Sequential Continuity Generation
A prompt sequence for GPT-Image-2 to maintain character consistency across different emotional states and actions.
适合生成网页、App 或仪表盘界面稿：先保留模块结构，再替换成你的业务文案和品牌视觉。
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 Qwen Image 提示词
English prompt
1st image: {argument name="action" default="making a plastic model with a serious expression"}. 2nd image: (after the first) {argument name="failure scene" default="a shot of turning pale after cutting the wrong part"}.Original prompt
1枚目：{argument name="作業内容" default="真剣な表情でガンプラを作るところ"} 2枚目：（1枚目の後に）{argument name="失敗の様子" default="間違った部分を切ってしまい、青ざめるカット"}相关 Qwen Image 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.
E-commerce Live Stream UI Mockup
Generates a realistic social media live stream interface overlaying a portrait, featuring customizable chat messages, gift popups, and a product purchase card.
Knight-Mage Battles Stone Golem
A cinematic fantasy battle scene for generating epic game-style artwork of an armored heroine fighting a giant stone golem in a ruined cathedral.
Censored Elven Adventurers in Medieval Village
Generates a cinematic fantasy scene of two detailed elven adventurers walking through a medieval village with castle backdrop and obscured faces.
Faceless Cyberpunk Infiltrator
Generates a cinematic anime scene of an armed faceless woman infiltrating a high-security futuristic server room.