284 hand-tested AI prompts across image, video, and music — each with full context, variables, and a sample output. Content is authored in Traditional Chinese; the UI here is English.
GPT Image 2 最被低估的能力是做資訊圖表。中文字符渲染比 Midjourney 穩 10 倍,直接給數據+結構,跑出能放到年報 / 簡報 / LinkedIn 的 infographic。