real size: a large adult green sea turtle, about one metre long, shell up to his thigh, and not oversized or cartoonishly giant.
Then I learned something useful. Which image you reference decides what changes. When I passed in the pose frame, the model rebuilt the turtle from scratch, so that's how I fixed the size. Once the turtle was right, I passed in that delivery frame instead, which kept the same turtle and only let me move the action. In the final pass he's closer, his hand actually gripping the brim, lifting the hat off the shell.
Exact prompt
Create a new photorealistic image based on the reference: the same man in the same white studio, now with a large but realistically-sized sea turtle that has arrived, offering a bucket hat balanced on its shell. FRAMING (match the reference exactly): a WIDE shot. The man stays the same small size and same position — standing in the left third, full body, with large amounts of empty white negative space above and to the right. Do NOT zoom in or crop closer. THE ANIMAL — a real, large green sea turtle at TRUE life size: its domed shell reaching roughly to the man's thigh/waist height when he stands, body about one metre long. Impressive and sizeable but completely believable — the size of an actual large adult green sea turtle, NOT oversized or cartoonishly giant. Grounded on the white floor, front flippers mid-stride, head raised toward the man. A turtle-print bucket hat sits balanced flat on top of its shell. THE SUBJECT: the same male model from the reference (same face, tousled dark hair, white linen camp shirt over white tee, deep-blue multicolored turtle-print swim trunks, barefoot), bending toward the turtle, reaching a hand down to the hat on its shell, delighted expression. THE DETAILS: hat is the Vilebrequin multicolored-turtle print (deep blue with small colorful turtle motifs). THE SETTING (UNCHANGED FROM REFERENCE): exact same seamless white studio, same floor, same soft daylight from the left, same long shadows, same wide empty composition. THE COMPOSITION: wide shot — man small in the left third, a realistically large turtle on the floor to his right, generous open white space to the right and above. 16:9. THE CAMERA: straight-on, eye-level, same distance as the reference, no zoom, no distortion.
Exact prompt
Create a new photorealistic image based on the reference, keeping the SAME turtle (same realistic large size, same breed and look), the SAME man, and the SAME wide framing and camera distance. Only change the staging of the handoff. THE CHANGE: the turtle has moved CLOSER to the man so they are right next to each other, and the handoff actually connects — the man's hand is firmly ON the turtle-print bucket hat, fingers gripping its brim, in the act of lifting it off the turtle's shell. The man leans in toward the turtle (not reaching into empty space); the gap between them is closed. It should clearly read as the turtle delivering the hat and the man taking it. KEEP THE SAME (from reference): the realistically-sized large green sea turtle (shell to about the man's thigh, correct proportions, grounded with flippers on the floor, head raised); the same man (face, tousled dark hair, white linen camp shirt over white tee, deep-blue multicolored turtle-print swim trunks, barefoot); the same wide framing with the man in the left third and generous white negative space to the right and above; the turtle-print bucket hat (deep blue with small colorful turtle motifs). THE SETTING (UNCHANGED FROM REFERENCE): exact same seamless white studio, same floor, same soft daylight from the left, same long shadows. THE COMPOSITION: wide shot, man and turtle together in the left-center, open white space to the right. 16:9. THE CAMERA: straight-on, eye-level, same distance as the reference, no zoom, no distortion.
4. The logo
I tried grabbing Vilebrequin's wordmark from a couple of logo sites and they wouldn't let me download it. The one that worked was a transparent PNG. Transparent matters: logos on a white background tend to render twice. This one came out once and clean.
Exact prompt
A brand end-card: the empty white studio with the real Vilebrequin wordmark logo snapped cleanly onto it. THE VIBE: The final frame of a luxury fashion spot — the airy white studio emptied of people, the brand signature resolving at center. Calm, premium, resort-elegant. THE SUBJECT: No people, no animal. Just the pristine white studio and the logo. THE SETTING (UNCHANGED FROM REFERENCE): The exact same seamless white cyclorama studio from the first reference image — same soft white floor, same gentle floor-to-wall curve, same even daylight. Do not change the room. THE LOGO: The second reference image is the official Vilebrequin wordmark (black serif "VILEBREQUIN" lettering on transparent background). Place it centered, horizontally, in the upper-middle of the frame. Render the wordmark EXACTLY ONCE — one single clean logo, crisp and sharp, true to the reference letterforms. ABSOLUTELY NO second copy, no echo, no faint duplicate, no reflection, no mirrored or repeated text anywhere in the frame. Keep the lettering solid black, evenly weighted, perfectly legible. THE LIGHT: Bright, soft, even studio daylight. Clean white with gentle floor shadow. No harsh highlights. THE KEY DETAILS: Lots of clean negative space around the logo. The wordmark sits as the single hero element. THE COMPOSITION: Centered, balanced, minimal. Logo in the upper-center third, open white space below. THE CAMERA: Straight-on, eye-level, static. 16:9.
5. He walks in
Empty room to pose. He steps in from the right with a bit of a resort swagger and only lands the pose at the very end of the clip.
Exact prompt
A luxury resort-fashion spot, segment 1 of 3: the model walks into the empty white studio from the right and settles into his opening pose. High subject motion, locked camera. THE STARTING FRAME: the empty seamless white studio — soft white floor, gentle floor-to-wall curve, even daylight, no people. THE SETTING (UNCHANGED FROM FRAME): the exact same white cyclorama studio throughout — same floor, same light. The room never changes. [SCENE 1] The empty studio holds for a beat. Then a male model steps briskly into frame from the RIGHT edge — white linen camp shirt open over a white tee, deep-blue multicolored turtle-print swim trunks, barefoot. He is mid-stride, confident, entering. [SCENE 2] He continues walking leftward across the white floor, relaxed resort swagger, arms swinging naturally, covering ground toward the left third of the frame. [SCENE 3] He arrives at the left third and settles: weight shifting onto one leg, body squaring gently to camera, coming to rest in his opening pose exactly as the final frame. He lands his pose only here, at the very end. THE CAMERA: straight-on, eye-level, static. 16:9. Land change only at the end.
6. The turtle brings the hat
Pose to delivery. The turtle paddles in on its flippers with the hat on its shell and stops right next to him. I said he grabs the hat only at the very end, so the grab lands on the last frame instead of happening early and undoing itself.
Exact prompt
A luxury resort-fashion spot, segment 2 of 3: a real sea turtle walks in from the right carrying the brand's turtle-print bucket hat and delivers it; the man takes hold of it. High subject motion, locked camera. THE STARTING FRAME: the male model stands at rest in the left third — white linen camp shirt over white tee, deep-blue turtle-print swim trunks, barefoot. Empty white studio to his right. THE SETTING (UNCHANGED FROM FRAME): the exact same white cyclorama studio throughout — same floor, same light. The room never changes. [SCENE 1] A realistic large adult green sea turtle enters from the RIGHT, moving across the white floor on its flippers, a deep-blue multicolored turtle-print bucket hat balanced on its shell. The man turns his head toward it, noticing. [SCENE 2] The turtle advances steadily toward the man and comes to rest close beside him at his right. The man begins to lean down, reaching toward the hat on the shell. [SCENE 3] The man bends over the turtle, his hand firmly ON the turtle-print bucket hat, fingers gripping the brim, in the act of lifting it off the shell — settling into the exact final frame. He connects with the hat only here, at the very end. THE CAMERA: straight-on, eye-level, static. 16:9. Land change only at the end.
7. They leave together
Delivery to end card. He puts the hat on, and they head out to the right side by side. I named "no sliding, no moonwalk" outright, because that's what Kling does with a walk-off if you let it.
Exact prompt
A luxury resort-fashion spot, segment 3 of 3: the man lifts the hat, he and the sea turtle walk off to the right together, the studio empties, and the brand wordmark snaps on. High subject motion, locked camera. THE STARTING FRAME: the man bent over the green sea turtle beside him, his hand gripping the brim of the turtle-print bucket hat, lifting it off the shell. Empty white studio to the right. THE SETTING (UNCHANGED FROM FRAME): the exact same white cyclorama studio throughout — same floor, same light. The room never changes. [SCENE 1] The man lifts the turtle-print bucket hat clear of the shell and straightens up, settling it onto his head with an easy resort grin. The turtle shifts its weight, turning toward the right. [SCENE 2] Man and turtle move off together toward the RIGHT edge of frame — the man strolling, the turtle ambling on its flippers beside him — both exiting cleanly out the right side. No sliding, no moonwalk; natural forward steps. [SCENE 3] The studio is now empty — pristine white floor, soft daylight, no people and no turtle. The black VILEBREQUIN wordmark snaps crisply onto the center of the frame, exactly once, matching the final frame. One clean logo, no echo, no duplicate. THE CAMERA: straight-on, eye-level, static. 16:9. Land change only at the end.
8. One video
Joined in Emero, walk-in, hand-off, exit.
Exact prompt
Combine the clips in order
Why it works
Size is what makes an animal look real. A turtle that's slightly too big reads as CGI right away. Get the scale right in the still and the video has nothing to fix.
Your turn: next time an animal comes out wrong, check which reference you passed in before you rewrite the prompt.
Emero writes these prompts for you and remembers what worked, so you're not starting over every chat. Everything's 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 - 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
Nano Banana Pro + Kling 3.0 - a peacock carries a bag by its gold chain
A gown in peacock colours, and a peacock that brings a jewel-toned bag by its gold chain
Nano Banana Pro, Kling 3.0 · 8 min render