🏮 Học tiếng Trung cùng bé

IMAGE PROMPT [1]

BE_BIN, 3D animated Vietnamese boy, 5 years old, round face, short black hair, bright brown eyes, wearing a yellow t-shirt with a small red apple print, blue shorts, white sneakers, and a small green backpack with a cartoon dinosaur keychain (fixed: yellow t-shirt with a small red apple print; green backpack with a dinosaur keychain); ME_LAN, 3D animated Vietnamese woman, 35 years old, warm smile, shoulder-length black hair tied in a low bun, wearing a light blue floral blouse, beige trousers, and brown sandals, carrying a woven bamboo basket (fixed: light blue floral blouse; woven bamboo basket), ME_LAN and BE_BIN stand in front of a fruit stall, ME_LAN points at a red apple, BE_BIN looks curious, warm sunlight, medium shot, eye level, premium 3D cinematic animation, near-realistic faces with soft cartoon charm, bright warm Vietnamese setting, clean uncluttered background, vertical 9:16, single still frame at the first moment of the clip, no Chinese characters, letters or symbols anywhere in the frame, perfect hand anatomy, no extra limbs, no distorted faces, no duplicate characters, mouth closed, no split screen, no collage, no text, no subtitles, no watermark, no logo overlay

VIDEO PROMPT [1]

vertical 9:16, exactly 8-second single continuous shot (no cuts, no montage, no transitions), premium 3D cinematic animation, near-realistic faces with soft cartoon charm, bright warm Vietnamese setting, clean uncluttered background. Use the provided reference image as the exact start frame; preserve the exact character designs, outfits, props, setting, color palette and lighting. Setting: Outdoor Vietnamese market with fruit stalls, bright morning sunlight, colorful fruits, clean and uncluttered background. Camera: slow push-in. Action: ME_LAN points at the apple, BE_BIN nods and repeats the word, no Chinese characters, letters or symbols anywhere in the frame. Audio: market ambience, soft chatter; cheerful soft kids music far below the voices, a gentle chime after each new word. No subtitles, no on-screen text, no watermark, no logo overlay. 4k, sharp, smooth natural motion. Voices: ME_LAN = gentle, warm, motherly, native Vietnamese, Northern Vietnamese (Hanoi) accent; BE_BIN = cheerful, high-pitched, energetic, native Vietnamese, Northern Vietnamese (Hanoi) accent; keep every voice identical in all scenes, never swap voices, no extra voices. Accurate Vietnamese lip-sync only for the character currently speaking, listeners keep mouths closed and react silently, no overlapping speech, the mouth closes completely after the line. Timing: 0.0–0.4s settle, mouths closed; 0.4–4.2s ME_LAN speaks; 4.5–6.6s BE_BIN speaks; 6.6–8.0s line finished, mouths closed, hold the reaction. ME_LAN says in Vietnamese: "Bin ơi, hôm nay mẹ con mình đi chợ mua táo nhé." BE_BIN says in Vietnamese: "Dạ thưa mẹ, táo là píngguǒ. Píngguǒ."

IMAGE PROMPT [2]

BE_BIN, 3D animated Vietnamese boy, 5 years old, round face, short black hair, bright brown eyes, wearing a yellow t-shirt with a small red apple print, blue shorts, white sneakers, and a small green backpack with a cartoon dinosaur keychain (fixed: yellow t-shirt with a small red apple print; green backpack with a dinosaur keychain); ME_LAN, 3D animated Vietnamese woman, 35 years old, warm smile, shoulder-length black hair tied in a low bun, wearing a light blue floral blouse, beige trousers, and brown sandals, carrying a woven bamboo basket (fixed: light blue floral blouse; woven bamboo basket), ME_LAN and BE_BIN at the same stall, ME_LAN points at a bunch of bananas, BE_BIN looks at them, close-up, slightly high angle, premium 3D cinematic animation, near-realistic faces with soft cartoon charm, bright warm Vietnamese setting, clean uncluttered background, vertical 9:16, single still frame at the first moment of the clip, no Chinese characters, letters or symbols anywhere in the frame, perfect hand anatomy, no extra limbs, no distorted faces, no duplicate characters, mouth closed, no split screen, no collage, no text, no subtitles, no watermark, no logo overlay

VIDEO PROMPT [2]

vertical 9:16, exactly 8-second single continuous shot (no cuts, no montage, no transitions), premium 3D cinematic animation, near-realistic faces with soft cartoon charm, bright warm Vietnamese setting, clean uncluttered background. Use the provided reference image as the exact start frame; preserve the exact character designs, outfits, props, setting, color palette and lighting. Setting: Same market stall with fruits, bright morning light. Camera: gentle pan right. Action: ME_LAN points at bananas, BE_BIN repeats the word with a smile, no Chinese characters, letters or symbols anywhere in the frame. Audio: market ambience, fruit stall sounds; cheerful soft kids music far below the voices, a gentle chime after each new word. No subtitles, no on-screen text, no watermark, no logo overlay. 4k, sharp, smooth natural motion. Voices: ME_LAN = gentle, warm, motherly, native Vietnamese, Northern Vietnamese (Hanoi) accent; BE_BIN = cheerful, high-pitched, energetic, native Vietnamese, Northern Vietnamese (Hanoi) accent; keep every voice identical in all scenes, never swap voices, no extra voices. Accurate Vietnamese lip-sync only for the character currently speaking, listeners keep mouths closed and react silently, no overlapping speech, the mouth closes completely after the line. Timing: 0.0–0.4s settle, mouths closed; 0.4–4.2s ME_LAN speaks; 4.5–6.6s BE_BIN speaks; 6.6–8.0s line finished, mouths closed, hold the reaction. ME_LAN says in Vietnamese: "Giỏi lắm! Thế còn quả chuối tiếng Trung gọi là gì nhỉ?" BE_BIN says in Vietnamese: "Dạ thưa mẹ, chuối là xiāngjiāo. Xiāngjiāo."