OpenZhenZhen AI Prompt Gallery · MiniMax H3 · video

First Trip to Tokyo: From the Airport to the Night Streets

First Trip to Tokyo: From the Airport to the Night Streets — explore this MiniMax H3 creation on OpenZhenZhen, with its original prompt and a reusable generation example.

First Trip to Tokyo: From the Airport to the Night Streets — AI video creation
First Trip to Tokyo: From the Airport to the Night Streets

Prompt

Chinese prompt

制作一段20秒、照片级写实的手持手机旅行Vlog：一名成年女性第一次前往东京。使用所提供的身份参考图来固定她的脸部与外貌；在所有镜头中保持她的身份、肤色、发型、身材比例、奶油米色短款风衣、象牙色针织上衣、深炭灰阔腿裤、白色运动鞋、黑色斜挎包、银色手表、自然妆容和行李箱一致。保持真实手机拍摄质感：轻微手部抖动、自动对焦呼吸、曝光变化、自然运动模糊和真实色彩，避免商业广告或电影化效果。0–3秒：明亮机场航站楼内，她拉着行李箱前行，随后短暂转向自己自拍，说：“Okay… this is actually happening.” 3–6秒：她穿过出发大厅，随手拍摄建筑结构和航班信息屏。6–9秒：她坐在飞机舷窗旁，展示云层上方被夕阳照亮的机翼，并说：“I can’t believe I’m going to Tokyo.” 9–12秒：降落滑行时，她拍摄窗外机场活动，并举起手机。12–15秒：她拖着行李箱走出机场，附近有自行车、自动售货机和铁路。15–17.5秒：安静的东京街区、咖啡馆和店铺门面；她边走边说：“Everything looks so different.” 17.5–19秒：夜晚城市路口，霓虹招牌、车流和行人交织；她兴奋地对着手机微笑。19–20秒：行走中的近距离自拍，她说：“Alright… let’s see where this takes me.” 随后伸手靠近手机，录制结束。音频仅使用自然现场声：机场环境声、行李轮声、脚步声、飞机与滑行声、列车声、交通声、人群交谈、风声和东京街头噪声；不要音乐。不要字幕、叠加文字、标志、水印、脸部变形、身份漂移、服装或发型变化、重复人物、CGI质感、美颜滤镜、奇幻元素或不可能的地点。画幅16:9。

English prompt

Create a 20-second photorealistic handheld smartphone travel vlog of one adult woman taking her first trip to Tokyo. Use the supplied identity reference image for her face and appearance; preserve her identity, skin tone, hairstyle, body proportions, cream-beige cropped trench coat, ivory knit top, dark charcoal wide-leg trousers, white sneakers, black crossbody bag, silver watch, natural makeup, and suitcase consistently in every shot. Keep authentic phone footage with subtle hand shake, autofocus breathing, exposure shifts, natural motion blur, and realistic colors; avoid a commercial or cinematic look. 0–3s: In a bright airport terminal, she pulls her suitcase, then briefly turns the phone toward herself and says, “Okay… this is actually happening.” 3–6s: She walks through the departure hall while casually filming the architecture and flight information screens. 6–9s: Seated beside an airplane window, she shows the wing above glowing clouds and says, “I can’t believe I’m going to Tokyo.” 9–12s: During landing and taxiing, she films the airport activity outside the window and holds up her phone. 12–15s: She exits the airport with her suitcase near bicycles, vending machines, and a train line. 15–17.5s: A quiet Tokyo neighborhood street with cafés and storefronts; she walks past and says, “Everything looks so different.” 17.5–19s: Evening city crossing with bright signs, traffic, and pedestrians; she smiles excitedly into the phone. 19–20s: Close walking selfie: “Alright… let’s see where this takes me,” then she reaches toward the phone and the recording ends. Audio is only natural diegetic sound: airport ambience, suitcase wheels, footsteps, airplane and taxiing sounds, train, traffic, conversations, wind, and Tokyo street noise; no music. No subtitles, overlays, logos, watermarks, face distortion, identity drift, outfit or hairstyle changes, duplicate people, CGI appearance, beauty filter, fantasy elements, or impossible locations. Aspect ratio 16:9.

Topics and styles

View API model

Explore more AI image and video prompts · Try image generation · Try video generation · Create on the AI canvas