🍢 Đồ ăn vặt – Quy trình làm

IMAGE PROMPT [1]

Close-up of hands holding a freshly fried crispy rice paper roll, steam rising, on a wooden cutting board, extreme close-up, eye level, photorealistic food video, clean modern Vietnamese kitchen counter, appetizing true-to-life food textures, soft daylight, visible steam and sizzle, vertical 9:16, single still frame at the first moment of the clip, the same kitchen counter, utensils and dominant hand, food state changes only through the shown action, 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), photorealistic food video, clean modern Vietnamese kitchen counter, appetizing true-to-life food textures, soft daylight, visible steam and sizzle. Use the provided reference image as the exact start frame; preserve the exact character designs, outfits, props, setting, color palette and lighting. Setting: Clean modern Vietnamese kitchen counter with wooden surface, soft daylight from window, minimal background. Camera: slow push-in. Action: Hands break the roll in half, then pick up one half and show it to the camera, the same kitchen counter, utensils and dominant hand, food state changes only through the shown action. Audio: crispy crackling sound, soft steam hiss; crisp food ASMR synced to the action (chopping, sizzling, crunching), light upbeat music far below the voice. No subtitles, no on-screen text, no watermark, no logo overlay. 4k, sharp, smooth natural motion. Voices: NARRATOR (off-screen voice-over, not visible) = Young Vietnamese female, 25-30, warm and cheerful, slightly fast-paced, native Vietnamese, Southern Vietnamese (Saigon) accent; keep every voice identical in all scenes, never swap voices, no extra voices. No visible character lip-syncs, every visible mouth stays closed. Timing: 0.0–0.4s settle, mouths closed; 0.4–7.2s NARRATOR speaks; 7.2–8.0s line finished, mouths closed, hold the reaction. Off-screen narrator says in Vietnamese: "Bánh tráng cuộn chiên giòn rụm, cắn một miếng là nghe rõ tiếng giòn tan nha. Chỉ cần vài nguyên liệu đơn giản thôi hen."

IMAGE PROMPT [2]

Medium shot of hands arranging ingredients on the counter: rice paper, eggs, ground pork, green onions, spices, medium shot, high angle, photorealistic food video, clean modern Vietnamese kitchen counter, appetizing true-to-life food textures, soft daylight, visible steam and sizzle, vertical 9:16, single still frame at the first moment of the clip, the same kitchen counter, utensils and dominant hand, food state changes only through the shown action, 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), photorealistic food video, clean modern Vietnamese kitchen counter, appetizing true-to-life food textures, soft daylight, visible steam and sizzle. Use the provided reference image as the exact start frame; preserve the exact character designs, outfits, props, setting, color palette and lighting. Setting: Clean modern Vietnamese kitchen counter with wooden surface, soft daylight from window, minimal background. Camera: gentle pan right. Action: Hands arrange ingredients, then pick up the rice paper package and show it to the camera, the same kitchen counter, utensils and dominant hand, food state changes only through the shown action. Audio: rustling of packaging, soft clink of spice jars; crisp food ASMR synced to the action (chopping, sizzling, crunching), light upbeat music far below the voice. No subtitles, no on-screen text, no watermark, no logo overlay. 4k, sharp, smooth natural motion. Voices: NARRATOR (off-screen voice-over, not visible) = Young Vietnamese female, 25-30, warm and cheerful, slightly fast-paced, native Vietnamese, Southern Vietnamese (Saigon) accent; keep every voice identical in all scenes, never swap voices, no extra voices. No visible character lip-syncs, every visible mouth stays closed. Timing: 0.0–0.4s settle, mouths closed; 0.4–7.6s NARRATOR speaks; 7.6–8.0s line finished, mouths closed, hold the reaction. Off-screen narrator says in Vietnamese: "Nguyên liệu nè: bánh tráng, trứng gà, thịt heo băm, hành lá, và gia vị. Tui để sẵn trên bàn, mấy bà chuẩn bị y chang là được hen."