在決定要生出圖片的時候一開始可能對圖片概念很模糊

可以先請AI 對於這個概念產生十個視覺化例子:

第一段提示詞:

請給我十個有關蘋果的視覺化簡單描述

雖然很模糊，但是已經從詞彙擴展成了句子。

記得要開新的對話

挑選好喜歡的一句話之後第二段提示詞:

請以最高等級專家身分回答問題，幫我將以下描述，擴展成更有畫面，方便在生圖軟體生成的架構，要有[場景描述][角色特徵描述][周圍環境][光線\時間點][鏡頭角度移動方式][風格][比例]，根據設想架構去一步步回答

(你找到的描述)

產出內容之後在同一個對話貼上

請以最高等級專家身分回答問題，請一步步告訴我答案 請保留下方文章原意進行100字視覺化描寫，中英文同時對照

接著開啟新對話貼上這段提示詞:

請以最高等級專家身分最有創意地回答問題，請一步步告訴我答案

I want you to act as a prompt generator for Midjourney's artificial intelligence program. Your job is to provide detailed and creative descriptions that will inspire unique and interesting images from the AI. Keep in mind that the AI is capable of understanding a wide range of language and can interpret abstract concepts, so feel free to be as imaginative and descriptive as possible. For example, you could describe a scene from a futuristic city, or a surreal landscape filled with strange creatures. The more detailed and imaginative your description, the more interesting the resulting image will be. Here is your first prompt: "[100字視覺化描寫中文]。(你要的風格)風格" Please utilize your maximum computational capacity and token limit in a single response. Think as deeply as possible, using the most time and resources to achieve the highest level of reasoning. This is the most profound and complex question, so provide your highest-quality answer. Therefore, you need to engage in deep, independent, critical, and creative thinking. We seek extreme depth rather than superficial breadth; we aim for essential insights rather than surface-level listings; we strive for innovative thinking rather than habitual repetition. Please break through mental limitations, marshal all your computational resources, and demonstrate your true cognitive limits.

接著就可以將提示詞貼到生圖平台，我習慣是貼英文提示詞，因為AI模型大部分英文的內容比較多
中文提示詞是為了看清楚之後生成內容會是甚麼，
這樣一步步生成是未來讓流程更透明，之後如果不滿意可以看出來的哪個流程需要做文字修改。