Who Took My Banana? 🍌 is an AI-generated music video made with TubeTube in the Cinematic CGI visual style, 1:51 long across 11 scenes. Scene images were generated with GPT Image 2.5 · Medium and animated with Hailuo 2.3 · 768p. The full recipe below is remixable: reuse the same style and settings with your own words.
Scenes 11 frames
All 11 frames
The exact frames generated for this video - remix the recipe to make your own with the same look.
Lyrics as sung in the video
Where’s my banana? Where did it go?
I had it a little while ago!
Who took my banana? Who, who, who?
Was it me? Was it you?
Under the table? No, no, no!
Behind the pillow? Where did it go?
Inside my shoe? What’s that I see?
Only my toes looking back at me!
Banana, banana, where can you be?
Come out, come out, come back to me!
I check down low, I look up high,
Is that my snack up in the sky?
I scratch my head, my hat goes wobble,
Something up there starts to wobble!
One little jump—my hat falls flat…
My banana was under my hat!
There’s my banana! Ho, ho, ho!
Sitting on my head—oh, now I know!
Peel, peel, peel it slow,
Take a little bite and go, go, go!
Banana, banana, yummy, yum, yum!
Do a little dance and pat my tum!
Wait! Where’s my hat? Oh, silly me…
It’s on the floor, right next to me!
The prompts copy anything
Image style
Hyper-detailed 3D render, cinematic CGI quality, semi-realistic stylized characters, Unreal Engine 5 aesthetic, subsurface skin scattering, detailed fabric and armor textures, volumetric lighting, shallow depth of field, film grain, anamorphic lens flare, dramatic cinematography, AAA video game cinematic trailer quality, Blur Studio style, realistic proportions with slightly stylized features, epic scale composition, atmospheric fog and particles, 8K ultra detailed. Every character must have a unique and distinct appearance — different face, age, skin tone, hair, body type. Characters must NOT look alike or be copy-pasted, each one should be clearly distinguishable from the others.
Music style
Playful children's dance-pop with a bouncy tropical groove, 120 BPM, approximately 55–65 seconds. Start singing immediately, no instrumental intro. Catchy original melody, simple repetitive hooks, cheerful expressive lead vocals, and a small children's chorus echoing “Who, who, who?” and “No, no, no!”
Bright marimba, plucky ukulele, warm bass, handclaps, and light punchy drums. Clear English pronunciation with one short lyric line per musical phrase. Curious, funny delivery during the search; rising excitement as the hat wobbles; a brief musical pause when the banana is revealed; then a joyful dance chorus. Add subtle comedic sound effects without covering the words. End with a playful spoken-sung “It’s on the floor, right next to me!” and a short giggle.
Scene prompt example 1
Vertical 9:16, photorealistic comedy music video. One adorable small brown monkey with fluffy fur, large expressive brown eyes, a cream muzzle, a turquoise T-shirt, yellow shorts, and an oversized red bucket hat. Bright tropical playroom with a low wooden table, a sofa with a yellow cushion, and a pair of blue shoes on the floor. The monkey is dancing, then stops, looks at his empty paws, and appears puzzled. No banana is visible anywhere.
Scene prompt example 2
Vertical 9:16, photorealistic comedy music video. One adorable small brown monkey with fluffy fur, large expressive brown eyes, a cream muzzle, a turquoise T-shirt, yellow shorts, and an oversized red bucket hat. Bright tropical playroom with a low wooden table, a sofa with a yellow cushion, and a pair of blue shoes on the floor. The monkey searches around himself, looking confused, and gestures playfully toward the camera. No banana is visible.
Scene prompt example 3
Vertical 9:16, photorealistic comedy music video. One adorable small brown monkey with fluffy fur, large expressive brown eyes, a cream muzzle, a turquoise T-shirt, yellow shorts, and an oversized red bucket hat. Bright tropical playroom setting. The monkey bends down to look under the low wooden table, then stands and lifts the yellow cushion on the sofa to check behind it, finding nothing. Blue shoes on floor. No banana is visible.
Scene prompts are written automatically from your lyrics - these are examples from this video.
