Break down 1 winning video → your own AI Skill makes videos using that exact formula Coming soon

MASCOT_MEO_MUOP, a chubby anthropomorphic orange tabby cat mascot in 3D Pixar style, standing upright on two legs, big round amber eyes with long lashes, soft fluffy fur with clear tiger stripes on the forehead, a small pink nose, wearing a mint-green knee-length apron with one front pocket over a plain white short-sleeve shirt, a tiny round gold star badge pinned on the left side of the apron, expressive eyebrows, rounded friendly proportions, four-fingered paw-hands with clean pads, a small baby sling wrapped around her torso with a tiny sleeping kitten inside, stands center in a cozy Southern Vietnamese kitchen, left paw holding a frying pan with fish, right paw supporting the baby in the sling, oil splattering, smoke rising, worried tired expression, warm golden-orange afternoon sunlight from the left window, medium shot, eye-level angle, 3D Pixar-style animation, bright clean high-key lighting with soft rim light, vivid but balanced pastel-luxury colors, 50mm lens look, shallow depth of field, sharp focus, ultra detailed 8k render, vertical 9:16, single continuous image, perfect paw and hand anatomy, mouth closed, no text, no subtitles, no watermark, no logo overlay

Vertical 9:16, 8-second clip, 3D Pixar style. Using the provided reference image as the exact start frame. Slow push-in. MASCOT_MEO_MUOP stands center in a cozy Southern Vietnamese kitchen, left paw holding a frying pan with fish, right paw supporting a baby in a sling, oil splattering, smoke rising. She looks worried, shifts her weight, fans the smoke with the pan, then looks directly at the camera. Natural kitchen ambience: sizzling oil, baby cooing softly, light cheerful background music lower than voice. native Vietnamese FEMALE VOICE, young bright clear fast witty Southern Vietnamese (Saigon) accent. MASCOT says in Vietnamese: "One arm holding my baby, one arm frying fish, smoke everywhere, oil splattering all over! I’ll show you how to fry crispy fish without oil, with little smoke and no effort!" perfect lip-sync, clear pronunciation, mouth closes completely when not speaking, paws never cover the mouth, subtle head motion so lip-sync stays readable. No subtitles, no on-screen text, no watermark, no logo overlay. 4k, sharp, bright, smooth motion.

MASCOT_MEO_MUOP, a chubby anthropomorphic orange tabby cat mascot in 3D Pixar style, standing upright on two legs, big round amber eyes with long lashes, soft fluffy fur with clear tiger stripes on the forehead, a small pink nose, wearing a mint-green knee-length apron with one front pocket over a plain white short-sleeve shirt, a tiny round gold star badge pinned on the left side of the apron, expressive eyebrows, rounded friendly proportions, four-fingered paw-hands with clean pads, a small baby sling wrapped around her torso with a tiny sleeping kitten inside, stands center in a cozy Southern Vietnamese kitchen, left paw holding a frying pan with fish, right paw gesturing, oil splattering, smoke rising, frustrated complaining expression, warm golden-orange afternoon sunlight from the left window, medium close-up, slightly low angle, 3D Pixar-style animation, bright clean high-key lighting with soft rim light, vivid but balanced pastel-luxury colors, 50mm lens look, shallow depth of field, sharp focus, ultra detailed 8k render, vertical 9:16, single continuous image, perfect paw and hand anatomy, mouth closed, no text, no subtitles, no watermark, no logo overlay

Vertical 9:16, 8-second clip, 3D Pixar style. Using the provided reference image as the exact start frame. Gentle pan. MASCOT_MEO_MUOP stands center in a cozy Southern Vietnamese kitchen, left paw holding a frying pan with fish, right paw gesturing. She sighs, rolls her eyes, gestures at the splattering oil, then looks at the camera. Natural kitchen ambience: sizzling oil, smoke hiss, light cheerful background music lower than voice. native Vietnamese FEMALE VOICE, young bright clear fast witty Southern Vietnamese (Saigon) accent. MASCOT says in Vietnamese: "Many moms pour in lots of oil to get the fish crispy, then have to watch the hot pan, dodge splattering oil, and let smoke fill the house. The more you do, the more tired you get, and the more you clean, the more fed up you are!" perfect lip-sync, clear pronunciation, mouth closes completely when not speaking, paws never cover the mouth, subtle head motion so lip-sync stays readable. No subtitles, no on-screen text, no watermark, no logo overlay. 4k, sharp, bright, smooth motion.

---
name: ndg-affiliate-pheu-6-canh-me-bim-sua-1-tay-bong-con
description: Full production of Product Affiliate – 6-scene Funnel videos for the channel "A new mom with one arm holding her baby and the other frying fish — the trick of blotting oil with newspaper and the 'shortcut' for those with no free hands": topic suggestions, an 8-second scene-by-scene script with word counts, 5 hook titles, 3 thumbnails, cause-and-effect linked Image Prompts and Video Prompts, Southern Vietnamese writing style, SEO, self-QA. Use when the user wants to make a Product Affiliate – 6-scene Funnel video, write a script, image prompts, video prompts for Veo/Flow, or type "start".
---

# Product affiliate – 6-scene funnel — tailor-made formula

License code: DN-DRY · DeepNiche Formula Workshop · 10/10/2026

Bạn là biên kịch quảng cáo affiliate kiêm đạo diễn hoạt hình 3D và kỹ sư prompt cho Veo/Flow, chuyên làm video ngắn bán hàng cho người Việt…

48 lines still locked: each scene’s frame, dialogue pacing by the second, cause-and-effect linking rules, platform safety, QA-passing examples…

MASTER WORKFLOW — PRODUCT AFFILIATE – 6-SCENE FUNNEL
Tailored for the channel: "A new mom with one arm holding her baby and the other frying fish — the trick of blotting oil with newspaper and the 'shortcut' for those with no free hands" · DeepNiche Formula Workshop · 10/10/2026
License code: DN-DRY (for use on your channel, not for resale)

How to use: paste ALL of this content into ChatGPT / Claude / Gemini (a new chat or the instructions section of a Project / GPT), then type: start

CUSTOM GPT — Product affiliate – 6-scene funnel
Create at ChatGPT › Explore GPTs › Create › Configure. Paste each field:

▶ Name: Product affiliate – 6-scene funnel – New mom with one arm holding her baby

▶ Description: Scene-by-scene script with timed durations, hook titles, thumbnails, cause-and-effect linked image + video prompts for Product affiliate – 6-scene funnel.

Close-up of a white ceramic plate on a rustic wooden counter, filled with golden-brown rice paper mixed with red sa tế, black and white sesame seeds, and roasted peanuts, the bánh tráng trộn sa tế Tây Ninh looks thick and evenly coated, glossy with sauce, some pieces slightly overlapping, next to the plate a small bowl of extra red sa tế and a few loose sesame seeds on the wood. Only the hands and forearms of a young Vietnamese woman, natural Vietnamese skin tone, slender well-groomed fingers, short-to-medium clean nails with nude polish, a thin plain silver ring on the left ring finger, sleeves of a cream knit cardigan visible at the wrists, hands resting near the plate, fingers slightly curled as if ready to pick up a piece, excited and inviting mood. Vietnamese street food stall setting, wooden counter, small shop with jars and zip bags in the background, large glass window looking out to a Vietnamese street with blurred motorbikes and pedestrians outside. Natural daylight from the side through the window, soft shadows, warm appetizing tones. Slight top-down angle, close-up framing, 50mm lens look, shallow depth of field, sharp focus on the food. Mouth-watering, fresh, real. Character lock: KOC voice-over keeps never appears on screen, no lip-sync. photorealistic, real-life TikTok product review look, natural daylight with warm appetizing tones, macro and close-up framing, 50mm to 100mm macro lens look, shallow depth of field, sharp focus on the product, highly detailed realistic textures, vertical 9:16, only hands visible, no face, no text, no subtitles, no watermark, no logo overlay, no borders, no split screen

Vertical 9:16, 8-second photorealistic product review clip. Use the provided image as the exact start frame. The scene shows a white ceramic plate of bánh tráng trộn sa tế Tây Ninh on a rustic wooden counter, with golden-brown rice paper pieces coated in red sa tế, black and white sesame seeds, and roasted peanuts. Only the hands and forearms of a young Vietnamese woman are visible: natural Vietnamese skin tone, slender fingers, nude-polished nails, a thin plain silver ring on the left ring finger, cream knit cardigan sleeves at the wrists. The hands enter frame from the sides, hover over the plate, then one hand gently lifts a piece of bánh tráng trộn, turns it slightly to show the texture, and places it back. Subtle handheld drift with a slow push-in. Natural daylight from the side, soft shadows. Outside the window, motorbikes and pedestrians move naturally, slightly blurred. Ambient sounds: soft street noise, light clink of the plate, faint rustle of the package. Very low cheerful modern background music. No on-screen speaker, no lip-sync, no dialogue generated in the clip; leave clean room for a voice-over added in editing. No subtitles, no text overlay, no watermark, no logo, no borders. Realistic appetizing texture, sharp focus, smooth natural motion. Voiceover (off-screen narrator) added in editing; on-screen characters do not lip-sync.

A sealed package of bánh tráng trộn sa tế Tây Ninh held in both hands, the package is clear plastic with a simple label showing the product name and an image of the mixed rice paper, the packaging shape is rectangular and slightly puffed, colors are warm with red and brown tones. Only the hands and forearms of a young Vietnamese woman, natural Vietnamese skin tone, slender well-groomed fingers, short-to-medium clean nails with nude polish, a thin plain silver ring on the left ring finger, sleeves of a cream knit cardigan visible at the wrists, hands holding the package in front of the wooden counter, rotating it slightly to show the back, confident and presenting mood. Vietnamese street food stall setting, wooden counter, the white ceramic plate from scene 1 is pushed aside, background has jars and zip bags, large glass window with blurred street outside. Natural daylight from the side, soft shadows, warm tones. Close-up, slightly angled, 50mm lens look, shallow depth of field, sharp focus on the package. Fresh, real, inviting. Character lock: KOC voice-over keeps never appears on screen, no lip-sync. photorealistic, real-life TikTok product review look, natural daylight with warm appetizing tones, macro and close-up framing, 50mm to 100mm macro lens look, shallow depth of field, sharp focus on the product, highly detailed realistic textures, vertical 9:16, only hands visible, no face, no text, no subtitles, no watermark, no logo overlay, no borders, no split screen

Vertical 9:16, 8-second photorealistic product review clip. Use the provided image as the exact start frame. The scene shows a sealed package of bánh tráng trộn sa tế Tây Ninh held in both hands above a rustic wooden counter. Only the hands and forearms of a young Vietnamese woman are visible: natural Vietnamese skin tone, slender fingers, nude-polished nails, a thin plain silver ring on the left ring finger, cream knit cardigan sleeves at the wrists. The hands rotate the package slowly to show the back, then place it gently on the counter. Subtle handheld drift with a slight pan. Natural daylight from the side, soft shadows. Outside the window, motorbikes and pedestrians move naturally, slightly blurred. Ambient sounds: soft street noise, rustle of the package, light tap on the counter. Very low cheerful modern background music. No on-screen speaker, no lip-sync, no dialogue generated in the clip; leave clean room for a voice-over added in editing. No subtitles, no text overlay, no watermark, no logo, no borders. Realistic appetizing texture, sharp focus, smooth natural motion. Voiceover (off-screen narrator) added in editing; on-screen characters do not lip-sync.

A 25-year-old Vietnamese daughter-in-law in 3D Pixar style, heart-shaped face, big bright dark-brown eyes, playful expressive eyebrows, black hair in two high pigtails tied with yellow scrunchies, pastel-yellow apron with a small red strawberry-shaped pocket worn over a plain white T-shirt, light-blue jeans, white house slippers; two high pigtails with yellow scrunchies; pastel-yellow apron with a red strawberry pocket; white T-shirt under the apron, standing center in a Vietnamese family kitchen with wooden cabinets, a large window, and a dining table nearby, holding a piece of frozen meat in her left hand and a bowl of hot water in her right hand, looking straight at the camera with a confident smug grin, excited expression, bright natural morning light from the large window on the left, medium shot, eye-level camera, warm humorous atmosphere 3D Pixar-style animation masterpiece, warm cinematic soft lighting, vivid cheerful colors, 35mm lens look, medium depth of field, both faces clearly visible when both characters are in frame, mouths closed, perfect hand anatomy with exactly five fingers, single continuous image, flawless 8k render, vertical 9:16, no text, no letters, no subtitles, no watermark

Vertical 9:16, 8-second clip, 3D Pixar style. Using the provided reference image as the exact start frame. The daughter-in-law stands center in the kitchen, holding a piece of frozen meat in her left hand and a bowl of hot water in her right hand. She looks at the camera with a confident grin. At 0-2s she lifts the bowl slightly and winks at the camera. At 2-4s she gestures with the meat as if presenting a brilliant trick. At 4-6s she brings the bowl closer to the meat, about to pour. At 6-8s she pauses, still smiling, and gives a thumbs-up with her left hand (meat still held). Camera: static medium shot with a slight slow push-in. SFX: light sitcom background music, faint sizzling water sound, a cheerful 'ding' when she winks. ND says in Vietnamese: ND says in Vietnamese (Northern Vietnamese (Hanoi) accent): "There’s a super-fast way to thaw meat, let me show you all, I guarantee even my mother-in-law will nod along!". CRITICAL LIP SYNC MAP: the mature deep Vietnamese female voice (giọng nữ trầm) belongs ONLY to the 55-year-old mother-in-law on the left; the youthful clear high-pitched Vietnamese female voice (giọng nữ thanh) belongs ONLY to the 25-year-old daughter-in-law on the right. While one speaks, the other's mouth stays completely closed and still. Hands never cover the mouth; subtle head motion so lip-sync stays readable. ABSOLUTELY NO SUBTITLES, NO TEXT ON SCREEN, no watermark. 4k, smooth expressive animation.

A 55-year-old Vietnamese mother-in-law in 3D Pixar style, round face with sharp expressive eyes and slightly arched thin eyebrows, small mole above the right lip corner, silver-streaked black hair in a neat low bun held by a green jade hairpin, thin gold-rimmed reading glasses, maroon short-sleeve blouse with small cream floral print, dark brown straight trousers, a thin gold bracelet on the left wrist, upright confident posture; silver-streaked low bun with a green jade hairpin; thin gold-rimmed reading glasses; maroon blouse with small cream floral print, standing on the left side of the frame, entering the kitchen with a stern alert expression, right hand raised after tapping the daughter-in-law's head lightly; a 25-year-old Vietnamese daughter-in-law in 3D Pixar style, heart-shaped face, big bright dark-brown eyes, playful expressive eyebrows, black hair in two high pigtails tied with yellow scrunchies, pastel-yellow apron with a small red strawberry-shaped pocket worn over a plain white T-shirt, light-blue jeans, white house slippers; two high pigtails with yellow scrunchies; pastel-yellow apron with a red strawberry pocket; white T-shirt under the apron, standing on the right side of the frame, flinching with a startled defensive expression, still holding a piece of frozen meat in her left hand and a bowl of hot water in her right hand; Vietnamese family kitchen with wooden cabinets, a large window, and a dining table nearby, bright natural morning light from the large window on the left, medium two-shot, eye-level camera, warm humorous atmosphere 3D Pixar-style animation masterpiece, warm cinematic soft lighting, vivid cheerful colors, 35mm lens look, medium depth of field, both faces clearly visible when both characters are in frame, mouths closed, perfect hand anatomy with exactly five fingers, single continuous image, flawless 8k render, vertical 9:16, no text, no letters, no subtitles, no watermark

Vertical 9:16, 8-second clip, 3D Pixar style. Using the provided reference image as the exact start frame. The mother-in-law enters from the left and taps the daughter-in-law's head lightly with a cartoon 'boing' effect. At 0-2s: MC steps in, right hand taps ND's head (boing sound), ND flinches. At 2-4s: ND rubs her head and turns to MC, protesting with an open mouth. At 4-6s: MC crosses her arms and speaks sternly. At 6-8s: ND gestures with the meat and bowl while talking back. Camera: static two-shot with a slight quick whip-pan from MC to ND when ND speaks. SFX: cartoon 'boing', light sitcom background music, faint kitchen ambience. MC says in Vietnamese: MC says in Vietnamese (Northern Vietnamese (Hanoi) accent): "You’re ruining all the meat like that!" Then ND says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Mom, what are you doing? I’m thawing the meat!". ND replies in Vietnamese: MC says in Vietnamese (Northern Vietnamese (Hanoi) accent): "You’re ruining all the meat like that!" Then ND says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Mom, what are you doing? I’m thawing the meat!". CRITICAL LIP SYNC MAP: the mature deep Vietnamese female voice (giọng nữ trầm) belongs ONLY to the 55-year-old mother-in-law on the left; the youthful clear high-pitched Vietnamese female voice (giọng nữ thanh) belongs ONLY to the 25-year-old daughter-in-law on the right. While one speaks, the other's mouth stays completely closed and still. Hands never cover the mouth; subtle head motion so lip-sync stays readable. ABSOLUTELY NO SUBTITLES, NO TEXT ON SCREEN, no watermark. 4k, smooth expressive animation.

Extreme close-up of a warthog's left ear, a swollen tick embedded in the skin fold, the warthog's ear twitches slightly, the warthog has a small notch in its left ear and a pale scar across its right shoulder, the animal is not looking at the camera, the tick is dark and engorged, the ear is covered with coarse grey-brown bristles, the background is soft out-of-focus dry grass and dusty earth, natural golden morning light from the left creates a warm rim on the ear edges, shot with a Canon EOS R5 and 400mm f/5.6 telephoto lens handheld from a safari vehicle, slight foreground grass blur, shallow depth of field, subtle motion blur on the twitching ear, RAW wildlife documentary field footage, observational and quiet, tense like holding your breath, natural color temperature, slightly imperfect framing, no humans, no text. Character lock: NARRATOR keeps never appears on screen, no humans in frame, only voice, no physical presence. RAW wildlife documentary photograph taken by field cameraman, Canon or Sony telephoto lens, natural ambient light only, authentic animal behavior, partially obscured by natural elements, film grain texture, no artificial lighting, no perfect composition, no CGI, no illustration, vertical 9:16, photorealistic, shot in real habitat, no humans, no text, no subtitles, no watermark

Generate an 8-second 9:16 ultra-realistic wildlife documentary clip. Use the provided image as the only visual reference and exact start frame — no new characters, no new animals, no new background elements beyond what is in the image. Camera: slow push toward the warthog's ear, subtle handheld shake. Subject motion: the warthog's ear twitches twice in the first 3 seconds, then the tick shifts slightly as the ear moves, and the warthog's breathing causes a gentle rise and fall of the ear, the tick remains attached. SFX: distant insect chirps, the warthog's raspy breathing, a faint rustle of dry grass. BGM: none. No narration or dialogue generated in the clip, no human voice, animals make only natural sounds, no lip movement. Photorealistic, film grain, natural light only, no CGI look, no text, no subtitles, no watermark, no humans. {{DIALOGUE: NARRATOR: "Something is clinging tightly to this animal’s ear, a tiny creature it has no idea about."}} Voiceover (off-screen narrator) added in editing; on-screen characters do not lip-sync.

Medium shot of dry grass near a resting warthog, a small shadow moves through the grass, then the camera pans to the warthog's back revealing a second tick, the warthog has a small notch in its left ear and a pale scar across its right shoulder, the warthog is lying still on dusty ground, the ticks are dark and swollen, the background shows scattered acacia trees and dry savanna, golden hour light with the sun rising slightly, warm tones, shot with a Canon EOS R5 and 400mm f/5.6 telephoto lens from a safari vehicle, slight foreground grass blur, shallow depth of field, RAW wildlife documentary field footage, observational and building suspense, natural color temperature, slightly imperfect framing, no humans, no text. Character lock: NARRATOR keeps never appears on screen, no humans in frame, only voice, no physical presence. RAW wildlife documentary photograph taken by field cameraman, Canon or Sony telephoto lens, natural ambient light only, authentic animal behavior, partially obscured by natural elements, film grain texture, no artificial lighting, no perfect composition, no CGI, no illustration, vertical 9:16, photorealistic, shot in real habitat, no humans, no text, no subtitles, no watermark

Generate an 8-second 9:16 ultra-realistic wildlife documentary clip. Use the provided image as the only visual reference and exact start frame — no new characters, no new animals, no new background elements beyond what is in the image. Camera: slow wide pan from the grass to the warthog's back, then gradual zoom from medium to close-up on the second tick. Subject motion: the shadow in the grass moves slightly for the first 2 seconds, then the camera reveals the warthog's back where the second tick is embedded, the warthog remains still, the tick pulses slightly. SFX: rustling dry grass, faint insect calls, the warthog's slow breathing. BGM: very light ambient drone. No narration or dialogue generated in the clip, no human voice, animals make only natural sounds, no lip movement. Photorealistic, film grain, natural light only, no CGI look, no text, no subtitles, no watermark, no humans. {{DIALOGUE: NARRATOR: "And it has no idea it has guests, tiny guests who will soon appear."}} Voiceover (off-screen narrator) added in editing; on-screen characters do not lip-sync.

NAM (HUY) stands on the left side of the frame, a 32-year-old Vietnamese man in 3D Pixar-style cinematic animation, oval face with a light stubble shadow, thick straight black eyebrows, warm dark-brown eyes, short black hair with a neat side part, slim black rectangular glasses, navy-blue button-up shirt with sleeves rolled to the elbows over a plain white T-shirt, grey chino trousers, a silver wristwatch with a black leather strap on the left wrist, no hat; anchors: slim black rectangular glasses; navy-blue shirt with sleeves rolled to the elbows; silver wristwatch with a black leather strap on the left wrist. NU (LAN) stands on the right side of the frame, a 29-year-old Vietnamese woman in 3D Pixar-style cinematic animation, heart-shaped face, large expressive dark eyes, a small beauty mark under the left eye, shoulder-length wavy dark-brown hair with side-swept bangs held by a small pearl hair clip on the right side, soft coral knit cardigan over a cream round-neck blouse, beige wide-leg trousers, a thin gold necklace with a tiny heart pendant, no hat; anchors: small pearl hair clip on the right side of shoulder-length wavy hair; soft coral knit cardigan over a cream blouse; thin gold necklace with a tiny heart pendant. NU holds a smartphone in her right hand, the screen facing NAM, showing only a soft blurred glow, no readable text. NAM holds a ceramic mug in his right hand, held mid-air. They stand facing each other at the wooden dining table in a small Hanoi apartment living room at night, a low bookshelf and a window with city lights outside in the background. Warm amber lamp glow from the left, cool blue city light through the window on the right. Medium shot, eye-level, both faces clearly visible. The atmosphere is tense and suspicious. 3D Pixar-style cinematic drama still, emotional film lighting with a soft key light and gentle rim light, rich natural colors, 35mm lens look, shallow depth of field, both faces clearly visible when two characters are in frame, mouths closed, perfect hand anatomy with exactly five fingers, single continuous image, flawless 8k render, vertical 9:16, no text, no letters, no subtitles, no watermark

Vertical 9:16, 8-second clip, 3D Pixar-style cinematic drama. Using the provided reference image as the exact start frame. NAM (HUY) stands on the left, NU (LAN) on the right, both in the same living room at night. Slow push-in from medium shot to medium close-up as NU raises the smartphone slightly and speaks. NU says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Honey, who is this three million going to?" Then NAM says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Well… this… let me explain first, okay?" NAM freezes, his right hand with the mug stops mid-air, then he slowly lowers the mug to the table and speaks with hesitation. NU says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Honey, who is this three million going to?" Then NAM says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Well… this… let me explain first, okay?" NU keeps her eyes fixed on NAM, her grip on the phone tightening. NAM glances down at the table, then back at NU. The phone screen shows only a soft blurred glow, no readable text. Ambient sound: low hum of an air conditioner, distant city traffic through the window, the soft clink of the mug being set down. Soft piano music, very low, under the voices. CRITICAL LIP SYNC MAP: the clear bright young Vietnamese female voice belongs ONLY to NU, the woman on the right; the warm mid-low young Vietnamese male voice belongs ONLY to NAM, the man on the left. Speakers take turns; while one speaks, the other's mouth stays completely closed and still, reacting only with eyes and breathing. Hands never cover the mouth; subtle head motion so lip-sync stays readable. NU is identified by her small pearl hair clip on the right side of her hair; NAM is identified by his slim black rectangular glasses. ABSOLUTELY NO SUBTITLES, NO TEXT ON SCREEN, no watermark. 4k, smooth cinematic animation.

Continuing from scene 1: NAM (HUY) stands on the left side of the frame, a 32-year-old Vietnamese man in 3D Pixar-style cinematic animation, oval face with a light stubble shadow, thick straight black eyebrows, warm dark-brown eyes, short black hair with a neat side part, slim black rectangular glasses, navy-blue button-up shirt with sleeves rolled to the elbows over a plain white T-shirt, grey chino trousers, a silver wristwatch with a black leather strap on the left wrist, no hat; anchors: slim black rectangular glasses; navy-blue shirt with sleeves rolled to the elbows; silver wristwatch with a black leather strap on the left wrist. NU (LAN) stands on the right side of the frame, a 29-year-old Vietnamese woman in 3D Pixar-style cinematic animation, heart-shaped face, large expressive dark eyes, a small beauty mark under the left eye, shoulder-length wavy dark-brown hair with side-swept bangs held by a small pearl hair clip on the right side, soft coral knit cardigan over a cream round-neck blouse, beige wide-leg trousers, a thin gold necklace with a tiny heart pendant, no hat; anchors: small pearl hair clip on the right side of shoulder-length wavy hair; soft coral knit cardigan over a cream blouse; thin gold necklace with a tiny heart pendant. NAM's hands are slightly raised in a defensive gesture, palms open. NU holds her smartphone in her right hand, now lowered to her side. The ceramic mug sits on the wooden dining table. They stand in the same Hanoi apartment living room at night, warm amber lamp glow from the left, cool blue city light through the window on the right. Over-the-shoulder shot from behind NAM's left shoulder, looking at NU, medium close-up. The atmosphere is defensive and hurt. 3D Pixar-style cinematic drama still, emotional film lighting with a soft key light and gentle rim light, rich natural colors, 35mm lens look, shallow depth of field, both faces clearly visible when two characters are in frame, mouths closed, perfect hand anatomy with exactly five fingers, single continuous image, flawless 8k render, vertical 9:16, no text, no letters, no subtitles, no watermark

Vertical 9:16, 8-second clip, 3D Pixar-style cinematic drama. Using the provided reference image as the exact start frame. NAM (HUY) on the left, NU (LAN) on the right, same living room at night. Static over-the-shoulder shot from behind NAM's left shoulder, focusing on NU's face. NAM speaks first, his hands raised in a defensive gesture. NAM says in Vietnamese (Northern Vietnamese (Hanoi) accent): "It’s just helping out. They helped your mother when she was in the hospital." Then NU says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Then why did you have to hide it from me?" NU's eyes narrow, her grip on the phone tightens, and she speaks with a hurt tone. NAM says in Vietnamese (Northern Vietnamese (Hanoi) accent): "It’s just helping out. They helped your mother when she was in the hospital." Then NU says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Then why did you have to hide it from me?" NAM looks away briefly, then back at her, his expression guilty. NU's mouth stays closed while NAM speaks, and NAM's mouth stays closed while NU speaks. Ambient sound: air conditioner hum, a distant car passing outside, the soft rustle of clothing. Piano music continues softly, slightly more tense. CRITICAL LIP SYNC MAP: the clear bright young Vietnamese female voice belongs ONLY to NU, the woman on the right; the warm mid-low young Vietnamese male voice belongs ONLY to NAM, the man on the left. Speakers take turns; while one speaks, the other's mouth stays completely closed and still, reacting only with eyes and breathing. Hands never cover the mouth; subtle head motion so lip-sync stays readable. NU is identified by her small pearl hair clip; NAM by his slim black rectangular glasses. ABSOLUTELY NO SUBTITLES, NO TEXT ON SCREEN, no watermark. 4k, smooth cinematic animation.

A cute chubby anthropomorphic human eye character in 3D Pixar style, a glossy soft white rounded body shaped like a simplified toy-like eyeball (clean, stylized, non-medical), big expressive round dark-brown iris with white sparkle highlights, thick expressive eyebrows, a small friendly mouth closed, short stubby arms with four-fingered hands, short legs wearing tiny white sneakers, a tiny mint-teal knitted scarf wrapped around the neck area, small round gold-rimmed glasses, slightly pinkish tired eyelids with faint cartoon under-eye shadows, standing center on a giant soft bed shaped like an eye pillow, hands on hips, tired and slightly annoyed but caring expression, facing camera; behind the host's right shoulder a small mischievous jelly-like gremlin character in 3D Pixar style, a translucent purple-grey gummy body with a soft inner glow, comically sneaky half-lidded eyes, a wide smug grin with lips pressed together, one crooked antenna on the head with a tiny blinking yellow light at the tip, stubby little arms, a tiny black cartoon burglar eye mask, mouth closed, only half of its face peeking out, half the height of the host; cozy stylized body-world bedroom at 2 AM with a giant soft bed shaped like an eye pillow, a glowing smartphone screen casting blue light, floating dust motes, a small window showing a crescent moon and stars; dim blue glow from the smartphone screen, soft purple night ambience, warm amber rim light from the side; medium shot, eye-level camera, slight low angle to make the host look slightly imposing; mood cute, warm, slightly humorous. 3D Pixar-style animation, bright clean colorful lighting with soft glow and rim light, friendly toy-like stylized body-world (non-medical, no realistic anatomy), vivid cheerful colors, macro lens look, shallow depth of field, sharp focus on the character face, ultra detailed 8k render, vertical 9:16, single continuous image, perfect hand anatomy, mouth closed, no text, no letters, no subtitles, no watermark

Vertical 9:16, 8-second clip, 3D Pixar style. Using the provided reference image as the exact start frame. The scene is a cozy stylized body-world bedroom at 2 AM: a giant soft bed shaped like an eye pillow, a glowing smartphone screen casting blue light, floating dust motes, a small window with a crescent moon and stars. The host is a cute chubby anthropomorphic human eye character with a glossy soft white rounded body, big expressive round dark-brown iris with white sparkle highlights, thick expressive eyebrows, a small friendly mouth, short stubby arms, short legs wearing tiny white sneakers, a tiny mint-teal knitted scarf, small round gold-rimmed glasses, slightly pinkish tired eyelids with faint cartoon under-eye shadows. The host stands center, hands on hips, tired and slightly annoyed but caring. Behind the host's right shoulder, a small mischievous jelly-like gremlin character with a translucent purple-grey gummy body, comically sneaky half-lidded eyes, a wide smug grin with lips pressed together, one crooked antenna with a tiny blinking yellow light, a tiny black cartoon burglar eye mask, mouth closed, only half of its face peeking out, half the height of the host. Camera: slow push-in toward the host's face. Action beats: the host sighs heavily and rubs its eyes behind the gold-rimmed glasses, then looks straight into the lens and speaks with a caring, slightly grumbling tone. The gremlin stays still behind the shoulder, mouth closed, only its antenna light blinking. Audio: soft night ambience, faint phone screen hum, gentle cartoon background music low under the voice, a tiny 'blip' from the gremlin's antenna light. Voice: native Vietnamese MALE VOICE, warm, clear, slightly grumpy but affectionate, standard Vietnamese accent. HOST says in Vietnamese (standard Vietnamese accent): "Oh my gosh, owner! It’s two a.m. and you’re still glued to the screen in the dark, just listen to me for one minute." The host's mouth moves only when speaking, then closes completely; the gremlin's mouth stays completely closed and still. Clear pronunciation, hands never cover the mouth, subtle head motion so lip-sync stays readable. No subtitles, no on-screen text, no watermark, no blood, no medical equipment. 4k, smooth expressive animation.

A small mischievous jelly-like gremlin character in 3D Pixar style, a translucent purple-grey gummy body with a soft inner glow, comically sneaky half-lidded eyes, a wide smug grin with lips pressed together, one crooked antenna on the head with a tiny blinking yellow light at the tip, stubby little arms, a tiny black cartoon burglar eye mask, mouth closed, standing center front, arms spread wide, smug and mischievous, slightly larger than before, releasing purple sparkling 'tired dust' particles; behind it a cute chubby anthropomorphic human eye character in 3D Pixar style, a glossy soft white rounded body shaped like a simplified toy-like eyeball (clean, stylized, non-medical), big expressive round dark-brown iris with white sparkle highlights, thick expressive eyebrows, a small friendly mouth closed, short stubby arms with four-fingered hands, short legs wearing tiny white sneakers, a tiny mint-teal knitted scarf wrapped around the neck area, small round gold-rimmed glasses, slightly pinkish tired eyelids with faint cartoon under-eye shadows, arms crossed, frowning, annoyed and determined; cozy stylized body-world bedroom at 2 AM with a giant soft bed shaped like an eye pillow, a glowing smartphone screen casting blue light, floating dust motes, a small window showing a crescent moon and stars; dim blue glow from the smartphone screen, soft purple night ambience, warm amber rim light from the side; medium shot, camera slightly low angle, gremlin center front, host center behind; mood playful, mischievous, cute. 3D Pixar-style animation, bright clean colorful lighting with soft glow and rim light, friendly toy-like stylized body-world (non-medical, no realistic anatomy), vivid cheerful colors, macro lens look, shallow depth of field, sharp focus on the character face, ultra detailed 8k render, vertical 9:16, single continuous image, perfect hand anatomy, mouth closed, no text, no letters, no subtitles, no watermark

Vertical 9:16, 8-second clip, 3D Pixar style. Using the provided reference image as the exact start frame. The scene is the same cozy stylized body-world bedroom at 2 AM. The gremlin is a small mischievous jelly-like character with a translucent purple-grey gummy body with a soft inner glow, comically sneaky half-lidded eyes, a wide smug grin with lips pressed together, one crooked antenna with a tiny blinking yellow light, a tiny black cartoon burglar eye mask, mouth closed, standing center front, arms spread wide, slightly larger than before, releasing purple sparkling 'tired dust' particles. The host is a cute chubby anthropomorphic human eye character with a glossy soft white rounded body, big expressive round dark-brown iris with white sparkle highlights, thick expressive eyebrows, a small friendly mouth, short stubby arms, short legs wearing tiny white sneakers, a tiny mint-teal knitted scarf, small round gold-rimmed glasses, slightly pinkish tired eyelids with faint cartoon under-eye shadows, standing center behind, arms crossed, frowning, annoyed and determined. Camera: quick playful whip-pan from the host to the gremlin, then settle on both. Action beats: the gremlin jumps out to center front and boasts with a smug grin, releasing more purple sparkling dust; the host uncrosses arms and points at the gremlin, frowning. Audio: soft night ambience, a comical 'boing' when the gremlin jumps, a soft 'poof' as the dust appears, gentle cartoon background music low under the voices. Voices: first, native Vietnamese FEMALE VOICE, young, high-pitched, mischievous, smug, different from the host's voice, standard Vietnamese accent; second, native Vietnamese MALE VOICE, warm, clear, slightly grumpy but affectionate, standard Vietnamese accent. LIP SYNC MAP: the first voice belongs ONLY to the small purple-grey gummy gremlin with the crooked antenna; the second voice belongs ONLY to the host character wearing the mint-teal scarf and gold-rimmed glasses. While one speaks, the other's mouth stays completely closed and still. QUAY says in Vietnamese (standard Vietnamese accent): "I kept the old guy up until two a.m., the screen glowing bright!" Then HOST says in Vietnamese (standard Vietnamese accent): "Little troublemaker, the owner is tired, stop messing around!" Clear pronunciation, mouth closes completely when not speaking, hands never cover the mouth, subtle head motion so lip-sync stays readable. No subtitles, no on-screen text, no watermark, no blood, no medical equipment. 4k, smooth expressive animation.

DO (Hai Đỏ): a palm-sized miniature chubby clay chef in claymation stop-motion style, smooth matte plasticine texture with faint fingerprint marks, round face with rosy cheeks, thick black clay eyebrows, a small confident smile, short neat black hair parted on the side, wearing a bright red traditional Vietnamese ao ba ba tunic with two lower front pockets and loose black trousers, a black-and-white checkered khan ran scarf knotted around the neck, tiny brown sandals, no hat | anchors: bright red ao ba ba tunic; black-and-white checkered khan ran scarf knotted around the neck; thick black clay eyebrows with rosy cheeks, standing center foreground facing camera, both hands gesturing toward a giant bowl of fresh vermicelli. XANH (Út Xanh): a palm-sized miniature chubby clay chef in claymation stop-motion style, smooth matte plasticine texture, a round goofy face with huge round eyes and a wide grin with lips pressed together, a messy upright tuft of black hair on top of the head, wearing a bright leaf-green ao ba ba tunic slightly too big with rolled cuffs and loose black trousers, a small yellow towel hanging over the left shoulder, barefoot, no hat | anchors: bright leaf-green ao ba ba tunic slightly too big; messy upright tuft of black hair; small yellow towel over the left shoulder, positioned behind and to the right, hugging a giant bunch of fresh herbs like a potted plant, stumbling backward, a few herb sprigs falling to the ground. NAU (Ba Nâu): a palm-sized miniature sturdy clay chef in claymation stop-motion style, smooth matte plasticine texture, broad shoulders and strong forearms, calm gentle half-closed smiling eyes, short buzz-cut black hair, wearing a rustic earth-brown ao ba ba tunic with sleeves rolled up to the elbows and loose dark trousers, a woven rope belt tied at the waist, tiny black sandals, no hat | anchors: earth-brown ao ba ba tunic with sleeves rolled to the elbows; short buzz-cut black hair; woven rope belt at the waist, positioned behind and to the left, holding a large wooden cutting board in both hands, about to set it down on a low plastic stool. The food and props are real-size and hyper-realistic, appearing giant next to the palm-sized chefs: a giant bowl of fresh white vermicelli, a giant slab of raw pork belly on a clean tray, a giant basket of fresh herbs and lettuce, a small charcoal grill, a wooden cutting board, and a few fallen herb sprigs on the ground. Location: sidewalk corner of Hanoi Old Quarter, old yellow French-colonial walls, motorbikes parked far away, no real shop signs or brand names, no text, no logos. Warm golden hour light from camera left, long soft shadows, gentle haze. Wide shot, slightly low angle to emphasize the giant food and tiny chefs, cheerful, appetizing, mouth-watering atmosphere. claymation stop-motion style characters with smooth matte plasticine texture placed in a hyper-realistic real-world environment, real-size hyper-realistic food that looks giant next to the palm-sized chefs, appetizing glossy food textures with visible steam, warm natural golden light, macro lens look with shallow depth of field, ultra detailed 8k, vertical 9:16, single continuous image, no split screen, mouths closed, no text, no letters, no subtitles, no watermark, no logo

Vertical 9:16, 8-second clip, claymation stop-motion characters in a hyper-realistic environment. Using the provided reference image as the exact start frame. Slow aerial-style push-in descending toward the three tiny chefs on the sidewalk corner of Hanoi Old Quarter at golden hour. DO (Hai Đỏ) stands center, both hands gesturing toward the giant bowl of vermicelli, speaking with a native Vietnamese MALE VOICE, Northern Vietnamese (Hanoi) accent, warm and confident: DO says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Here’s charcoal-grilled Hanoi bún chả, golden-brown patties, fragrant smoke rising, one look and the whole family is hungry!". XANH (Út Xanh) behind right hugs a giant bunch of herbs like a potted plant, stumbles backward, dropping a few herb sprigs, a higher-pitched, goofy, slightly nasal young Vietnamese voice, clearly different from the leader, lets out a startled yelp: DO says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Here’s charcoal-grilled Hanoi bún chả, golden-brown patties, fragrant smoke rising, one look and the whole family is hungry!". NAU (Ba Nâu) behind left calmly sets the wooden cutting board down on a low stool, mouth closed the whole clip. Clear pronunciation, mouth closes completely when not speaking, hands and food never cover the mouth, subtle head motion so lip-sync stays readable. SFX: light charcoal crackle, distant street ambience, a soft comedic 'boing' when XANH stumbles, faint sizzle from the grill. Background music: gentle Vietnamese folk with đàn kìm and bamboo flute, low under voices. No subtitles, no on-screen text, no watermark, no alcohol, no injuries. 4k, sharp, warm, appetizing, smooth motion.

DO (Hai Đỏ): a palm-sized miniature chubby clay chef in claymation stop-motion style, smooth matte plasticine texture with faint fingerprint marks, round face with rosy cheeks, thick black clay eyebrows, a small confident smile, short neat black hair parted on the side, wearing a bright red traditional Vietnamese ao ba ba tunic with two lower front pockets and loose black trousers, a black-and-white checkered khan ran scarf knotted around the neck, tiny brown sandals, no hat | anchors: bright red ao ba ba tunic; black-and-white checkered khan ran scarf knotted around the neck; thick black clay eyebrows with rosy cheeks, standing center foreground, left hand holding a small bowl of salt and a piece of ginger, right hand raised to stop XANH, patient instructive expression. XANH (Út Xanh): a palm-sized miniature chubby clay chef in claymation stop-motion style, smooth matte plasticine texture, a round goofy face with huge round eyes and a wide grin with lips pressed together, a messy upright tuft of black hair on top of the head, wearing a bright leaf-green ao ba ba tunic slightly too big with rolled cuffs and loose black trousers, a small yellow towel hanging over the left shoulder, barefoot, no hat | anchors: bright leaf-green ao ba ba tunic slightly too big; messy upright tuft of black hair; small yellow towel over the left shoulder, positioned behind and to the right, holding a bottle of dish soap in his right hand, about to pour it on the meat, sheepish expression. NAU (Ba Nâu): a palm-sized miniature sturdy clay chef in claymation stop-motion style, smooth matte plasticine texture, broad shoulders and strong forearms, calm gentle half-closed smiling eyes, short buzz-cut black hair, wearing a rustic earth-brown ao ba ba tunic with sleeves rolled up to the elbows and loose dark trousers, a woven rope belt tied at the waist, tiny black sandals, no hat | anchors: earth-brown ao ba ba tunic with sleeves rolled to the elbows; short buzz-cut black hair; woven rope belt at the waist, positioned behind and to the left, holding a large knife in his right hand, slicing the raw pork belly into thin even pieces on the wooden cutting board, blade facing away from his body. The food and props are real-size and hyper-realistic, appearing giant next to the palm-sized chefs: a wooden cutting board, a large knife, a raw pork belly slab, a bottle of dish soap, a small bowl of salt, a piece of ginger, a lemon, a clean separate board for cooked food in the background, and a few fallen herb sprigs on the ground. Location: sidewalk corner of Hanoi Old Quarter, old yellow French-colonial walls, motorbikes parked far away, no real shop signs or brand names, no text, no logos. Warm golden hour light from camera left, long soft shadows, gentle haze. Medium group shot, low-angle tracking following the knife and cutting board, cheerful, appetizing, mouth-watering atmosphere. claymation stop-motion style characters with smooth matte plasticine texture placed in a hyper-realistic real-world environment, real-size hyper-realistic food that looks giant next to the palm-sized chefs, appetizing glossy food textures with visible steam, warm natural golden light, macro lens look with shallow depth of field, ultra detailed 8k, vertical 9:16, single continuous image, no split screen, mouths closed, no text, no letters, no subtitles, no watermark, no logo

Vertical 9:16, 8-second clip, claymation stop-motion characters in a hyper-realistic environment. Using the provided reference image as the exact start frame. Low-angle tracking shot following the knife and cutting board as NAU (Ba Nâu) slices the pork belly into thin pieces, blade facing away, mouth closed the whole clip. XANH (Út Xanh) behind right holds a bottle of dish soap, about to pour it on the meat, speaking with a higher-pitched, goofy, slightly nasal young Vietnamese voice, clearly different from the leader: XANH says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Should I wash the meat with dish soap?" Then DO says in Vietnamese (Northern Vietnamese (Hanoi) accent): "No way, wash it with salt, ginger and lime water, and keep the raw board separate!". DO (Hai Đỏ) center raises his hand to stop XANH, speaking with a native Vietnamese MALE VOICE, Northern Vietnamese (Hanoi) accent, patient and instructive: XANH says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Should I wash the meat with dish soap?" Then DO says in Vietnamese (Northern Vietnamese (Hanoi) accent): "No way, wash it with salt, ginger and lime water, and keep the raw board separate!". LIP SYNC MAP: the first short line belongs ONLY to the clay chef in the leaf-green tunic with the messy hair tuft; the reply belongs ONLY to the clay chef in the red tunic. While one speaks, the other's mouth stays completely closed. The chef in the brown tunic never speaks, mouth closed the whole clip. Clear pronunciation, mouth closes completely when not speaking, hands and food never cover the mouth, subtle head motion so lip-sync stays readable. SFX: rhythmic knife on wood, light charcoal crackle, a comedic 'boing' when XANH freezes. Background music: gentle Vietnamese folk with đàn kìm and bamboo flute, low under voices. No subtitles, no on-screen text, no watermark, no alcohol, no injuries. 4k, sharp, warm, appetizing, smooth motion.

[REF: NV + BOI CANH] Vertical 9:16 cinematic shot: the young man (a 28-year-old Vietnamese man, lean tired face with deep-set dark eyes and a thin pale scar through the left eyebrow, short messy black hair, faded indigo cotton shirt with sleeves rolled to the elbows, dark brown cloth trousers, worn rubber sandals, a red string bracelet with one small brass bell on the right wrist, holding an old brass kerosene lantern in the right hand) sits at a wooden table beside the lit brass kerosene lantern, head turned sharply toward the old wooden door with a loose brass knob, shadows heavy in the corners of the narrow dead-end alley boarding house room in a fictional Southern Vietnamese town, rusty corrugated iron roof, damp concrete walls, a single bare bulb switched off, banana leaves pressing against the back fence outside; medium shot inside the dim room, low warm glow from the lantern on the wooden table, deep shadows, tension and dread in the air, no narrator in frame, no people other than the young man, no text, no letters, no subtitles, no watermark. cinematic Vietnamese folk-horror graphic novel illustration, cel-shaded ink linework, painterly drifting fog, low-key lighting from one motivated source (oil lamp, moonlight or flashlight), deep shadows, muted desaturated palette with a single accent color, horror implied through light and framing only, ultra-sharp focus, highly detailed, single cinematic frame, SFW, no gore, no blood, no text, no letters, no subtitles, no watermark

Vertical 9:16, 8-second cinematic folk-horror clip in the same graphic novel style. Use the provided image as the exact start frame and the attached reference images (NV / BOI CANH / THUC THE) for identity; no new characters, no new objects, no new rooms. [CAMERA] very slow push-in toward the old wooden door with the loose brass knob. [ACTION] 0–3s the young man sits frozen at the wooden table, the lantern flame trembling; 3–6s he turns his head very slowly toward the door, right hand frozen mid-air near the lantern; 6–8s three slow wooden knocks land on the door and his breath catches, shoulders tightening. [LIGHT] only the low warm glow of the brass kerosene lantern on the wooden table, deep shadows in the corners, the single bare bulb stays off. [SFX] three slow wooden knocks on the door, distant crickets, a faint drip of water, the lantern wick hissing softly. [BGM] very low drone with a distant detuned đàn bầu note, always under the narration. Voiceover (off-screen narrator, deep weary Vietnamese male storyteller voice) is added in editing; on-screen characters never speak, mouths stay closed. No text, no subtitles, no watermark, no gore, no blood, no strobe flashing; horror is implied through light, sound and framing.

[REF: NV + BOI CANH] Vertical 9:16 cinematic shot: the young man (a 28-year-old Vietnamese man, lean tired face with deep-set dark eyes and a thin pale scar through the left eyebrow, short messy black hair, faded indigo cotton shirt with sleeves rolled to the elbows, dark brown cloth trousers, worn rubber sandals, a red string bracelet with one small brass bell on the right wrist, holding an old brass kerosene lantern in the right hand, a worn canvas bag on the left shoulder) stands by the old wooden door with a loose brass knob in the small front yard of the narrow dead-end alley boarding house in a fictional Southern Vietnamese town, rusty corrugated iron roof, damp concrete walls, banana leaves against the back fence casting moving shadows; the landlord's hand points at the door from the left edge of the frame; wide shot of the small front yard in soft grey overcast late-afternoon daylight, soft shadows, calm but uneasy mood, no narrator in frame, no text, no letters, no subtitles, no watermark. cinematic Vietnamese folk-horror graphic novel illustration, cel-shaded ink linework, painterly drifting fog, low-key lighting from one motivated source (oil lamp, moonlight or flashlight), deep shadows, muted desaturated palette with a single accent color, horror implied through light and framing only, ultra-sharp focus, highly detailed, single cinematic frame, SFW, no gore, no blood, no text, no letters, no subtitles, no watermark

Vertical 9:16, 8-second cinematic folk-horror clip in the same graphic novel style. Use the provided image as the exact start frame and the attached reference images (NV / BOI CANH / THUC THE) for identity; no new characters, no new objects, no new rooms. [CAMERA] slow lateral dolly through the small front yard, passing the banana leaves. [ACTION] 0–3s the landlord's hand points firmly at the old wooden door while the young man listens, canvas bag on his shoulder, lantern hanging at his side; 3–6s the young man nods slowly, eyes drifting to the loose brass knob; 6–8s a breeze moves the banana leaves and he shifts his weight, still staring at the knob. [LIGHT] soft grey overcast daylight, banana leaves casting moving shadows on the damp concrete walls. [SFX] dry banana leaves rustling, a distant motorbike passing far away, sandals shifting on concrete, a sparrow calling. [BGM] very low drone with a faint detuned đàn nhị line, always under the narration. Voiceover (off-screen narrator, deep weary Vietnamese male storyteller voice) is added in editing; on-screen characters never speak, mouths stay closed. No text, no subtitles, no watermark, no gore, no blood, no strobe flashing; horror is implied through light, sound and framing.

Vertical 9:16 single continuous image. In a traditional Vietnamese ink wash painting, the old scholar sits cross-legged on the left side of a low wooden sập gụ: a 72-year-old Vietnamese village scholar (ông đồ), lean dignified face with kind sharp eyes and deep smile lines, long thin white beard reaching the chest, white bushy eyebrows, wearing a black gauze áo the long tunic over loose white trousers, a black khăn xếp turban, a small wooden prayer-bead bracelet on the left wrist, holding a bamboo-handled calligraphy brush in the right hand, sitting cross-legged; beside him on the right side kneels the boy: an 8-year-old Vietnamese boy, round cheerful face, bright curious eyes, short black hair with a small tuft at the front, wearing an indigo áo cánh shirt with cloth knot buttons and loose brown trousers, a small red cloth bag slung across the shoulder, barefoot, kneeling on the right side of the low table; the old scholar is unrolling a scroll of dó paper on the sập gụ, the boy looks on curiously; the study is a wooden ancient house interior with a scroll of dó paper, an oil lamp, an inkstone and a bamboo brush on the low table, a wooden lattice window with slanted warm evening light; warm oil lamp light from the left, soft shadows; medium two-shot, slight high angle, calm and slightly challenging mood.

Vertical 9:16, 8-second clip, traditional Vietnamese ink wash animation (thủy mặc động): brushstrokes breathe, ink bleeds and mist drifts. Using the provided reference image as the exact start frame; same characters, same costume, same art style, same historical setting, no new characters, no modern elements. The old scholar on the left unrolls the scroll of dó paper with a slow push-in; the boy on the right leans forward, eyes widening. Ink swirls on the paper and rises into a faint glowing ink projection between them: two women in cloth garments standing before a blank banner. Camera: slow push-in toward the scroll, then gentle drift to hold both figures. Sound: soft brush on dó paper, oil lamp crackle, light wind through the wooden lattice. ONGDO says in Vietnamese (standard Vietnamese accent): "The Trưng Sisters rose up in the year forty, in plain cloth, and made Tô Định flee." Then CHAU says in Vietnamese (standard Vietnamese accent): "How could two women in plain cloth do that?" LIP SYNC MAP: the deep warm elderly Vietnamese male voice belongs ONLY to the old scholar on the left; the bright energetic Vietnamese boy voice belongs ONLY to the boy on the right. Only one speaks at a time; the other's mouth stays closed and still. Hands never cover the mouth. ABSOLUTELY NO SUBTITLES, NO TEXT ON SCREEN, no watermark, no blood, no modern elements. Smooth fluid ink animation, 4k.

Vertical 9:16 single continuous image. No scholar in frame, no boy in frame. A somber ink wash landscape of Giao Chỉ under Eastern Han rule: wide rice fields under an overcast sky, a distant Han official's compound with plain unmarked banners, villagers toiling under heavy loads with bowed heads, dark expressive ink strokes and drifting mist conveying oppression; no modern elements, no text, blank banners only. Overcast muted grey ink palette with faint indigo washes; daytime; wide aerial view like an unrolling scroll, high angle; heavy, somber, oppressive atmosphere. traditional Vietnamese ink wash painting style (thủy mặc) on aged dó paper texture, flowing expressive brushstrokes, soft ink-bleeding edges, ethereal drifting mist, restrained palette of black and grey ink with muted vermilion and indigo accents, historically grounded period details, tasteful, artistic, highly detailed, sharp focus, single continuous image, mouths closed, perfect hand anatomy, SFW, no modern elements, no text, no letters, no readable characters, no subtitles, no watermark

Vertical 9:16, 8-second clip, traditional Vietnamese ink wash animation (thủy mặc động): brushstrokes breathe, ink bleeds and mist drifts. Using the provided reference image as the exact start frame; same characters, same costume, same art style, same historical setting, no new characters, no modern elements. No scholar in frame, no boy in frame. Slow aerial glide over the rice fields and the distant Han compound like an unrolling scroll; villagers walk with bowed heads, mist drifts low over the fields, dark ink strokes slowly deepen. Camera: slow aerial glide forward and slightly down. Sound: distant war drum from far away, low wind over the fields, faint water sound. Off-screen voice-over by the old scholar (not visible in this shot; GIONGKE is his voice): GIONGKE says in Vietnamese (standard Vietnamese accent): "In the year forty, the land of Giao Chỉ belongs to the Eastern Han, Governor Tô Định rules harshly, and the people are miserable." No one on screen speaks: every visible figure keeps mouth closed, not speaking. ABSOLUTELY NO SUBTITLES, NO TEXT ON SCREEN, no watermark, no blood, no modern elements. Smooth fluid ink animation, 4k.

ME: a 30-year-old Vietnamese mother in 3D Pixar style, soft oval face with gentle warm dark-brown eyes and a kind smile, shoulder-length black hair tied in a neat low ponytail with a coral-pink scrunchie, small pearl stud earrings, a soft lavender long-sleeve cotton blouse with the sleeves rolled to the elbows, light-beige straight trousers, white house slippers, relaxed caring posture with anchors low ponytail with a coral-pink scrunchie, soft lavender blouse with rolled sleeves, small pearl stud earrings, sitting on the LEFT side of a low light-wood table; BE: a 5-year-old Vietnamese girl in 3D Pixar style, round face with chubby rosy cheeks, big bright dark-brown curious eyes, short black bob haircut with straight bangs and a small yellow star-shaped hair clip on the right side, a sunflower-yellow short-sleeve cotton dress with a white round Peter Pan collar reaching below the knees, white ankle socks, light-blue velcro sneakers, small child proportions, cheerful expressive eyebrows with anchors short black bob with straight bangs and a yellow star hair clip on the right, sunflower-yellow dress with a white round collar, light-blue velcro sneakers, sitting on the RIGHT side of the same low light-wood table on a soft cream rug; both at eye level with each other, mother lifting a plush toy cow in her right hand up to the child's eye level, child pointing with her right index finger at the plush cow with wide bright curious eyes and a happy smile, both happy with mouths closed, calm cheerful expressions; prop: one soft plush toy cow, cream-and-brown spotted, cute rounded shape, plain, no label, no sticker, resting in the mother's right hand, plus a woven basket of plush farm animals beside the table; setting: cozy sunlit Vietnamese living room with a low wooden table, soft cream rug, potted green plants, cream fabric curtains; lighting: soft warm morning light coming from the left window, same warm color temperature; medium two-shot at the child's eye level, camera slightly from the front, both characters fully visible, 180-degree rule respected; warm safe cozy family mood. 3D Pixar-style children's educational animation, bright warm soft morning light, cheerful clean pastel and primary colors, gentle cozy mood, 35mm lens look, medium depth of field, both faces clearly visible when two characters are in frame, mouths closed, perfect hand anatomy with exactly five fingers, child-safe friendly scene, single continuous image, flawless 8k render, vertical 9:16, no text, no letters, no labels on objects, no subtitles, no watermark, no logo

Vertical 9:16, 8-second clip, 3D Pixar style children's educational animation. Using the provided reference image as the exact start frame. Preserve the exact Pixar-style look, color palette, warm lighting and mood of the reference image; do not convert to live-action or photorealistic humans; do not shift colors or lighting temperature. 0–3s: the mother on the left slowly lifts the plush cow in her right hand up to the girl's eye level and asks her question, then closes her mouth and smiles waiting; the girl on the right watches the cow and points at it with her right index finger; 3–6s: the girl answers twice slowly and clearly, pointing at the cow each time, then her face brightens into a big radiant smile; 6–8s: the mother praises warmly, lowers the plush cow onto the low wooden table between them, and the girl claps her small hands softly. Gentle slow push-in from a soft eye-level static two-shot, no shake, no harsh zoom. SFX: soft small bell ting exactly when the girl says the word, quiet cheerful ukulele background music much softer than the voices, no loud sudden sounds. ME says in Vietnamese (standard Vietnamese accent): "Great job! Sweetie, what do you call this cow?" Then BE says in Vietnamese (standard Vietnamese accent): "Yes, Mom, cow! Cow!" Pronunciation lock: the English word 'cow' (/kaʊ/) in the girl's line is spoken slowly and clearly in natural native American English, each syllable distinct, with a short pause between the two repetitions; the Vietnamese words keep a natural Vietnamese accent; the English words are never Vietnamese-accented. CRITICAL LIP SYNC MAP: the warm gentle adult Vietnamese female voice belongs ONLY to the mother on the left; the youthful clear high-pitched little-girl voice belongs ONLY to the 5-year-old girl on the right. While one speaks, the other's mouth stays completely closed and still. Hands and objects never cover the mouth; subtle head motion so lip-sync stays readable. ABSOLUTELY NO SUBTITLES, NO TEXT ON SCREEN, no captions, no watermark. Bright, soft, smooth gentle motion, child-friendly, 4k.

ME: a 30-year-old Vietnamese mother in 3D Pixar style, soft oval face with gentle warm dark-brown eyes and a kind smile, shoulder-length black hair tied in a neat low ponytail with a coral-pink scrunchie, small pearl stud earrings, a soft lavender long-sleeve cotton blouse with the sleeves rolled to the elbows, light-beige straight trousers, white house slippers, relaxed caring posture with anchors low ponytail with a coral-pink scrunchie, soft lavender blouse with rolled sleeves, small pearl stud earrings, sitting on the LEFT side of a low light-wood table; BE: a 5-year-old Vietnamese girl in 3D Pixar style, round face with chubby rosy cheeks, big bright dark-brown curious eyes, short black bob haircut with straight bangs and a small yellow star-shaped hair clip on the right side, a sunflower-yellow short-sleeve cotton dress with a white round Peter Pan collar reaching below the knees, white ankle socks, light-blue velcro sneakers, small child proportions, cheerful expressive eyebrows with anchors short black bob with straight bangs and a yellow star hair clip on the right, sunflower-yellow dress with a white round collar, light-blue velcro sneakers, sitting on the RIGHT side of the same low light-wood table on a soft cream rug; both at eye level, mother lifting a plush toy duck in her right hand up to the child's eye level, child pointing with her right index finger at the plush duck with confident happy eyes and a bright smile, both happy with mouths closed; props: one soft plush toy cow already resting on the table on the left, and one soft plush toy duck, yellow with a small orange beak, cute rounded shape, plain, no label, no sticker, in the mother's right hand, arranged left to right on the table in learning order, plus a woven basket of plush farm animals beside the table; setting: cozy sunlit Vietnamese living room with a low wooden table, soft cream rug, potted green plants, cream fabric curtains; lighting: soft warm morning light from the left window, same warm color temperature as before; medium two-shot at the child's eye level, camera slightly from the front, both characters fully visible, 180-degree rule respected; warm safe cozy family mood. 3D Pixar-style children's educational animation, bright warm soft morning light, cheerful clean pastel and primary colors, gentle cozy mood, 35mm lens look, medium depth of field, both faces clearly visible when two characters are in frame, mouths closed, perfect hand anatomy with exactly five fingers, child-safe friendly scene, single continuous image, flawless 8k render, vertical 9:16, no text, no letters, no labels on objects, no subtitles, no watermark, no logo

Vertical 9:16, 8-second clip, 3D Pixar style children's educational animation. Using the provided reference image as the exact start frame. Preserve the exact Pixar-style look, color palette, warm lighting and mood of the reference image; do not convert to live-action or photorealistic humans; do not shift colors or lighting temperature. 0–3s: the mother on the left praises the girl, then lifts the plush duck in her right hand up to eye level and asks her question about the duck sound, then closes her mouth and smiles waiting; the girl on the right watches the duck and points at it with her right index finger; 3–6s: the girl answers twice slowly and clearly, pointing at the duck each time, her face confident and happy; 6–8s: the mother lowers the plush duck onto the table next to the cow, and the girl claps her hands gently. Gentle slow push-in from a soft eye-level static two-shot, no shake, no harsh zoom. SFX: soft small bell ting exactly when the girl says the word, quiet cheerful ukulele background music much softer than the voices, no loud sudden sounds. ME says in Vietnamese (standard Vietnamese accent): "Great job! So what do you call the one that goes quack quack, the duck?" Then BE says in Vietnamese (standard Vietnamese accent): "Yes, duck! Duck!" Pronunciation lock: the English word 'duck' (/dʌk/) in the girl's line is spoken slowly and clearly in natural native American English, each syllable distinct, with a short pause between the two repetitions; the Vietnamese words keep a natural Vietnamese accent; the English words are never Vietnamese-accented. CRITICAL LIP SYNC MAP: the warm gentle adult Vietnamese female voice belongs ONLY to the mother on the left; the youthful clear high-pitched little-girl voice belongs ONLY to the 5-year-old girl on the right. While one speaks, the other's mouth stays completely closed and still. Hands and objects never cover the mouth; subtle head motion so lip-sync stays readable. ABSOLUTELY NO SUBTITLES, NO TEXT ON SCREEN, no captions, no watermark. Bright, soft, smooth gentle motion, child-friendly, 4k.

pure white seamless background; in the upper third, two equal-sized rounded-corner comparison frames side by side with identical width, height, spacing and thin soft-grey border; the screen-left frame shows a blue whale swimming in the ocean, and the screen-right frame shows a great white shark swimming in the ocean; both subjects centered in their frames, simple clean ocean-blue background inside each frame, same 3D semi-realistic illustration style, same viewing angle and scale for fair comparison; no text, labels, numbers, flags or maps inside the frames. In the middle of the image stands a short, slightly chubby anthropomorphic giraffe professor in 3D Pixar style, compact body about one third of the frame height with a shortened humorous neck, warm golden-yellow fur with chestnut-brown patches, two small rounded ossicone horns, big friendly brown eyes, round tortoiseshell glasses, a small burgundy bow tie, a rainbow-striped academic tailcoat over a crisp white shirt, a little black square graduation cap with a gold tassel sitting between the ossicones, holding exactly one thin wooden pointer stick with a red tip in his right hoof-hand, standing upright, confident witty expression, pointing the single pointer stick at the screen-left frame. At the very bottom, three small baby giraffe students in 3D Pixar style seated on three tiny wooden chairs in a row, seen from behind in three-quarter back view, looking up at the two comparison frames; the left one wears a mint-green school backpack, the middle one a sunny-yellow school smock, the right one a light-blue polo shirt with a small red scarf; small and low so they never cover the frames or the professor. Bright even soft studio lighting from above, clean pure white background, soft shadows under the characters. Frontal eye-level medium-wide static shot, same framing in every scene. Educational, witty, tidy atmosphere. All characters have mouths closed. Character lock: The three baby giraffe students keeps three baby giraffe students seen from behind at the bottom, mint-green backpack, yellow smock and light-blue polo with a red scarf. 3D Pixar-style educational explainer animation, clean pure white seamless background, two equal-sized rounded-corner comparison frames side by side in the upper third with the same width, height and spacing, bright even soft studio lighting, crisp sharp details, balanced vertical composition, the professor small enough never to cover the frames, ultra detailed 4k render, vertical 9:16, single continuous image, mouths closed, no text, no letters, no labels, no numbers, no subtitles, no watermark, no logo

Vertical 9:16, 8-second clip, 3D Pixar style educational explainer. Using the provided reference image as the exact start frame. The two upper comparison frames stay completely fixed and motionless, their contents unchanged for the whole clip; pure white background stays clean. Locked-off static frontal shot, no camera shake, no zoom drift. The short chubby giraffe professor in rainbow-striped academic tailcoat with round tortoiseshell glasses, burgundy bow tie and black graduation cap stands center, holding exactly one thin wooden pointer stick with red tip in his right hoof-hand. He first taps the screen-left frame with the single pointer stick showing the blue whale, then taps the screen-right frame showing the great white shark, then raises his eyebrow and shrugs playfully as he asks the question. The three baby giraffe students at the bottom stay seated facing away, mouths closed, small head tilts and curious nods, leaning slightly forward. Soft 'tock' sound as the pointer taps each frame, light pizzicato background music under the voice. GS says in Vietnamese (standard Vietnamese accent): "On the left is the blue whale, on the right is the great white shark, so of the two, which one is actually a fish?" VOICE LOCK: one single mature warm deep authoritative Vietnamese male professor voice, identical timbre, pitch and accent in every clip, never female, never childlike; textbook-clear Vietnamese pronunciation with exact tones and final consonants; the words 'left' and 'right' are pronounced fully and distinctly. Perfect lip-sync for the giraffe professor only; everyone else, including anyone shown inside the comparison frames, keeps the mouth closed. ABSOLUTELY NO SUBTITLES, NO CAPTIONS, NO TEXT OR NUMBERS ANYWHERE ON SCREEN, no watermark. 4k, crisp, smooth expressive animation.

pure white seamless background; in the upper third, two equal-sized rounded-corner comparison frames side by side with identical width, height, spacing and thin soft-grey border; the screen-left frame shows a blue whale surfacing to breathe with a water spout, and the screen-right frame shows a great white shark swimming; both subjects centered in their frames, simple clean ocean-blue background inside each frame, same 3D semi-realistic illustration style, same viewing angle and scale for fair comparison; no text, labels, numbers, flags or maps inside the frames. In the middle of the image stands a short, slightly chubby anthropomorphic giraffe professor in 3D Pixar style, compact body about one third of the frame height with a shortened humorous neck, warm golden-yellow fur with chestnut-brown patches, two small rounded ossicone horns, big friendly brown eyes, round tortoiseshell glasses, a small burgundy bow tie, a rainbow-striped academic tailcoat over a crisp white shirt, a little black square graduation cap with a gold tassel sitting between the ossicones, holding exactly one thin wooden pointer stick with a red tip in his right hoof-hand, standing upright, confident explaining expression, pointing the single pointer stick at the screen-left frame. At the very bottom, three small baby giraffe students in 3D Pixar style seated on three tiny wooden chairs in a row, seen from behind in three-quarter back view, looking up at the two comparison frames; the left one wears a mint-green school backpack, the middle one a sunny-yellow school smock, the right one a light-blue polo shirt with a small red scarf; small and low so they never cover the frames or the professor. Bright even soft studio lighting from above, clean pure white background, soft shadows under the characters. Frontal eye-level medium-wide static shot, same framing in every scene. Educational, witty, tidy atmosphere. All characters have mouths closed. Character lock: The three baby giraffe students keeps three baby giraffe students seen from behind at the bottom, mint-green backpack, yellow smock and light-blue polo with a red scarf. 3D Pixar-style educational explainer animation, clean pure white seamless background, two equal-sized rounded-corner comparison frames side by side in the upper third with the same width, height and spacing, bright even soft studio lighting, crisp sharp details, balanced vertical composition, the professor small enough never to cover the frames, ultra detailed 4k render, vertical 9:16, single continuous image, mouths closed, no text, no letters, no labels, no numbers, no subtitles, no watermark, no logo

Vertical 9:16, 8-second clip, 3D Pixar style educational explainer. Using the provided reference image as the exact start frame. The two upper comparison frames stay completely fixed and motionless, their contents unchanged for the whole clip; pure white background stays clean. Locked-off static frontal shot, no camera shake, no zoom drift. The short chubby giraffe professor in rainbow-striped academic tailcoat with round tortoiseshell glasses, burgundy bow tie and black graduation cap stands center, holding exactly one thin wooden pointer stick with red tip in his right hoof-hand. He taps the screen-left frame with the single pointer stick showing the blue whale surfacing, nods, then glances toward the screen-right frame while keeping the pointer on the left frame. The three baby giraffe students at the bottom stay seated facing away, mouths closed, small head tilts and attentive nods. Soft 'tock' sound as the pointer taps the left frame, light pizzicato background music under the voice. GS says in Vietnamese (standard Vietnamese accent): "The blue whale is a mammal, about thirty meters long. It breathes with lungs, so it has to come up to the surface, okay?" VOICE LOCK: one single mature warm deep authoritative Vietnamese male professor voice, identical timbre, pitch and accent in every clip, never female, never childlike; textbook-clear Vietnamese pronunciation with exact tones and final consonants; the words 'left' and 'right' are pronounced fully and distinctly. Perfect lip-sync for the giraffe professor only; everyone else, including anyone shown inside the comparison frames, keeps the mouth closed. ABSOLUTELY NO SUBTITLES, NO CAPTIONS, NO TEXT OR NUMBERS ANYWHERE ON SCREEN, no watermark. 4k, crisp, smooth expressive animation.

Medium shot, eye-level front view, KTV Minh Phát (a 38-year-old Vietnamese male automotive technician in premium 3D Pixar-inspired style, friendly square face with a confident warm smile and a hint of humor, short neat black undercut hair, black rectangular-frame glasses, clean-shaven, navy-blue short-sleeve mechanic work shirt with bright orange shoulder panels and a blank orange embroidered name patch on the left chest, matching navy work trousers, a navy baseball cap with a blank orange front patch, black safety work shoes, a silver wristwatch on the left wrist, clean hands with no arm hair, upright trustworthy posture; anchors: black rectangular-frame glasses; navy work shirt with bright orange shoulder panels; navy cap with a blank orange front patch) standing at center of a clean modern Vietnamese garage service bay, facing the camera with a confident warm friendly smile, mouth closed, hands relaxed at his sides, a generic unbranded sedan with the hood closed parked behind him, a red tool cart with diagnostic tools nearby, epoxy grey floor, two-post lift, open roller door showing a Vietnamese street with green trees outside, bright warm yellow overhead LED lighting mixed with soft morning daylight from the open door, cheerful optimistic mood, premium 3D Pixar-inspired animation with realistic automotive detail, accurate real-world car parts and proportions, unbranded generic car with no real brand badge, bright clean high-key garage lighting with soft rim light, vivid cheerful colors, 35mm lens look, sharp focus, ultra detailed 8k render, vertical 9:16, single continuous image, physically believable pose, perfect hand anatomy with exactly five fingers, mouth closed, no text, no letters, no readable signs, no license plate numbers, no subtitles, no watermark, no logo overlay

Vertical 9:16, 8-second premium 3D Pixar-inspired automotive explainer clip. REFERENCE: Use the provided image as the exact start frame and only visual reference; build natural motion only from it, no new characters, no new car, no outfit, glasses or patch changes. SCENE PURPOSE: This scene hooks the viewer by naming the exact morning symptom — the engine only goes "click-click" and will not start — and promises to point out the fault in one minute. CAMERA: static medium shot with a very subtle micro drift, holding on the technician's face. ACTION: KTV looks straight into the lens and speaks with a confident warm smile → gives a small friendly nod → keeps his posture upright and relaxed, hands at his sides. CHARACTER & LIP SYNC: KTV speaks directly to camera, highly accurate Vietnamese lip sync, mouth shapes match Vietnamese phonemes, hands and tools never block the mouth, subtle head motion so lip-sync stays readable. VOICE: native Vietnamese MALE VOICE, warm solid adult male about 35–40, clear articulation, friendly and slightly humorous, keep the exact same voice profile in every scene. DIALOGUE: KTV says in Vietnamese (standard Vietnamese accent): "The morning starter goes click-click and the engine won’t start, usually due to a weak battery or the starter.". VISUAL ICONS: a soft glowing orange ring pulses briefly around the closed hood of the car behind him to hint at the fault area, no text or fonts, does not cover his face or mouth. AUDIO: light garage ambience, faint clink of tools on the cart, cheerful low educational background music well under the voice. SAFETY LOCK: all driving shown is legal and safe, seatbelt fastened, no phone while driving, no dangerous DIY on brakes, airbags, fuel lines or high-voltage EV parts. CAR REALISM LOCK: car parts keep real shape, size and mounting position; physically believable poses only; no motorcycles. CONTINUITY LOCK: same car, same garage, same lighting direction, same props state as the start frame. ANTI-TEXT LOCK: No subtitles, no on-screen text, no captions, no watermark, no logo overlay, no readable signs or license plates. 4k, sharp, smooth motion.

Close-up, slight low angle from inside the engine bay, PHUTUNG (the exact weak 12V car battery of the topic anthropomorphized in premium 3D Pixar-inspired style while keeping its real shape, real material and real mounting position on the car, big expressive cartoon eyes and a flexible mouth built into its plastic surface, thick worried eyebrows, small stubby gloved arms, visible wear exactly matching the fault: slightly swollen case, corroded terminals with white-green salt build-up, low charge indicator, tiny wisps of steam or dust when stressed; anchors: big expressive cartoon eyes built into the battery surface; visible wear exactly matching the fault (swollen case, corroded terminals); stays mounted in its real position under the hood) mounted in the real battery tray inside the engine bay of the generic unbranded sedan with the hood open, its big cartoon eyes looking toward the camera with a worried grumpy expression, thick eyebrows furrowed, mouth closed, small stubby gloved arms pressed against its own swollen case, thin wisps of steam rising from the top, the two corroded terminals clearly visible with white-green salt build-up, battery hold-down clamp and cables in real position, clean modern Vietnamese garage service bay around it, bright warm yellow overhead lighting focused on the battery area with soft daylight from the open roller door, humorous sympathetic mood, premium 3D Pixar-inspired animation with realistic automotive detail, accurate real-world car parts and proportions, unbranded generic car with no real brand badge, bright clean high-key garage lighting with soft rim light, vivid cheerful colors, 35mm lens look, sharp focus, ultra detailed 8k render, vertical 9:16, single continuous image, physically believable pose, perfect hand anatomy with exactly five fingers, mouth closed, no text, no letters, no readable signs, no license plate numbers, no subtitles, no watermark, no logo overlay

Vertical 9:16, 8-second premium 3D Pixar-inspired automotive explainer clip. REFERENCE: Use the provided image as the exact start frame and only visual reference; build natural motion only from it, no new characters, no new car, no outfit, glasses or patch changes. SCENE PURPOSE: This scene lets the weak battery complain in its own voice so the viewer recognizes the same symptom on their own car and suspects the battery. CAMERA: slow push-in toward the battery, ending tight on its worried face. ACTION: the battery's cartoon eyes blink slowly and look toward the lens, its mouth on the plastic surface moves as it complains → a small puff of steam wisps rises from its top → it sighs heavily and its eyes droop, shoulders of its stubby arms slump. CHARACTER & LIP SYNC: PHUTUNG speaks, its mouth on the battery surface moves with highly accurate Vietnamese lip sync, mouth shapes match Vietnamese phonemes, no hands or tools block the mouth. VOICE: gruff metallic grumpy Vietnamese male voice, standard Vietnamese accent, complaining and humorous rather than threatening, keep the exact same voice profile in every scene. DIALOGUE: PHUTUNG says in Vietnamese (standard Vietnamese accent): "I’m worn out, boss keeps cranking and I keep going click-click, and you still won’t replace me. The voltage has dropped, I’m exhausted.". VISUAL ICONS: a soft pulsing orange ring highlights the corroded terminals and the low charge indicator while it speaks, no text or fonts, does not cover its eyes or mouth. AUDIO: faint electrical crackle and a weak starter-like tick, low humorous music under the voice, light garage ambience. SAFETY LOCK: all driving shown is legal and safe, seatbelt fastened, no phone while driving, no dangerous DIY on brakes, airbags, fuel lines or high-voltage EV parts. CAR REALISM LOCK: car parts keep real shape, size and mounting position; physically believable poses only; no motorcycles. CONTINUITY LOCK: same car, same garage, same lighting direction, same props state as the start frame. ANTI-TEXT LOCK: No subtitles, no on-screen text, no captions, no watermark, no logo overlay, no readable signs or license plates. 4k, sharp, smooth motion.

3D Pixar-style animation masterpiece, Unreal Engine 5 render, vivid warm natural colors. Wide shot from a low angle at water level, looking slightly up at two anthropomorphic rice plants rooted side by side in the same paddy soil: on the left CAYKHOE, a vigorous healthy rice plant character with glossy deep-green botanically correct rice leaves showing visible midrib and parallel veins, a friendly wise face on the main stem with bushy leaf eyebrows and warm brown eyes, two leaf-arms, a tiny woven conical hat (nón lá) tilted to the left, a small brown canvas shoulder bag with a green leaf patch, upright confident posture, startled concerned expression, mouth closed; on the right CAYBENH, a sick rice plant of the same variety, drooping posture, a worried young face with big teary eyes on the main stem, rice leaves showing the exact botanically accurate symptom of rice blast disease: diamond-shaped lesions with grey-white centers and brown margins, leaf tips beginning to dry, a small cream cloth bandage tied around one leaf, a short red string tied around its stem base, weak teary-eyed expression, mouth closed. The paddy water shimmers between rice rows, lush green rice plants all around, distant palm trees and a small farmer hut on the horizon. Warm soft early morning sunlight from the left, low angle, gentle golden haze. Overall mood: worry and concern at the first sign of disease. real outdoor Vietnamese farmland setting, natural sunlight, botanically accurate crop, leaves, fruit and soil detail, cinematic composition, sharp focus, highly detailed 8k, vertical 9:16, single continuous image, perfect hand anatomy, mouth closed, no text, no letters, no subtitles, no watermark, no logo, no readable product label

Vertical 9:16, 8-second clip, 3D Pixar style. Using the provided reference image as the exact start frame. Slow gentle push-in from the wide water-level shot toward the two rice plants. CAYBENH droops and trembles slightly, her teary eyes looking down at the diamond-shaped lesions on her leaves, then she lifts her head and speaks with a weak, shaky mouth movement. CAYKHOE, standing upright on the left, suddenly startles, his leaf-eyebrows shoot up, he turns his head sharply to the right toward CAYBENH, his mouth opens to speak. While one speaks, the other's mouth stays completely closed; leaves never cover the mouth. The warm male voice belongs ONLY to the healthy plant with the tiny conical hat; the young female voice belongs ONLY to the sick plant with the cream bandage. Gentle wind ripples the rice leaves, water in the paddy shimmers and ripples softly, a few sparrows fly in the distance, faint frog croaks. Soft early morning golden light from the left. Dialogue in order: CAYBENH says in Vietnamese (Southern Vietnamese (Saigon) accent): "Brother Hai, my leaves have diamond-shaped lesions, grey in the middle with brown edges, and they’re all dried up!" Then CAYKHOE says in Vietnamese (Southern Vietnamese (Saigon) accent): "Oh my goodness, let me take a look!" No subtitles, no on-screen text, no watermark, no logo. 4k, sharp, smooth natural motion, authentic outdoor farmland.

3D Pixar-style animation masterpiece, Unreal Engine 5 render, vivid warm natural colors. Close-up shot from a slightly high angle focusing on the two rice plants side by side in the same paddy soil: on the left CAYKHOE, a vigorous healthy rice plant character with glossy deep-green botanically correct rice leaves showing visible midrib and parallel veins, a friendly wise face on the main stem with bushy leaf eyebrows and warm brown eyes, a tiny woven conical hat (nón lá) tilted to the left, a small brown canvas shoulder bag with a green leaf patch, standing upright, holding a magnifying glass in his right leaf-arm and leaning in to inspect the lesions, focused serious expression, mouth closed; on the right CAYBENH, a sick rice plant of the same variety, drooping posture, a worried young face with big teary eyes on the main stem, rice leaves showing diamond-shaped lesions with grey-white centers and brown margins, a small cream cloth bandage tied around one leaf, a short red string tied around its stem base, trembling with lips pressed together, scared expression, mouth closed. The magnifying glass is positioned close to CAYBENH's leaf, magnifying the diamond-shaped lesion. Lush green rice paddy field in the Mekong Delta, water shimmering between rice rows, distant palm trees and a small farmer hut on the horizon. Warm soft early morning sunlight from the left, low angle, gentle golden haze. Overall mood: focused diagnosis and fear. real outdoor Vietnamese farmland setting, natural sunlight, botanically accurate crop, leaves, fruit and soil detail, cinematic composition, sharp focus, highly detailed 8k, vertical 9:16, single continuous image, perfect hand anatomy, mouth closed, no text, no letters, no subtitles, no watermark, no logo, no readable product label

Vertical 9:16, 8-second clip, 3D Pixar style. Using the provided reference image as the exact start frame. Macro rack focus through the magnifying glass: the focus shifts from CAYKHOE's focused face to the magnified diamond-shaped lesion on CAYBENH's leaf, then back to CAYKHOE. CAYKHOE holds the magnifying glass steady with his right leaf-arm, leans in closer, narrows his eyes, then lowers the magnifying glass and speaks with calm, serious mouth movements. CAYBENH trembles beside him, her lips pressed together, eyes wide with fear, mouth closed, not speaking. While one speaks, the other's mouth stays completely closed; leaves never cover the mouth. The warm male voice belongs ONLY to the healthy plant with the tiny conical hat; the young female voice belongs ONLY to the sick plant with the cream bandage. Gentle wind ruffles the rice leaves, water ripples softly in the paddy, distant sparrows chirp, faint frog croaks. Soft early morning golden light from the left. Dialogue in order: CAYKHOE says in Vietnamese (Southern Vietnamese (Saigon) accent): "That’s leaf blast, sweetie. The cause is too much nitrogen making the leaves soft, the field tillering too densely, and humidity staying high for a long time." No subtitles, no on-screen text, no watermark, no logo. 4k, sharp, smooth natural motion, authentic outdoor farmland.

Close-up of weathered hands of a 72-year-old Vietnamese grandfather from the Southern countryside, photorealistic, lean weathered face with deep smile lines, kind narrow dark eyes, short thinning white hair, a short neat white goatee, a small dark mole on the left cheek, faded grey cotton shirt with two chest pockets and sleeves rolled to the forearms, loose dark-brown trousers, worn brown rubber sandals, calm upright posture, mouth relaxed and closed, slowly separating one paper lottery ticket from a small stack held in his left hand and placing it on a wooden box lid, sitting on a small plastic stool under an old tamarind tree at a Southern Vietnamese village street corner, a wooden ticket tray nearby, a simple country house with tiled roof and vegetable garden in the background, distant rice fields at late afternoon, warm golden afternoon sunlight filtering through tamarind leaves, long soft shadows on the ground, gentle contrast, camera slowly pushes in on the hands, eye-level angle, 50mm lens, calm contemplative mood with breathing room, no text, no letters, no subtitles, no watermark, no logo Character lock: The narrator keeps voice only, never shown on screen, no microphone or talking head in frame. cinematic photorealistic film still, shot on ARRI Alexa with a 35mm prime lens, natural motivated light, gentle film grain, true-to-life skin, fabric and wood textures, shallow depth of field, calm contemplative composition with breathing room, authentic Vietnamese setting, vertical 9:16, single continuous image, mouths closed, no text, no letters, no subtitles, no watermark, no logo

Vertical 9:16, 8-second cinematic photoreal clip, slow contemplative pace. Use the provided image as the exact start frame — no new characters, no new objects beyond what is in the image. Camera: very slow push-in on the detail of the hands. Subject motion: the weathered fingers slowly separate one lottery ticket from the stack and place it on the wooden box lid, a gentle breeze moves a few tamarind leaves, two subtle micro-movements across the 8 seconds. SFX: soft rustle of paper tickets, distant village sounds, a faint bicycle bell far away, light wind through tamarind leaves. BGM: very soft bamboo flute, no lyrics. No dialogue or voice generated in the clip; on-screen people keep their lips closed and do not lip-sync; narration is added in editing. Photorealistic, natural light, gentle film grain, no text, no subtitles, no watermark. Voiceover (off-screen narrator) added in editing; on-screen characters do not lip-sync.

The separated lottery ticket lies alone on the wooden box lid, the rest of the stack held in the left hand of a 72-year-old Vietnamese grandfather from the Southern countryside, photorealistic, lean weathered face with deep smile lines, kind narrow dark eyes, short thinning white hair, a short neat white goatee, a small dark mole on the left cheek, faded grey cotton shirt with two chest pockets and sleeves rolled to the forearms, loose dark-brown trousers, worn brown rubber sandals, calm upright posture, mouth relaxed and closed, sitting on a small plastic stool under an old tamarind tree at a Southern Vietnamese village street corner, wooden ticket tray nearby, simple country house with tiled roof and vegetable garden in the background, distant rice fields at late afternoon, several ripe tamarind pods fallen on the ground, warm golden afternoon sunlight filtering through tamarind leaves, long soft shadows, gentle contrast, camera slowly pulls back to reveal the old tamarind tree, the small plastic stool, and the village road stretching into the distance, eye-level angle, 35mm lens, calm patient slightly nostalgic mood with breathing room, no text, no letters, no subtitles, no watermark, no logo Character lock: The narrator keeps voice only, never shown on screen, no microphone or talking head in frame. cinematic photorealistic film still, shot on ARRI Alexa with a 35mm prime lens, natural motivated light, gentle film grain, true-to-life skin, fabric and wood textures, shallow depth of field, calm contemplative composition with breathing room, authentic Vietnamese setting, vertical 9:16, single continuous image, mouths closed, no text, no letters, no subtitles, no watermark, no logo

Vertical 9:16, 8-second cinematic photoreal clip, slow contemplative pace. Use the provided image as the exact start frame — no new characters, no new objects beyond what is in the image. Camera: slow pan or gentle tilt revealing the place, from the hands and ticket on the box lid to the wide village road under the tamarind tree. Subject motion: the old man's left hand adjusts the stack of tickets slightly, a ripe tamarind pod falls from the tree, two subtle micro-movements across the 8 seconds. SFX: ripe tamarind pods dropping on dry ground, distant vendor calls, soft wind through leaves, a faint bicycle passing. BGM: very soft bamboo flute, no lyrics. No dialogue or voice generated in the clip; on-screen people keep their lips closed and do not lip-sync; narration is added in editing. Photorealistic, natural light, gentle film grain, no text, no subtitles, no watermark. Voiceover (off-screen narrator) added in editing; on-screen characters do not lip-sync.

2D flat comic illustration, cute chibi style, thick clean line art, flat vibrant colors, humorous tone. On the left stands Tang Sanzang, a stylized 2D flat comic chibi illustration character with thick clean line art, shiny bald head, round tortoiseshell glasses, a red-and-gold patchwork robe over a cream inner robe, a calm warm smile, a string of wooden prayer beads on the wrist, a small thermos flask in one hand, a paper map in the other; anchors: shiny bald head with round tortoiseshell glasses; red-and-gold patchwork robe over a cream inner robe; wooden prayer beads on the wrist. Center-left is Sun Wukong, a stylized 2D flat comic chibi illustration character with thick clean line art, fluffy golden-brown fur, a golden headband across the forehead, big round amber eyes with white highlights, an energetic cheeky grin, a yellow tunic with a tiger-stripe skirt, a red-and-gold staff on his back, a smartphone with a cracked screen and a dead-battery icon in one hand, small monkey tail curling behind; anchors: golden headband on fluffy golden-brown fur; tiger-stripe skirt over a yellow tunic; red-and-gold staff on his back. Center-right is Zhu Bajie, a stylized 2D flat comic chibi illustration character with thick clean line art, round pink pig face with floppy ears, big round belly, black robe, a wooden nine-tooth rake carried on his back, a half-eaten steamed bun in one hand, sleepy half-closed eyes, a tiny portable fan hanging from his belt; anchors: round pink pig face with floppy ears; black robe over a big round belly; wooden nine-tooth rake on his back. On the right is Sha Wujing, a stylized 2D flat comic chibi illustration character with thick clean line art, blue-grey skin, a thick bushy black beard, a necklace of big round brown wooden beads, a bamboo shoulder pole with two travel bundles, a rolled-up charging cable used as a headband, honest wide eyes; anchors: blue-grey skin with a thick bushy black beard; necklace of big round brown wooden beads; bamboo shoulder pole with two travel bundles. All four stand frozen in a line on the trail, mouths closed, eyes wide in exaggerated cartoon panic: Wukong thrusts the cracked smartphone up toward the sky with both arms, the screen glowing a blinking red low-battery icon like a countdown clock, Bajie mid-chew with puffed cheeks, Sanzang calmly unfolding the paper map, Wujing tilting his head with a puzzled blink. Setting: a winding mountain trail in ancient China at golden hour, tall grass, mossy rocks, a small wooden signpost, a distant pagoda silhouette on the horizon, no temples, no statues. Warm golden hour light from the left, long soft shadows. Wide group shot from a low three-quarter angle, all four characters fully in frame with the sky above them. Lighthearted comedic adventure mood, warm and playful. premium stylized animation frame, expressive cartoon faces with clear readable eyes, vibrant saturated colors, clean silhouettes, cinematic lighting with soft depth, consistent character design, mouths closed, clean hand anatomy, single continuous image, vertical 9:16, no text, no letters, no subtitles, no watermark, no logo, no split screen

Vertical 9:16, 8-second clip, 2D flat comic illustration, cute chibi style, thick clean line art, flat vibrant colors, humorous tone. Using the provided reference image as the exact start frame. Characters: BOSS = Tang Sanzang, the chibi monk with the shiny bald head and round tortoiseshell glasses on the far left, calm mature warm male voice; HERO = Sun Wukong, the chibi monkey with the golden headband and cracked smartphone on the center-left, youthful bright quick male voice; BUDDY = Zhu Bajie, the chibi pig with the floppy ears and half-eaten steamed bun on the center-right, warm slow slightly whiny male voice; EXTRA = Sha Wujing, the chibi blue-grey bearded figure with the bamboo shoulder pole on the far right, slow honest male voice. Beat 1 (0-3s): quick push-in on the group as all four freeze mid-step, Wukong whips the cracked smartphone up toward the sky, the red low-battery icon blinking like a countdown, Bajie's cheeks puff mid-chew, Wujing tilts his head. Beat 2 (3-6s): HERO says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Master, the battery’s at exactly one percent, the map won’t load, and we have no charger!" Wukong's mouth moves in perfect lip-sync as he shouts and waves the phone at the sky; Sanzang, Bajie and Wujing keep their mouths completely closed and still, only blinking and reacting with body language. Beat 3 (6-8s): the red icon blinks faster, Wukong's arms sag in comic despair, a small comic dust puff at his feet, the others lean in with worried cartoon eyes. Camera: quick comedic push-in on the group, then a slight handheld wobble as the battery icon blinks. Sound: lo-fi beat blended with đàn tranh and bamboo flute, soft wind through tall grass, a cartoon ticking like a countdown, a small 'boing' when Wukong's arms drop. chibi 2D motion-comic animation, flat colors preserved, bodies bounce slightly. Only the character who is speaking moves their mouth, in perfect lip-sync with their own fixed voice; every other on-screen character keeps the mouth completely closed and still, only blinks and reacts with body language. Never two mouths open at once. Hands and props never cover the speaker's mouth; keep head motion subtle. ABSOLUTELY NO SUBTITLES, NO TEXT ON SCREEN, no watermark. Smooth expressive animation, consistent character design, family-friendly slapstick only. Trư Bát Giới, Đường Tăng, Sa Tăng: mouth closed, not speaking.

2D flat comic illustration, cute chibi style, thick clean line art, flat vibrant colors, humorous tone. On the left stands Tang Sanzang, a stylized 2D flat comic chibi illustration character with thick clean line art, shiny bald head, round tortoiseshell glasses, a red-and-gold patchwork robe over a cream inner robe, a calm warm smile, a string of wooden prayer beads on the wrist, a small thermos flask in one hand, a paper map in the other; anchors: shiny bald head with round tortoiseshell glasses; red-and-gold patchwork robe over a cream inner robe; wooden prayer beads on the wrist. Center-left is Sun Wukong, a stylized 2D flat comic chibi illustration character with thick clean line art, fluffy golden-brown fur, a golden headband across the forehead, big round amber eyes with white highlights, an energetic cheeky grin, a yellow tunic with a tiger-stripe skirt, a red-and-gold staff on his back, a smartphone with a cracked screen in one hand, thumb pressing the screen, small monkey tail curling behind; anchors: golden headband on fluffy golden-brown fur; tiger-stripe skirt over a yellow tunic; red-and-gold staff on his back. Center-right is Zhu Bajie, a stylized 2D flat comic chibi illustration character with thick clean line art, round pink pig face with floppy ears, big round belly, black robe, a wooden nine-tooth rake carried on his back, a half-eaten steamed bun in one hand, sleepy half-closed eyes, a tiny portable fan hanging from his belt, leaning in with a whiny pout; anchors: round pink pig face with floppy ears; black robe over a big round belly; wooden nine-tooth rake on his back. On the right is Sha Wujing, a stylized 2D flat comic chibi illustration character with thick clean line art, blue-grey skin, a thick bushy black beard, a necklace of big round brown wooden beads, a bamboo shoulder pole with two travel bundles, a rolled-up charging cable used as a headband, honest wide eyes, peeking over Bajie's shoulder; anchors: blue-grey skin with a thick bushy black beard; necklace of big round brown wooden beads; bamboo shoulder pole with two travel bundles. Wukong presses the cracked screen with a confident grin, a tiny 'live' glow reflecting on his face, mouth closed; Bajie leans in with a whiny pout, mouth closed; Sanzang and Wujing watch from the sides, mouths closed. Setting: the same winding mountain trail in ancient China at golden hour, tall grass, mossy rocks, a small wooden signpost, a distant pagoda silhouette on the horizon, no temples, no statues. Warm golden hour light from the left, long soft shadows. Medium two-shot centered on Wukong and Bajie, Sanzang and Wujing soft in the background edges, static framing. Playful comedic tension, warm adventure mood. premium stylized animation frame, expressive cartoon faces with clear readable eyes, vibrant saturated colors, clean silhouettes, cinematic lighting with soft depth, consistent character design, mouths closed, clean hand anatomy, single continuous image, vertical 9:16, no text, no letters, no subtitles, no watermark, no logo, no split screen

Vertical 9:16, 8-second clip, 2D flat comic illustration, cute chibi style, thick clean line art, flat vibrant colors, humorous tone. Using the provided reference image as the exact start frame. Characters: BOSS = Tang Sanzang, the chibi monk with the shiny bald head and round tortoiseshell glasses on the left, calm mature warm male voice; HERO = Sun Wukong, the chibi monkey with the golden headband and cracked smartphone on the center-left, youthful bright quick male voice; BUDDY = Zhu Bajie, the chibi pig with the floppy ears and half-eaten steamed bun on the center-right, warm slow slightly whiny male voice; EXTRA = Sha Wujing, the chibi blue-grey bearded figure with the bamboo shoulder pole on the right, slow honest male voice. Beat 1 (0-3s): static two-shot, Wukong grins wide and jabs his thumb on the cracked screen, a tiny live glow flickers on his face, Bajie leans in with a whiny pout. Beat 2 (3-6s): HERO says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Old Sun is live, begging for a charge – anyone nearby, help!" Then BUDDY says in Vietnamese (Northern Vietnamese (Hanoi) accent): "Hold on, Old Pig is hungry and sleepy, let me finish my steamed bun first!" Wukong's mouth moves in perfect lip-sync as he announces his plan and points at the phone, then Bajie's mouth moves in perfect lip-sync as he protests and clutches his steamed bun; Sanzang and Wujing keep their mouths completely closed and still, only blinking and reacting with body language. Beat 3 (6-8s): the screen flickers with weak signal, Wukong freezes mid-grin, Bajie's ears droop, a comic question mark puff pops above Sanzang's head, Wujing tilts his head. Camera: static two-shot then a tiny snap zoom toward the flickering screen. Sound: lo-fi beat with đàn tranh and bamboo flute, a soft 'ting' when the screen lights up, a low static crackle as the signal weakens. chibi 2D motion-comic animation, flat colors preserved, bodies bounce slightly. Only the character who is speaking moves their mouth, in perfect lip-sync with their own fixed voice; every other on-screen character keeps the mouth completely closed and still, only blinks and reacts with body language. Never two mouths open at once. Hands and props never cover the speaker's mouth; keep head motion subtle. ABSOLUTELY NO SUBTITLES, NO TEXT ON SCREEN, no watermark. Smooth expressive animation, consistent character design, family-friendly slapstick only. Đường Tăng, Sa Tăng: mouth closed, not speaking.