Google AI Gemini日前推出全新的「Nano Banana （Gemini 2.5 Flash Image ）」圖像編輯模型，可以讓人物或物件變換造型，但「樣貌始終如一」引來不少網友驚豔，現在更有人拿來做3D公仔 ，整體更為逼真因而爆紅，聲勢似乎壓過OpenAI的ChatGPT ，聯合新聞網《科技玩家》現在就帶你一起來做3D公仔，用1張圖片和Gemini公仔指令 就能完成！

教你用Gemini做3D公仔

1.進入Gemini網頁版或APP後，切換成Gemini 2.5 Flash Image模型。

★Gemini網頁版：點我進入

2.上傳想要製作3D公仔的照片，建議全身照才會比較清楚。

3.輸入以下指令後按下生成 。

「A hyper-realistic 1/7 scale figurine of a character, designed as a finished commercial product, placed on an iMac computer desk with a white Apple keyboard. The figurine stands on a clean, round transparent acrylic base with no labels or text. Professional studio lighting highlights the sculpted details. On the iMac screen in the background, display the ongoing ZBrush modeling process of the same figurine, showing the contrast between "work in progress" and the finished product. Next to the figurine, place its packaging box with rounded corners and a transparent front window. The box is open at the top, revealing only the inner transparent plastic clamshell, and its height is slightly taller than the figure, realistically sized to contain it.」

4.登登～來看看成果，包含貓咪、柴犬等寵物、人物都能清楚呈現。

整體來說，「Nano Banana（Gemini 2.5 Flash Image）」所生成的模樣相當逼真，在生成過程當中，也可看到Gemini提示可「要求Gemini修改圖片」，並稱「Gemini就是你想像力的延伸，沒有生成不了的圖片！如果生成結果與你的預期有差距，請試著在提示詞加入更多細節。提示詞越詳細，Gemini越能生成符合你想像的圖片。」讀者也能微調讓照片更有趣。