Ai Fruit Drama Generator

GLOBAL LOCK: The video features a series of anthropomorphic fruits with hyper-realistic, grotesque human facial features. The subjects include a red apple, a yellow lemon, and an orange. All fruits have deeply wrinkled skin, realistic human teeth, and expressive eyes. Tiny 1:87 scale miniature construction workers wearing orange high-visibility vests and yellow hard hats are positioned on and around the fruits, performing labor with shovels and scaffolding. The setting is a weathered wooden surface, likely a deck or table, with a soft-focus green foliage background. The lighting is natural, diffused daylight. The camera uses a macro lens aesthetic with a very shallow depth of field. The color grade is cinematic with high texture contrast and natural saturation. Audio consists of guttural, distorted vocalizations and wet, crunchy ASMR sound effects.

[00:00–00:04]
A close-up of a red apple with a grumpy, wrinkled human face. Its mouth is slightly open, revealing realistic teeth and gums. Several miniature workers are on top and at the base; one worker on the left is shoveling the apple's skin. The apple's face contorts as if groaning, with the jaw moving up and down. The camera is static, focusing on the facial movement. Guttural "Grah!" sound effect synced to the jaw opening.

[00:04–00:08]
Transition to a yellow lemon with a wide, laughing or screaming human face. The skin is bumpy and textured. Miniature workers are on top, and a small metal scaffolding structure is built on the right side with a worker standing on it. The lemon's mouth opens wide in a silent shout, tongue visible. The camera angle is slightly wider. High-pitched, distorted "Yeah!" vocalization.

[00:08–00:12]
Transition to an orange with an extremely angry expression, bulging eyes, and a furrowed brow. Workers are shoveling orange pulp at the base. Suddenly, thick red liquid (resembling blood or lava) erupts from a hole in the top of the orange's head like a volcano. Simultaneously, the orange opens its mouth wide and sticks out a long tongue as red liquid flows out. The eruption is violent with droplets splashing. Sound of a wet explosion and squelching.

NEGATIVE PROMPT: Smooth skin, cartoonish features, low resolution, blurry textures, plastic-looking fruit, static faces, silent audio, bright studio lighting, clean clothes on workers, floating objects, flickering liquid, robotic movement, watermark, text.

SPEECH PACK:
[00:00-00:04]
Transcript: [Guttural groan/shout] "GRAAAH!"
TAKE_A: Deep, gravelly, low-pitched roar.
TAKE_B: Short, sharp, pained grunt.
TAKE_C: Distorted, monster-like vocalization.

[00:04-00:08]
Transcript: [Distorted shout] "YEAAAH!"
TAKE_A: High-energy, manic laughter-scream.
TAKE_B: Aggressive, distorted cheer.
TAKE_C: Glitchy, pitched-up vocal burst.

[00:08-00:12]
Transcript: [Eruption sound + Gurgle]
TAKE_A: Wet, bubbling sound followed by a deep "BLARGH".
TAKE_B: Explosive "POP" followed by liquid flowing sounds.
TAKE_C: Visceral, squelching eruption noise.

GLOBAL LOCK: Create a vertical, hyper-detailed surreal food animation set on a warm sunlit kitchen counter. The central object is a freshly cut fig standing upright like a sacred forbidden fruit, its ruby-red interior glossy, wet, and tactile, with thick crimson juice pooling onto the countertop. Beside it are small anthropomorphic produce characters, especially a smiling peeled onion or garlic-like figure with a tufted top and a tall corn cob character with a textured yellow body and leafy husk styling. Keep the overall tone whimsical but slightly uncanny, with soft morning light, creamy highlights, shallow depth of field, and strong ASMR-style food texture emphasis. No dialogue, no text, no camera cuts beyond the scene progression; let the camera remain close and intimate with subtle handheld or slider motion.

[00:00-00:02] Start with a hero close shot of the halved fig alone on the kitchen counter. The fig is upright, glistening, and oozing deep red syrup or juice onto the smooth surface. Warm sunlight from the left creates soft reflections on the liquid, while the blurred kitchen cabinets and window glow in the background.

[00:00:02-00:00:04] Introduce the anthropomorphic produce companions. A cheerful onion or garlic-like figure with a tufted white top steps into frame near the fig, followed by a tall corn cob character with expressive eyes and a playful grin. Their bodies are stylized but tactile, like handcrafted edible mascots sharing the same countertop world.

[00:00:04-00:00:06] The onion-like character climbs or presses against the fig’s open red center, interacting with the sticky fruit flesh. The corn character leans in from the side, observing or reacting. Emphasize the contrast between glossy fig seeds, dripping juice, and the matte fibrous textures of the other produce characters.

[00:00:06-00:00:08] The fig begins to deform under the contact, becoming more molten and creamy. Pink-red syrup thickens around the base, and the onion-like figure appears partially enveloped by the fruit. Keep the motion slow, squishy, and ASMR-like, with every surface looking richly tactile.

[00:00:08-00:00:10] A pale cream glaze or milky sauce begins to pour or bloom over the fig and the small produce character, creating a forbidden-dessert effect. The once-clean cut fruit becomes a sticky, overflowing sculpture of white cream, red pulp, and soft collapsing flesh. The corn character remains nearby as an amused witness.

[00:00:10-00:00:11] End on the messy climax: the fig has collapsed into a luscious pool of white cream and crushed red fruit, splashing across the countertop while the anthropomorphic produce figures stand amid the aftermath. The final image should feel indulgent, grotesque, and satisfying, like an AI food-art ASMR payoff.

NEGATIVE PROMPT: low-detail food textures, plastic-looking fruit, dry surfaces, dark moody lighting, extra characters, warped anatomy, horror gore, insects, dirt, burnt textures, text overlays, watermarks, subtitles, harsh camera shake, unrealistic empty background, flat lighting, dull colors, broken liquid physics.

GLOBAL LOCK:
Subject is a stylized anthropomorphic banana with a smooth yellow peel, wearing small blue denim shorts. The banana has a humanoid posture and thin, yellow limbs. The environment is a realistic kitchen with dark forest green cabinets, a rustic wooden table, and a large window with soft, natural daylight. The lighting is cinematic with soft shadows and high-key highlights. The color grade is warm and saturated. A bowl of berries (strawberries, blueberries, blackberries) with small, expressive cartoon faces sits on the table.

[00:00–00:02]
The anthropomorphic banana stands on a wooden table, facing away from the camera toward a white ceramic bowl filled with fruit. The camera is at a medium-low angle, slightly behind the banana. The banana is static, looking at the fruit. The fruit in the bowl have small, curious eyes.

[00:02–00:04]
The banana reaches back and peels its own skin down from its "shoulders" to its waist, revealing a rounded, peach-like "butt" made of the inner white banana fruit. Simultaneously, a small yellow Minion character with goggles floats into the upper right corner of the frame, looking down. The camera pushes in slightly toward the banana's back.

[00:04–00:07]
The banana's "tail" (the bottom tip of the peel) curves upward and begins spraying a thick, realistic stream of white cream or milk into the bowl of fruit. The motion is fluid and continuous. The berries in the bowl change their expressions to wide-eyed shock and fear.

[00:07–00:10]
The cream continues to fill the bowl, splashing over the berries. The camera remains in a close-up on the bowl and the banana's lower half. The berries are now partially covered in white liquid, their faces showing extreme distress. The lighting remains consistent, highlighting the glossy texture of the liquid.

NEGATIVE PROMPT:
Flickering, morphing limbs, distorted faces on fruit, blurry textures, inconsistent denim shorts color, robotic movement, low resolution, watermark, text, messy liquid physics, floating artifacts, sudden lighting changes.

SPEECH PACK:
(No speech present in the original video, only background music and sound effects.)
TAKE_A: [Whimsical orchestral music with a "pop" sound at 00:02 and a "fountain spray" sound at 00:04]
TAKE_B: [Upbeat jazz track with a "slide whistle" during the peel and "bubbling" sounds during the spray]
TAKE_C: [Silent background with hyper-realistic foley: fabric rustle, peel snapping, and liquid splashing]

MASTER PROMPT

Absurd cinematic character short starring an anthropomorphic banana man named Mr. Big, vertical 9:16, surreal comedy-drama, expressive humanlike banana with eyes, mouth, arms, and legs, moving through a sequence of stylish urban and intimate scenes: flashy city introduction, campus popularity, lonely prom, fast-food counter, late-night bedroom reflection, quiet morning kitchen, then a return to swagger. Premium cinematic color, emotional performance, slightly satirical tone, social-first pacing.

GLOBAL LOCK: Keep the main character consistent across the whole video: a tall bright-yellow anthropomorphic banana with peel texture, expressive face, smooth cartoon-real hybrid anatomy, white gloves or yellow hands, humanlike legs, and emotionally readable eyes and mouth. In the “cool” scenes he wears a leopard-print coat and matching wide-brim hat; in formal scenes he may wear a tuxedo jacket; in quieter scenes he appears simpler and more vulnerable. Preserve polished cinematic lighting, realistic environments, controlled camera work, and a tonal arc that moves from confidence to loneliness to self-awareness and back to charisma.

[00:00-00:06]
Mr. Big is introduced on a sunlit city street beside a red convertible and glamorous women, wearing a leopard-print coat and hat. He smirks, counts money, and poses with exaggerated confidence in golden-hour light. The camera alternates between medium full-body swagger shots and tighter portrait shots that emphasize his self-satisfied grin.

[00:06-00:12]
Cut to a bright outdoor campus plaza where the same banana character appears without the luxury styling, standing among students and trying to act cool. He waves awkwardly, flirts, and moves with overstated confidence while people around him react casually. The mood is playful and slightly cringed.

[00:12-00:18]
Transition to a prom or formal dance floor with purple-blue party lights. Mr. Big now wears a tuxedo and holds a drink, but his expression turns sad and uncertain. Close-ups emphasize his drooping eyes and lonely mood in a room full of couples and celebration.

[00:18-00:24]
At a fast-food counter under warm fluorescent lights, the banana stands at the register looking rejected and embarrassed. He turns sideways and slumps slightly while workers and customers watch. The camera stays medium-wide and observational, making the character look exposed and awkward.

[00:24-00:34]
Night interior in a dim bedroom. Mr. Big stands alone near a mirror and bed under a warm bedside lamp, staring at his reflection with a heavy, self-critical expression. The shots alternate between side profile, mirror framing, and frontal sadness. The room is quiet, intimate, and melancholic.

[00:34-00:42]
Morning kitchen sequence. The banana appears smaller and softer in posture beside a bowl of fruit on a table, almost like he is reconsidering his whole identity. Natural morning light enters from the window while he gestures or raises his arms in a moment of comic existential frustration.

[00:42-00:52]
The final act loops back to swagger: Mr. Big returns to the city street and convertible, again dressed in leopard print and hat, smoking or posing with casual superiority as the sun glows behind him. End on a half-ironic, half-triumphant close-up that suggests the character learned nothing and everything at once.

NEGATIVE PROMPT

bad anatomy, warped banana peel, broken face, lifeless eyes, extra limbs, missing limbs, low-resolution textures, inconsistent banana color, cheap mascot suit look, horror gore, childish low-detail cartoon, shaky camera, muddy lighting, flat composition, unreadable expression, environment flicker, deformed convertible, broken hands, watermark, text overlay, logo

GLOBAL LOCK: A sentient tomato plant in a terracotta pot, 3D animation style with a tactile claymation texture. The pot has a wide, expressive human-like face with large blue eyes and a mischievous grin. The tomatoes on the vine also have expressive faces with large eyes. The setting is a rustic kitchen windowsill with a wooden frame, a lace curtain to the left, and warm golden hour sunlight streaming in. The color palette is dominated by vibrant reds, earthy terracotta oranges, and lush greens, with a warm, high-contrast lighting grade. Consistent high-quality fluid simulation for liquids. Audio: High-pitched cartoonish gibberish and squelching sounds.

[00:00–00:02]
The terracotta pot and the two main tomatoes on the vine wake up. Their eyes pop open simultaneously. The pot has a sleepy but waking expression, while the tomatoes look surprised. Static medium close-up shot. Lighting is warm and directional from the right.

[00:02–00:05]
The tomato on the left opens its mouth wide, sticking out a pink tongue. A thick, opaque white liquid (resembling milk) begins to spill out of its mouth and down the side of the pot. The pot's face shifts into a wide, toothy grin. Slight camera zoom-in.

[00:05–00:08]
The left tomato "vomits" a larger stream of the white liquid, which pools around the base of the plant inside the pot. The pot's eyes widen in delight, and its mouth opens to reveal a tongue. The liquid has realistic viscosity and highlights.

[00:08–00:11]
A long, muscular, prehensile tongue extends rapidly from the mouth of the left tomato, reaching toward the right side of the frame. The camera follows the tongue's movement. The pot's face remains in a fixed, creepy grin with its own tongue sticking out.

[00:11–00:14]
The extended tongue pierces a smaller tomato on the right side of the vine. Vibrant red juice and seeds splatter upon impact, mixing with the white liquid. The tongue then retracts slightly. The scene maintains its high-contrast, sun-drenched aesthetic. The cut lands on the final "splat" sound.

NEGATIVE PROMPT: Realistic photography, human skin texture, blurry backgrounds, low resolution, flickering light, robotic movement, flat lighting, desaturated colors, text, watermarks, inconsistent facial features, jittery motion, silent audio.

SPEECH PACK:
[00:00-00:14]
Transcript: (High-pitched cartoon gibberish) "Ooh! Ah-ha! Blurp... Squelch... Ha-ha!"
TAKE_A: Energetic and squeaky, matching the eye-pop.
TAKE_B: More gurgly and wet, emphasizing the liquid spill.
TAKE_C: Mischievous and laughing, focusing on the pot's grin.
Prosody: Rapid-fire delivery, rising intonation on the "Ooh!", wet squelching sounds synced to the liquid and tongue.
Sync: High lip-sync strictness for the tomato and pot's mouth movements.

GLOBAL LOCK: 
Cinematic food photography style. A rustic wooden bowl sits on a weathered wooden table. The scene is bathed in warm, golden hour sunlight streaming from the side, creating long, soft shadows and glowing highlights. The subject is a group of anthropomorphic penne pasta pieces and one large, curvaceous red tomato. The penne pasta pieces have small, expressive human faces (eyes, mouths) with mischievous and joyful expressions. The tomato has a feminine face with long black eyelashes, green-painted lips, and a curvaceous, "butt-like" shape at its base. High detail, 4k, shallow depth of field with a blurred background of a sunlit room. Consistent warm color palette (reds, oranges, browns). Audio consists of high-pitched, squeaky gibberish voices and wet slurping sounds.

[00:00–00:03]
Extreme close-up of the wooden bowl. The tomato is on the right, looking toward the pasta pieces on the left. The pasta pieces are wiggling and making squeaky noises. The tomato blinks its long eyelashes and moves its green lips as if whispering. Static camera, macro lens feel.

[00:03–00:06]
The tomato makes an exaggerated "O" face, looking surprised and delighted. The penne pasta pieces look up toward the top of the frame, their mouths open in anticipation. The lighting catches the moisture on the tomato's skin.

[00:06–00:10]
A thick, vibrant red tomato sauce begins to pour from above in two distinct streams, drenching the tomato and the pasta. The characters react with excitement; the pasta pieces stick their tongues out to catch the sauce. The sauce splashes realistically against the wooden bowl. High-speed camera feel to capture the liquid dynamics.

[00:10–00:13]
A human hand enters the frame from the top left, sprinkling a generous amount of white shredded mozzarella cheese over the sauce-covered characters. The tomato has its tongue out, looking ecstatic. The pasta pieces are partially buried in sauce and cheese but continue to move.

[00:13–00:15]
Final shot of the bowl overflowing with sauce and cheese. The tomato's face is visible through the cheese, still making a joyful, exhausted expression. The camera slightly zooms in. The lighting remains warm and golden.

NEGATIVE PROMPT: 
Blurry faces, distorted anatomy, flickering light, plastic texture, low resolution, static eyes, robotic movement, muted colors, cold lighting, text, watermarks, messy sauce physics, inconsistent character features.

SPEECH PACK:
[00:00-00:03] 
TAKE_A: (High-pitched squeaks) "Ooh, look at them! Hehe!"
TAKE_B: (Squeaky gibberish) "Mi-mi-mi-mi! My turn!"
TAKE_C: (Excited chirps) "Is it time? Is it time?"

[00:06-00:10]
TAKE_A: (Slurping sounds) "Mmm, yeah! Splash it!"
TAKE_B: (Gurgling joy) "Ohhh, so warm! Hehe!"
TAKE_C: (Wet splashes) "Yesss! More sauce!"

[00:10-00:15]
TAKE_A: (Soft sigh) "Cheese please... ahhh."
TAKE_B: (Happy squeak) "It's snowing! Hehe!"
TAKE_C: (Satisfied moan) "Perfect... mmm."

GLOBAL LOCK: 
Subject is a series of hyper-realistic, hand-blown glass fruits (pomegranate, apple, pear). The material is highly translucent with realistic refractive indices and intricate caustics. The environment is a minimalist, high-end interior with white draped fabric and clean white/glass plates. Lighting is soft, directional window sunlight creating sharp, beautiful light patterns (caustics) on the surfaces. The color grade is clean, high-key, and editorial with a slight dreamy glow. Camera language is steady, cinematic close-ups with shallow depth of field. No speech, purely visual and motion-driven.

[00:00–00:03]
A close-up of a ruby-red glass pomegranate on a white plate. The pomegranate suddenly shatters from the inside in slow motion, its crystalline shell breaking into large shards while hundreds of glowing, jewel-like red seeds spill out and bounce softly. The lighting captures the refraction through the breaking glass. A silver fork is visible in the foreground.

[00:03–00:05]
A medium close-up of a translucent, soft pink glass apple sitting on a clear glass plate. A silver fork lies next to it. The camera subtly zooms in. The lighting is bright and airy, highlighting the smooth, curved surface of the pink glass and the soft shadows on the white fabric background.

[00:05–00:07]
A close-up of a golden-amber glass apple. Thick, viscous golden honey is being poured from a silver fork held above, draping over the apple and pooling on the glass plate below. The honey is translucent and catches the light, creating a warm, glowing effect. The motion of the honey is slow and heavy.

[00:07–00:10]
A medium close-up of a bright yellow, liquid-filled glass pear. It sits on a white ceramic plate with a gold-rimmed edge. A silver fork stands vertically behind it. The camera has a very slight handheld shimmer. The pear glows from within as sunlight hits it, casting vibrant yellow caustics onto the white tablecloth.

NEGATIVE PROMPT:
Plastic texture, opaque materials, low resolution, jittery motion, unrealistic liquid physics, dark shadows, messy background, distorted fork tines, flickering light, muddy colors, cartoonish style, air bubbles in glass (unless intentional), flat lighting, watermark, text.

SPEECH PACK:
(No speech present in the reference video. Focus is entirely on visual foley and ambient music.)
- Audio Suggestion: Soft crystalline tinkling for the pomegranate shatter, a thick "glug" or "drip" sound for the honey, and a low ambient synth pad for the overall atmosphere.

GLOBAL LOCK: Create a vertical surreal fast-food ASMR animation set on a Taco Bell-style restaurant tray or prep counter. The scene is crowded with anthropomorphic ingredients: a glossy red tomato character, a curvy avocado or guacamole-green character, browned meat patties or taco filling, shredded lettuce, diced tomatoes, cups of sour cream, and bottles of hot sauce. The overall mood is chaotic, funny, indulgent, and messy, like a food fight turning into a fully loaded fast-food disaster. Use cinematic close-up lighting, warm steam from grills in the background, saturated food colors, and rich tactile detail in sauces, toppings, and splashes. No dialogue, no subtitles, no text.

[00:00-00:04] Open on a loaded fast-food plate with browned meat in the center, lettuce underneath, and anthropomorphic tomato and avocado characters flanking the mound. The tomato character is glossy, red, and energetic; the avocado is green, fleshy, and expressive. Steam rises from a grill in the background, establishing a fast-food kitchen atmosphere.

[00:00:04-00:07] The tomato character jumps or stomps onto the meat, releasing a cascade of diced tomato pieces. The avocado character leans in from the side, reacting with delight or mischief. The plate becomes more crowded with chunks, juices, and garnish, but the overall composition remains readable from a close-up front angle.

[00:00:07-00:10] The avocado character climbs over the center mound, adding guacamole-like flesh and green smears. Both produce characters now actively shape the dish, as if assembling it through chaos. Keep the texture contrasts clear: glossy tomato, creamy avocado, rough browned meat, and crisp lettuce.

[00:00:10-00:13] A white sauce, sour cream, or melted cheese is poured over the center pile from above, coating the meat and vegetables in thick drips. The tomato and avocado characters remain visible as the sauce floods the plate, turning the scene from playful to fully indulgent and messy.

[00:00:13-00:16] Red hot sauce bottles or packets appear and squeeze or spill spicy sauce across the already loaded pile. The plate becomes a chaotic mountain of meat, diced tomato, white sauce, and red sauce. The tomato character looks triumphant while the avocado character seems overwhelmed but delighted.

[00:00:16-00:18] End on a maximal fast-food eruption: the central mound bursts upward like a cheesy volcano, with steam, sauce, and fillings spraying as the anthropomorphic ingredients frame the blast. The final image should feel absurd, overstuffed, and deeply satisfying for messy food-ASMR viewers.

NEGATIVE PROMPT: dry toppings, low-detail lettuce, dull tomato color, plastic avocado, broken sauce physics, dark muddy fast-food environment, insects, gore, text overlays, subtitles, watermarks, duplicate ingredient characters, flat lighting, unrealistic tray scale, weak steam, burnt black food.

GLOBAL LOCK: Vertical surreal macro miniature-world video showing tiny construction workers operating on oversized fruit placed on dark soil. The fruit changes across the clip: a red apple, a strawberry, a watermelon, a purple grape, and a cut citrus fruit. Miniature workers in helmets and workwear climb, drill, cut, inspect, and enter the fruit as if each one is an excavation site or tiny building. Camera is shallow-depth-of-field macro with soft natural light, earthy ground textures, vivid fruit surfaces, and whimsical industrial action. The scale contrast between the tiny workers and the fruit must remain the central visual hook throughout.

[00:00-00:03] Open on a glossy red apple resting on soil while tiny workers surround it with ladders, tools, and climbing motions. The apple is then shown partially opened or cored out, revealing holes and an internal cavity as if the workers have excavated it. Keep the camera low and close, making the workers feel ant-sized against the fruit.

[00:03-00:05] Transition to a large strawberry split into a clean vertical opening, with multiple workers standing on the outside and inside edge as though inspecting or constructing within the fruit. The red surface, seeds, and green leaves stay crisp and oversized, while the crew adds a miniature industrial narrative.

[00:05-00:07] Show a watermelon on soil, then a cut section revealing a hollowed interior like a tiny red room. Small workers gather around and inside it, turning the fruit into a miniature habitat or worksite. The macro lens should emphasize moist flesh texture and the dramatic curvature of the rind.

[00:07-00:09] Move to a purple grape sliced open like a pod, with workers climbing ladders and using tools along the glossy skin and exposed interior. The lighting stays soft and tactile, making the grape surface look enormous and almost architectural at this scale.

[00:09-00:11] End on a yellow citrus fruit, partially cut to reveal pink flesh inside, while workers appear to be drilling, entering, or servicing the fruit as if it were another tiny construction project. Keep the soil base, shallow focus, and whimsical miniature-labor logic consistent through the final frame.

GLOBAL LOCK: preserve a creator-led talking-head tutorial format mixed with vertical phone screen recordings. Keep one young male creator in a backward black cap and dark hoodie speaking directly to camera in a studio setup with a microphone. Intercut iPhone-style screen captures showing ChatGPT/OpenAI image workflow steps, uploaded object photos, prompt entry, and AI video generation screens. Maintain a practical “make from your phone” educational reel structure. No random B-roll, no unrelated tools, no logo overlays beyond app UI already present in the source.

Create a 37.8-second social-first AI tutorial reel showing how to turn ordinary phone photos into animated AI character videos. Begin with a hook using a simple hand-held object photo and bold on-screen teaching posture from the creator. Then show phone interfaces: photo selection, ChatGPT or image-tool screens, prompt entry, image transformation results, switching to an AI video tool, uploading the generated image, entering a motion prompt, and generating the final animated output. Use repeated face-cam segments where the creator explains the steps and emphasizes that the workflow can be done from a phone.

Include the specific examples visible in the source: tiny object/food photos held in a hand, ChatGPT app icon and mobile interface, typed prompts that turn objects into cute expressive characters, a generated pear-like baby character image, a switch to another AI generation interface, upload and prompt steps for video, and a final generated moving result shown on-screen. Preserve the educational pacing and creator-marketing vibe.

SHOT SEGMENTS:
[00:00-00:06] Hook with object photos in hand and creator talking-head intro about making AI content from your phone.
[00:06-00:14] Mobile screens show ChatGPT / image workflow setup, app screens, and prompt entry.
[00:14-00:22] Creator explains the key steps while on-screen phone UI shows prompt refinement and generated object-to-character image outputs.
[00:22-00:30] The tutorial switches to an AI video tool, showing upload, prompt, and generation steps from the phone.
[00:30-00:37.8] Final result displays the generated animated character clip, while the creator closes with a call to try the workflow.

ENVIRONMENT: creator desk/studio face-cam plus crisp mobile screen recordings. CAMERA: direct-to-camera presenter shots alternating with full-screen phone UI captures. LIGHTING: clean creator-studio lighting on face-cam; bright legible phone UI on inserts. MOTION: tutorial pacing, finger taps on phone UI, creator emphasis gestures, no cinematic narrative scenes.

NEGATIVE PROMPT: generic AI ad montage, unrelated tools, desktop-only workflow, no phone UI, missing creator face-cam, subtitles replacing the actual visible UI, blurry screens, watermark, logo overlays.

SPEECH PACK: creator-to-camera tutorial speech implied, but do not transcribe captions here.

GLOBAL LOCK: The video features a series of anthropomorphic food characters with highly detailed, human-like facial features, including large expressive eyes, long eyelashes, and full, expressive lips. The style is photorealistic 3D animation, reminiscent of a high-budget animated film. Lighting is consistently warm and cinematic, often suggesting golden hour or a cozy kitchen. The color palette is vibrant and saturated. Motion is fluid and intentional, with a focus on character expressions and dynamic liquid physics (sauces, condiments).

[00:00–00:14]
A wooden bowl sits on a rustic wooden table under warm, dappled sunlight. Inside, several penne pasta tubes have mischievous human faces. A large, round red tomato with a female face (full green lips, long lashes) sits among them. The tomato has a shocked expression, then "ejaculates" a thick stream of red tomato sauce from its "butt" (the bottom of the tomato) onto the pasta. The pasta characters react with joy and laughter. The sauce is viscous and splashes realistically.

[00:15–00:33]
On a wooden sushi board in a traditional Japanese kitchen, a piece of salmon nigiri has a female face with heavy makeup and a suggestive expression. A triangular onigiri (rice ball) with a mischievous male face and black seaweed "pants" stands over it. The onigiri aggressively smears green wasabi onto the salmon's "back," then pours dark, glossy soy sauce from a nearby bottle over the salmon. The salmon character has an exaggerated, ecstatic expression with its tongue out.

[00:34–00:50]
In a bright, modern kitchen, a hot dog bun with large female lips and eyes lies open. A grilled sausage with a smug male face stands over it, holding a small, terrified pickle character. The sausage "stuffs" the pickle into the bun. Then, the sausage holds a crying onion character and "chops" it, sprinkling white onion bits over the bun. Finally, anthropomorphic ketchup and mustard bottles "ejaculate" their contents over the bun. The bun character has an exaggerated, cross-eyed expression of pleasure.

[00:51–01:07]
A single large macaroni tube with a female face and a large "butt" stands on a wooden counter. A small, square block of cheese with a devious face approaches. The cheese block climbs onto the macaroni and begins to "melt" into it, turning into a thick, gooey yellow cheese sauce that coats the macaroni. The macaroni character performs suggestive, rhythmic movements. The scene ends with the macaroni "exploding" into a pile of smaller mac and cheese.

NEGATIVE PROMPT: blurry, low resolution, distorted faces, static eyes, robotic movement, thin watery sauce, flat lighting, cartoonish, 2D, watermark, text, flickering, inconsistent character features, messy liquid physics.

An 11-second surreal macro food metamorphosis video shot on a clean neutral tabletop background. The clip presents a sequence of isolated ingredients in close-up: first an avocado half or avocado-shaped form, then a white egg, then a whole pineapple. Each food item is centered in frame and treated as if it has a soft circular opening on its surface. From these openings, smaller ingredients slowly emerge and protrude outward, including a pickle or cucumber-like piece, a smooth white cylindrical piece, and finally a strawberry-like fruit. The camera remains mostly static and tightly framed, emphasizing tactile textures such as avocado skin, eggshell smoothness, and pineapple rind detail. Lighting is bright, soft, and studio-clean, with shallow depth of field and minimal background distraction. The tone is absurd, uncanny, and visually satisfying, focusing on impossible food transformations rather than cooking or realism.

GLOBAL LOCK: Create a vertical surreal sushi-ASMR animation on a rustic kitchen prep board. The hero subject is an anthropomorphic salmon nigiri with expressive eyes and lips, lying on a wooden cutting board beside a mischievous or aggressive rice-ball character. The world is a warm Japanese-inspired kitchen with hanging herbs, soft daylight through a window, and tightly framed food textures. The sequence should feel playful, grotesque, and deeply tactile, emphasizing salmon sheen, rice grain texture, nori wrap tension, glossy sauces, and popping fish roe. No dialogue, no text, no subtitles. Use close-up cinematic food photography with subtle camera movement and strong material transformation.

[00:00-00:03] Open on the salmon nigiri creature resting on a cutting board. The salmon topping has a glossy orange surface and a face embedded in it, while a white rice-ball character with angry expressive brows leans in nearby. The kitchen is warm and rustic, with herbs, bowls, and a soft window glow in the background.

[00:00:03-00:06] The rice-ball character begins to attack, prod, or climb over the salmon nigiri. The salmon face reacts with discomfort while the rice figure presses into the fish and board. Keep the motions small but readable, with tactile pressure and slight wobble in the sushi structure.

[00:00:06-00:09] Additional ingredients and tools enter the frame. A tiny sauce-spraying or torch-like mechanical arm appears, and the sushi begins to shift from a simple nigiri into a more layered, overbuilt form. The rice-ball character remains dominant, as if assembling or transforming the dish through force.

[00:00:09-00:12] A sheet of glossy nori wraps partly around the salmon, while roe-like pearls or sauce beads begin to appear. The salmon face is partially obscured as the sushi becomes denser, richer, and more grotesquely appetizing. Emphasize shiny seaweed, sticky rice, and moist salmon surface transitions.

[00:00:12-00:15] The sequence ends in a maximal sushi payoff: the transformed roll or nigiri is now covered or surrounded by a mound of bright salmon roe, with the rice-ball character looming above as if victorious. The board becomes crowded with glossy orange pearls, dark nori bands, and layered fish flesh. End on a dense close-up that feels indulgent, absurd, and ASMR-satisfying.

NEGATIVE PROMPT: dry sushi, low-detail rice, plastic salmon, broken nori physics, dark muddy kitchen, gore, insects, duplicate characters, flat lighting, subtitles, text overlays, watermarks, unrealistic chopsticks, broken mechanical arm anatomy, weak roe texture, blurry food surfaces.

GLOBAL LOCK: 
Subject: A series of hybrid animal-fruit creatures. 
Style: High-end 3D animation, Pixar-like aesthetic, hyper-realistic textures (fur, fruit skin, feathers). 
Environment: Natural settings (forest, snow, jungle) with deep depth of field and soft bokeh. 
Lighting: Cinematic, warm dappled sunlight or bright high-key snow light. 
Color Grade: Highly saturated, vibrant colors, clean contrast. 
Camera: Slow tracking shots, low angles to emphasize cuteness. 
Audio: Rhythmic electronic beat, no speech, sound effects for transitions.

[00:00–00:03]
Visual: A realistic tabby cat with white paws sits on a mossy forest floor on the left. A giant, glossy red strawberry sits on the right. A white "+" sign is between them. Text "Cat" above the cat, "Strawberry" above the strawberry.
Camera: Static wide shot.
Lighting: Warm sunlight filtering through trees.

[00:03–00:06]
Visual: A hybrid "Strawberry Cat" creature. It has the body of a small kitten but its fur is replaced by a red strawberry texture with tiny seeds. It has green strawberry leaves as a "hat" or ears. Large, glossy black eyes. It walks slowly across a wooden surface.
Camera: Low-angle medium shot, tracking the movement.
Motion: Smooth walking, slight head tilt.

[00:07–00:10]
Visual: An Emperor penguin stands on the left in a snowy landscape. A large, ripe yellow pear sits on the right. A white "+" sign between them. Text "Penguin" and "Pear".
Camera: Static wide shot.
Lighting: Bright, cool, high-key daylight.

[00:10–00:13]
Visual: A hybrid "Pear Penguin". The body is shaped exactly like a yellow pear with a small green leaf on top, but it has penguin flippers, a beak, and large eyes. It waddles on the snow.
Camera: Eye-level close-up.
Motion: Characteristic penguin waddle, blinking eyes.

[00:14–00:17]
Visual: A tall ostrich stands on a dirt path in a forest on the left. A single yellow banana sits on the right. A white "+" sign between them. Text "Ostrich" and "Banana".
Camera: Static wide shot with a fast digital zoom-in transition at the end.

[00:17–00:21]
Visual: A hybrid "Banana Ostrich". The main body is a large, partially peeled yellow banana. The neck and legs are those of an ostrich. It walks gracefully through a tropical jungle.
Camera: Full shot, tracking the ostrich from the side.
Motion: Long strides, neck bobbing.

[00:22–00:24]
Visual: A small sparrow perched on a mossy branch on the left. A bright red chili pepper on the right. A white "+" sign between them. Text "Sparrow" and "Pepper".
Camera: Static close-up.

[00:24–00:28]
Visual: A hybrid "Pepper Sparrow". The bird's body is a plump, red chili pepper. The stem of the pepper acts as a crest on its head. It has small wings and a beak. It sits on a branch and chirps.
Camera: Extreme close-up.
Motion: Subtle chirping movement, tail twitch, eyes closing at the very end.

NEGATIVE PROMPT: 
Visual: Morphing limbs, distorted faces, blurry textures, low resolution, watermark, text glitches, extra legs, messy fur, dull colors, flat lighting, jittery motion, flickering shadows.
Speech: N/A (No speech in video).

SPEECH PACK:
(No speech present in the original video. The audio consists of a rhythmic music track and transition sound effects.)

GLOBAL LOCK:
Subject: Anthropomorphic carrot-like creatures and hybrid surreal entities. Vibrant orange and red skin with fibrous vegetable textures. Wardrobe includes pinstriped suits, grey blazers, and red high-top sneakers. 
Environment: Outdoor desert and beach settings, clear blue skies, minimalist landscapes. 
Lighting: Harsh, direct midday sunlight, high contrast, sharp shadows. 
Color Grade: Highly saturated warm tones (red/orange) vs. cool blue skies. 
Camera Language: Static shots or slow tracking/dolly movements, symmetrical compositions. 
Speech: None. 
Audio: Upbeat, quirky rhythmic electronic music.

[00:00–00:02]
Subject: Two tall surreal figures. On the right, a humanoid with red-horned helmet, red and white segmented suit, and white sneakers. On the left, a creature with a large red-and-white striped mushroom cap head and multiple thin, striped legs. Small human figures stand on top of the mushroom cap.
Environment: A flat, sandy beach under a clear blue sky.
Action: The figures stand still, small figures on top wave their arms.
Camera: Wide shot, static, eye-level.
Lighting: Bright, direct sunlight from the side.

[00:02–00:03]
Subject: A tall, multi-tiered red mushroom creature with small red caps on stalks. It has long, yellow, segmented legs and wears large black boots. A smaller version walks beside it.
Environment: A desert road with a cloudy sky.
Action: The creatures walk forward with a rhythmic, heavy stride.
Camera: Medium-wide shot, tracking the movement.
Lighting: Softened daylight with high contrast.

[00:03–00:05]
Subject: A carrot-octopus hybrid with a large orange carrot head, two large eyes, and many long, orange carrot-tentacles for legs.
Environment: A neutral grey studio-like background.
Action: The creature hangs from a rope by its head, tentacles waving and writhing in the air.
Camera: Medium shot, low angle looking up.
Lighting: High-key studio lighting with sharp shadows.

[00:05–00:06]
Subject: A creature with a segmented red body and a pinstriped suit. It has long antennae and small red-headed figures standing on its outstretched arms and floating nearby.
Environment: A grey, minimalist space.
Action: The creature stands with arms wide, small figures balance on its limbs.
Camera: Medium shot, static.
Lighting: Flat, bright lighting.

[00:06–00:08]
Subject: A sliced red carrot creature with a single large eye in the center. It has many white "slices" protruding like fins and walks on a single, thin leg. Tiny red figures are perched on the slices.
Environment: A flat, sandy plain under a deep blue sky.
Action: The creature hops or walks forward rhythmically.
Camera: Full shot, profile view, tracking.
Lighting: Intense, direct sunlight.

[00:08–00:09]
Subject: A man with a large, spiky orange carrot head and two bulging eyes. He wears a grey pinstriped suit and red shoes.
Environment: A vast desert landscape.
Action: The man walks confidently toward the camera.
Camera: Medium shot, tracking his walk.
Lighting: Natural desert sun, high contrast.

[00:09–00:11]
Subject: Two striped carrot creatures with blue, palm-tree-like hair. One is tall and thin, the other is shorter and more robotic. They have white sneakers.
Environment: Standing on the roof of a small building in a desert. A line of small figures stands below.
Action: The creatures make slight, jerky movements. A spark or flash occurs at their feet.
Camera: Wide shot, symmetrical composition.
Lighting: Cinematic, slightly muted daylight.

[00:11–00:13]
Subject: A sliced carrot creature in a pinstriped suit and red sneakers. It is being moved by thin strings like a puppet. Smaller carrot-puppets float around it.
Environment: A bright desert under a blue sky.
Action: The creature walks forward, its limbs moving in a puppet-like, jerky fashion.
Camera: Medium shot, tracking from the side.
Lighting: Bright, clear daylight.

[00:13–00:15]
Subject: Two orange carrot-like creatures with palm tree hair. Their bodies are covered in multiple yellow "smiley face" eyes. They have many tentacles at the base.
Environment: A desert with large white clouds in the background.
Action: The creatures stand still, their many eyes blinking or shifting slightly.
Camera: Medium shot, static.
Lighting: Warm, late-afternoon sun.

[00:15–00:18]
Subject: A giant carrot puppet wearing a grey pinstriped suit. It has two large carrots as ears/horns. Small red figures pull on strings attached to it.
Environment: A sandy desert.
Action: The giant puppet is pulled down, falling forward into a massive cloud of sand and dust.
Camera: Wide shot, high angle.
Lighting: Dramatic, dusty, bright sunlight.

NEGATIVE PROMPT:
Visual: Blurry textures, low resolution, distorted faces, extra limbs that don't fit the surreal theme, flickering lights, jittery motion, text, watermarks, logos, messy backgrounds, dull colors, inconsistent lighting.
Speech: N/A (No speech in video).

SPEECH PACK:
(No speech present in the original video. The audio consists of a rhythmic electronic music track.)
Transcript: N/A
Delivery: N/A
Sync: N/A

A creator-led vertical tutorial explains how to build a viral AI-generated TikTok series. The video combines talking-head instruction, account examples, and screen-recorded walkthroughs. Early on, the presenter introduces a successful anime-style storytelling account as proof of concept, showing follower counts, monthly growth, and examples of short serialized episodes built around recurring characters and cinematic scenes. He then breaks down the workflow using tools such as ChatGPT for scripting, image-generation platforms for visual development, and video-generation tools like Higgsfield or Kling to animate shots, change camera angles, and turn still frames into repeatable episode content. The tutorial focuses on consistency, character-driven storytelling, scene generation, motion design, and how to convert single-shot outputs into a coherent multi-video series optimized for short-form social media.