Character Costume Design Transfer
Deconstructs specific character costumes from an image and applies the design to a new subject model.
适合做图解、清单、路线图和知识长图：先锁定信息层级，再把文字量控制在模型能稳定处理的范围里。
画幅建议
16:9 或 4:3
细节策略
先快速出图，再细节精修
生成流程
先用文字生成定主画面，再一次只改一个重点细节。
完整 GPT Image 2 提示词
English prompt
Deconstruct the character's clothing, generate a costume design diagram, and apply it to an {argument name="ethnicity" default="average East Asian woman"}, {argument name="aspect ratio" default="3:2"}.Original prompt
拆解角色服装，生成服装设计图，并套用在{argument name="人种" default="普通东亚女性"}身上，{argument name="比例" default="3:2"}相关 GPT Image 2 提示词
VR Headset Exploded View Poster
Generates a high-tech exploded view diagram of a VR headset with detailed component callouts and promotional text.
Illustrated City Food Map
Generates a hand-drawn, watercolor-style tourist map featuring numbered local food specialties, landmarks, and a legend.
3D Stone Staircase Evolution Infographic
Transforms a flat evolutionary timeline into a realistic 3D stone staircase infographic with detailed organism renders and structured side panels.
Momotaro Explainer Slide in Hybrid Style
A prompt that combines the simple, warm aesthetic of simple illustration style illustrations with the high-information density characteristic of Japanese government slides.
Faceless Cyberpunk Infiltrator
Generates a cinematic anime scene of an armed faceless woman infiltrating a high-security futuristic server room.
Pancake Angel Cafe Cover
Generates a dreamy watercolor anime cover of a winged cafe angel serving honey pancakes in a sunlit morning cafe.