← Back to prompt library

GPT Image 2 · Image

Insert Reference Person Into Shibuya Scene

Imported YouMind GPT Image 2 commerce prompt matched by "服装".

@jaizard服装English2026-06-22
Insert Reference Person Into Shibuya Scene
842Views
36Likes
14Copies
ImageFormat

Generation prompt

以 REFERENCE_1 作为基础场景,将 REFERENCE_0 中的女性自然地插入到涩谷十字路口繁忙的人群中,使其成为一名照片级逼真的路人。匹配 REFERENCE_1 的光影、透视、镜头感、比例及街拍真实感,并保持其服装、包袋和整体外观与 REFERENCE_0 一致。将她放置在前景偏左的位置,置身于行人之中,身体微向左侧,姿态自然放松,仿佛她原本就在那里拍摄的一样。通过逼真的阴影、色彩匹配、边缘融合以及部分人群遮挡处理,使她与环境完美融合,避免产生“抠图感”。保留 REFERENCE_1 中现有的城市背景、标志牌及人群构图。

AutoAGC workflow

Turn it into a reusable workflow

  1. Copy the prompt text and keep the role, task, model, style, and output constraints.
  2. Paste it into GPT Image 2 or a comparable model with your reference material or workflow brief.
  3. Replace the final constraints for output format, brand voice, language, and execution objective.

Asset

Resource preview

Insert Reference Person Into Shibuya Scene
Asset type
Image
Model
GPT Image 2
Scene
服装

More prompts

More GPT Image 2 system prompts

Browse workflows

All Image workflow scenes