GPT Image 2AIプロンプト
Reference-Based Character Portrait: Taiwan MRT Scene Prompt
Easily place your character into a Taiwan MRT scene while keeping their look consistent with this AI prompt.
プロンプト · EN
在 arglocation: 台湾捷运车厢 内，一位年轻女性坐在靠近车门的座位上。她的外貌和服饰必须参考上传照片中的女性（包括面部特征、气质、发型和穿搭风格；服装必须与照片完全一致）。她正低头专注于手机，神情自然，没有看向镜头。角色位于画面的右侧三分之一处，左侧有模糊的前景遮挡。
このプロンプトについて
Easily place your character into a Taiwan MRT scene while keeping their look consistent with this AI prompt. Use it as a コンセプトアート starting point for GPT Image 2: keep the visual structure and style constraints intact, then swap in your own subject, brand, or scene.
Start by replacing location, then keep the camera, composition, and material cues in the same order. This makes the output easier to compare across variations.
このプロンプトの使い方
- Copy the prompt text from this page.
- Upload your reference image to a compatible AI model (e.g., Midjourney with
--cref, Stable Diffusion with IP-Adapter). - Optionally, modify the
locationargument to change the scene (default: Taiwan MRT carriage). - Paste the prompt and generate your image.
- Adjust reference strength (e.g.,
--cwin Midjourney) to fine-tune identity consistency.
