东京旅行 13 格视频封面
720 × 922 · 由 GPT Image 2 生成

场景与叙事GPT Image 2英文提示词

东京旅行 13 格视频封面

  • UI
  • 海报
  • 写实
  • 科技
  • 电商
  • 旅行

完整提示词

Generate image of young female travel vlogger exploring Tokyo across multiple candid moments, extremely beautiful with long dark wavy hair, wearing stylish Japanese-inspired oversized streetwear, expressive and spontaneous personality, captured across a 13-frame grid collage (Row 1: 4 frames | Row 2: 5 frames | Row 3: 4 frames), each frame feels like a real casual phone capture with imperfect framing and natural inconsistencies.

Frame Breakdown

Row 1 - Frame 1 (Tokyo Tower): low angle selfie with Tokyo Tower behind her, slightly tilted horizon, sky overexposed to near white, she's mid-natural smile adjusting into frame, small lens smudge in corner, candid arrival energy.
Row 1 - Frame 2 (Shibuya street level): walking through Shibuya crossing at night, handheld motion blur, she glances back at camera mid-step, neon reflections on wet pavement, slightly shaky framing, imperfect crop.
Row 1 - Frame 3 (Convenience store): inside a brightly lit convenience store, she is holding onigiri close to camera, playful raised eyebrows, harsh fluorescent lighting flattening the scene, slight overexposure on whites, shelves softly blurred behind.
Row 1 - Frame 4 (Yoyogi park): sitting on a bench under trees, looking away from camera, quiet candid moment, soft dappled daylight, slight focus miss on eyes, subtle lens smudge bottom corner.
Row 2 - Frame 5 (Takoyaki reaction): close-up while eating single takoyaki, reacting mid-bite with laughter, slight motion blur, warm lantern light behind, face slightly out of focus due to movement.
Row 2 - Frame 6 (Vending machine night): standing in front of glowing vending machine, blue and pink light casting uneven tones on her face, pressing button casually, high ISO grain visible.
Row 2 - Frame 7 (Train reflection): her face reflected in train window at night, city lights streaking behind, layered reflection effect, slight ghosting on glass, she looks away from camera.
Row 2 - Frame 8 (Torii gate): low angle shot of her walking through a torii gate, captured from slightly behind, motion blur in her movement, bright sky causing mild lens flare.
Row 2 - Frame 9 (Digital art exhibit): inside immersive light exhibit, colored lights (blue, violet, gold) washing across her face, she looks upward in awe, slight motion blur, low-light noise visible.
Row 3 - Frame 10 (Gundam statue): low angle wide shot, she stands small in frame while large statue towers above, slight barrel distortion from phone lens, sky slightly blown out.
Row 3 - Frame 11 (Lantern alley): walking through narrow alley lit by warm lanterns, shot from behind, she glances back briefly, underexposed shadows, grainy night detail.
Row 3 - Frame 12 (Rooftop skyline): selfie with Tokyo skyline behind, arm extended, wind blowing hair partially across lens, horizon slightly tilted, warm city glow overexposed in distance.
Row 3 - Frame 13 (Nara park): crouching down in a park in Nara, she holds out a deer cracker toward a deer, the deer bows its head toward her, she bursts into genuine laughter mid-reaction, surprised and slightly leaning back, another deer nudges her from behind causing her to lose balance slightly, camera captures the moment imperfectly with slight shake and off-center framing, soft natural daylight, open park background with trees and space, unscripted chaotic energy, candid expression.

Young female travel vlogger exploring Tokyo across 13 candid moments in a grid collage, extremely beautiful with long dark wavy hair, wearing stylish Japanese streetwear, expressive and spontaneous, scenes include Tokyo Tower selfie, Shibuya crossing at night, convenience store snack moment, park bench quiet scene, takoyaki reaction, vending machine glow, train window reflection, torii gate walk, immersive light exhibit, Gundam statue low angle, lantern alley walk, rooftop skyline selfie, Harajuku street ending, each frame slightly imperfect with motion blur.

看懂这条提示词

点点逐段翻译

生成一张东京旅行 vlog 封面:13 格拼图,每格是旅行博主在东京不同地点的随手抓拍,故意带点模糊和不完美。

逐段在说什么

  1. 1
    Generate image of young female travel vlogger…

    总体:年轻女旅行博主在东京的 13 个随手瞬间,排成三行(4 / 5 / 4 格),每格都像手机随拍,构图不完美。

  2. 2
    Row 1 (Frame 1–4)

    第一行:东京塔前自拍、涩谷十字路口夜景回头、便利店举着饭团、代代木公园长椅上发呆。

  3. 3
    Row 2 (Frame 5–9)

    第二行:吃章鱼烧大笑、自动售货机的彩光、电车玻璃里的倒影、穿过鸟居、沉浸式灯光展。

  4. 4
    Row 3 (Frame 10–13)

    第三行:巨大高达像下的广角、灯笼小巷回头、天台天际线自拍、奈良公园喂鹿被顶得差点摔倒。

  5. 5
    最后一段总结

    把整体要求重复一遍:漂亮的深色长卷发、日系街头穿搭、表情自然,每格都有轻微动态模糊。

可以替换的部分

  • Tokyo 及 13 个地点换城市就要把每一格的地点和动作一起换,比如成都:宽窄巷子、熊猫基地、火锅、太古里……

小贴士想用自己的照片,在开头加 based on the person in the uploaded photo。格子越多越容易出错,第一次可以改成 3×3 九格。

来源

收录自
Awesome GPT Image 2MIT 协议

提示词与效果图版权归原作者所有,本站仅作学习参考;标题、分类与变量说明由灵点AI 翻译整理。如需调整署名或删除,请邮件 seadxiao@gmail.com。