霸榜蘋果應用榜的ChatGPT，終于被真·超越了！

Nano Banana掀起破圈熱潮之后，谷歌Gemini登頂成新王。

并且不止美區，包括在印度、加拿大、摩洛哥等地，Gemini全部實現登頂。

而一切的一切都要歸功于：Nano Banana太好用（而且免費）。

正如此前“吉卜力玩法”帶動ChatGPT用戶增長一樣，谷歌8月推出的圖像生成工具Nano Banana目前也被外界認為是驅動Gemini此輪爆發的最關鍵因素。

短短不到一個月，Gemini應用程序在此期間新增用戶2300萬，Nano Banana也被用于編輯超過5億張圖片。

甚至DeepMind CEO哈薩比斯也在最新采訪中表示，Nano Banana是同類產品中最好的。

而像包括Vercel CEO在內的網友們，更是對Nano Banana的作用大力肯定：

所以，迄今為止Nano Banana都有哪些玩法，哪些提示詞效果更佳？

是時候全面總結、盤點一下了~

玩法提示詞大盤點

先來康康一些網友們用Nano Banana搞出的腦洞大開（邪修玩法）

玩法一：一張照片百變風格。

想必大家最近的社媒都被Nano Banana美式證件照刷屏了，不會吧不會吧，屏幕前的你還沒有跟上這波潮流？提示詞在此，速來～

Prompt：Transform the uploaded portrait into a business-style headshot in the American aesthetic, while keeping the original subject completely unchanged in appearance. Facial features and identity should be clearly preserved. The image should feature a half-body composition, set against a blue textured studio background with soft, natural indoor lighting to bring out realistic skin tones and a subtle sense of depth. The subject is dressed in a blue shirt and a black blazer, styled in a minimalist and elegant manner that reflects a modern and professional look, and accessorized with gold hoop earrings. Her expression should appear relaxed and natural, with bright, expressive eyes and a sincere, confident smile. The overall image should be clean, refined, and convey a trustworthy, professional impression.

次元壁什么的，在Nano Banana面前都得認輸，2D人物化身漫展Coser，這還原度真香！

Prompt：The background is removed and the person is transformed into a cosplayer. The cosplayer is standing in the center of a bustling comic convention event. (The comic convention event is lively and crowded.) Lighting: The cosplayer is perfectly lit. Camera: Photographed with a 50mm camera. Angle: A portrait shot captured the entire body. Cosplayer: A beautiful young Japanese cosplayer. —ar 3:4.

也可以搞點真·破碎感肖像照，成為朋友圈里的憂郁美男子（bushi）

Prompt：close-up image capturing a fragmented portrait of a [SUBJECT] through [4 or 5] irregularly shaped glass shards scattered on a textured off-white background. Each shard reveals intricate details with light reflections, while jagged glass edges with a slight green hue emphasize the image’s disjointed, fragmented composition. The shards are arranged to suggest a cohesive subject without fully revealing it.

呼叫俺的星露谷老鄉們！快來一起手搓像素風形象。

Prompt：reimagine me as a 16-Bit Video Game character and put me in a 2D 16-bit platform video game.

手中物品改成3D的透明線條全息圖，谷歌手機Pixel 9999系列我先用為敬。

Prompt：Turn the object I am holding into a 3d transparent line art hologram.

玩法二：精準匹配素描圖里的姿勢。

保持原始圖像背景不變，讓武士跟隨我的素描圖做好戰斗準備姿勢。

Prompt：Recreate the wandering samurai from the reference img1, with long black hair, unkempt beard,and a tattered kimono, holding a single katana.Change his posture to match the dynamic combat pose from the second sketch reference img2 (Both must go with the @ in front) low stance, torso leaning forward, one knee bent, the other leg extended, arms gripping the katana with correct anatomy, blade angled diagonally across the body.Keep the Edo-period rural Japanese village backdrop, muted earthy tones, dramatic overcast lighting, painterly cinematic realism. His kimono should flow naturally with the motion, shadows and foreshortening consistent. No standing pose, no plain background.

啥？你說你只會畫簡筆畫，滿足，統統滿足。

Prompt：Make the character from Image 2 perform the exact same pose as the stick figure in Image 1. Keep the same cinematic background from Image 2.

玩法三：搞個模型玩玩。

Nano Banana手辦玩法已經司空見慣了？莫慌，這里還有一堆加強版，最新趨勢咱也要趕上。

先來看個桌面原版：

Prompt：Create a 1/7 scale commercialized figurine of the characters in the picture, in a realistic style, in a real environment. The figurine is placed on a computer desk. The figurine has a round transparent acrylic base, with no text on the base. The content on the computer screen is a 3D modeling process of this figurine. Next to the computer screen is a toy packaging box, designed in a style reminiscent of high-quality collectible figures, printed with original artwork. The packaging features two-dimensional flat illustrations.

下面咱上上難度，來一個漂流瓶Plus版。

Prompt：A 1/7 scale commercialized collectible figure of the character from the photo, crafted in a highly realistic style. The figure is placed in a detailed beach environment with sand, seashells, and gentle ocean waves. The entire toy display is enclosed inside a clear souvenir glass bottle, giving it a premium miniature diorama look, with realistic lighting and shadows.

又或者邪惡版？（哈利波特叛變加入伏地魔陣營？？）

Prompt：Premium 3D product render of a chibi skeleton-style [CHARACTER] on a round pedestal, holding [ACCESSORY], beside a matte-black package box. Print ‘[TEXT]’ big on the box. Dark studio background, soft rim light, cinematic shadows, realistic materials (leather/fur/metal), subtle X-ray vibe: skull face + visible limb bones but still recognizable. Ultra-detailed, crisp focus, product photography, depth of field, aspect ratio 3:4.

類似的，還可以制作星爸爸、麥當當的微縮景觀模型。

Prompt：Tiny diorama shop for [BRAND]. Roof made of oversized [PRODUCT], big [BRAND] logo sign above the window, vendor handing a [PRODUCT] to a customer, ground covered with many [PRODUCT]. Hand-made polymer-clay look, studio macro photo, soft light, shallow depth of field, vertical 3:4.

小模型OK，城市大模型上Nano Banana也是手到擒來。

Prompt：Create a giant hyper-realistic statue based on the given photo, keeping the original face exactly the same without changes. The statue stands tall in the middle of a roundabout in Dhaka, near a famous historical landmark. The statue is still under construction, surrounded by scaffolding, with many construction workers in yellow helmets and orange vests climbing, welding, and working on it. Parts of the statue’s body are still exposed metal framework, while other sections are already detailed and finished. The background shows the realistic atmosphere of VARANASI CITY: crowded streets with colorful rickshaws, packed buses, and small cars circling the roundabout. Street vendors with tea stalls, fruit carts, and colorful umbrellas line the roadside. Shop signs, big billboards, and messy hanging electric wires crisscross above the streets, creating the typical Dhaka city vibe. The bright daytime sky shines above, with tropical trees and a bustling, lively atmosphere. Style: photorealistic, vibrant, and full of life.

玩法四：局部元素對比修改。

比如說試穿新衣服，用到的正是Nano Banana的高級組合功能，可以將不同圖像里的元素組合在一起，新衣服秒上身，麻麻再也不用擔心我會亂買衣服啦～

Prompt：Create a new image by combining the elements from the provided images. Take the [element from image 1] and place it with/on the [element from image 2]. The final image should be a [description of the final scene].

裝修糾結癥犯了，也能讓Nano Banana幫忙保留整體風格，只調換其中一個家具元素。

Prompt：Using the provided image, change only the [specific element] to [new element/description]. Keep everything else in the image exactly the same, preserving the original style, lighting, and composition.

玩法五：歡迎來到虛擬世界。

各種虛擬場景生成也不在話下，比如說兩只怪物battle的格斗游戲。

Prompt：Create a mid motion action scene where both subject are in focus with a Three-Quarter Angle in martial arts fighting stances. They are in the same cinematic scene. Remove the line down the centre with a blurred crumbling ruins in a purple alien world in the background. The scene is shot at sunrise. Modern Fighting game health bars MORDON V’s DEATH SEED. power move. Hud style screen effects. Add a thumbnail of each character to the health bars. Lense flares.

或者撕開現實的幕布，想象無限～

Prompt：A photorealistic image of a torn piece of paper revealing [INSIDE VIEW]. The torn paper is vertically oriented, with the edges rough and uneven, as if ripped by hand. The contrast between the textured white paper and the detailed landscape creates a striking visual effect, capturing a feeling of discovery and wonder.

咳咳，那最后再來康康谷歌官方補充的六大類提示詞（一本正經版）。

玩法六：玩轉真實攝影。

Nano Banana就是你手中舉起的AI相機，只需在提示詞中，精心加入相機角度、鏡頭類型、光線照明，再打磨億點點細節，一張超逼真的AI照片隨即誕生。

Be like下面這張人像攝影，面部的皺紋輪廓清晰可見。

Prompt：A photorealistic close-up portrait of an elderly Japanese ceramicist with deep, sun-etched wrinkles and a warm, knowing smile. He is carefully inspecting a freshly glazed tea bowl. The setting is his rustic, sun-drenched workshop. The scene is illuminated by soft, golden hour light streaming through a window, highlighting the fine texture of the clay. Captured with an 85mm portrait lens, resulting in a soft, blurred background (bokeh). The overall mood is serene and masterful. Vertical portrait orientation.

玩法七：制作風格化貼紙。

要讓Nano Banana協助設計，需要明確好所有細節，也就是成為一個合格的甲方（bushi），包括貼紙風格、關鍵特征和色彩選擇等等。

嗯，感覺下面這張小熊貓的貼紙，可以直接產出物料了捏～

Prompt：A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It’s munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.

玩法八：制作一個品牌logo。

據官方透露，Gemini相當擅長渲染文本，所以拿來搞logo設計再合適不過，當然同樣需要描述清楚自己想要嵌入的文本以及字體。

比如說下面這張咖啡館logo，咖啡豆的巧妙設計可不是Nano Banana自己琢磨出來的，還得靠人類聰明的小腦瓜下達指令。

Prompt：Create a modern, minimalist logo for a coffee shop called ‘The Daily Grind’. The text should be in a clean, bold, sans-serif font. The design should feature a simple, stylized icon of a coffee bean seamlessly integrated with the text. The color scheme is black and white.

玩法九：拍攝專業的產品照片。

產品拍攝和一般的真實拍攝還是有所不同的，作為品牌宣傳照，要讓Nano Banana選擇性突出產品特性，同時場景也必須服務產品，除了選擇相機參數，產品的細節也要在提示詞中充分表達。

例如官方生成的這張產品照中，就在提示詞中加入了具體的材質描述：拋光混凝土表面上的極簡主義啞光黑色陶瓷咖啡杯。

Prompt：A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface. The lighting is a three-point softbox setup designed to create soft, diffused highlights and eliminate harsh shadows. The camera angle is a slightly elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with sharp focus on the steam rising from the coffee. Square image.

玩法十：極簡背景設計。

像網站、PPT這些，背景要求普遍都是極簡、干凈，所以在用Nano Banana生成時，可以提出需要一塊大面積空曠畫布。

例如生成該PPT背景模板時，大面積留白也為后續用戶自己填充文字保留了足夠的嵌入空間。

Prompt：A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas, creating significant negative space for text. Soft, diffused lighting from the top left. Square image.

玩法十一：成為一個漫畫家。

Nano Banana讓人人都能成為漫畫家，而你只需要講出你的故事，編劇是你，作畫是它。

舉個栗子，在某個雨夜，小鎮里突然來了一位神秘的偵探……

Prompt：A single comic book panel in a gritty, noir art style with high-contrast black and white inks. In the foreground, a detective in a trench coat stands under a flickering streetlamp, rain soaking his shoulders. In the background, the neon sign of a desolate bar reflects in a puddle. A caption box at the top reads “The city was a tough place to keep secrets.” The lighting is harsh, creating a dramatic, somber mood. Landscape.

谷歌終于迎來“App Store時刻”

有一說一，從被ChatGPT壓著打開始，谷歌這回也算是憑借Nano banana真正逆襲了。

兩家的恩怨情仇幾乎可以追溯到OpenAI的創辦……

馬斯克（屬于最早創辦OpenAI的一批人）在去年的一場公開采訪中透露，其實成立OpenAI就是想在一定程度上對抗谷歌：

這在很大程度上是一個單極世界，谷歌在AI領域完全占據主導地位。

就是說，兩家的對抗屬于基因里自帶那種。而后來，OpenAI果然憑借ChatGPT奪得所有目光，使得包括谷歌在內的所有玩家幾乎都處在ChatGPT陰影之下。

在很長的一段時間里，谷歌幾乎一直處于追趕的位置，而且過程中不乏各種“翻車”。

比如當ChatGPT迅速成為全民級應用后，谷歌匆忙推出的Bard一度被吐槽體驗遠遜ChatGPT。

甚至推出的AI摘要、AI生圖等工具，也因內容錯誤、侵犯隱私肖像等問題引發廣泛爭議。

但是，隨著谷歌不斷推出新的Gemini系列，局面終于開始反轉。

一方面，技術上谷歌逐步補齊短板。Gemini 1.5將上下文長度直接拉到百萬量級，Gemini 2.0更是被外界評價為“全面對標甚至部分超越GPT-4”，Gemini 2.5 Pro在代碼、推理等能力上更是斬獲一眾好評。

另一方面，更重要的或許還在于谷歌打出了生態牌。Gemini不再是一個孤立的模型，而是被嵌入搜索、Chrome瀏覽器、YouTube、Gmail、Docs等核心應用，覆蓋全球數十億用戶。

結果就是，從一度“被迫補課”，到如今App Store排行榜反超ChatGPT，谷歌迎來了真正意義上的“逆襲時刻”。

大部分網友的反應be like：

實至名歸，繼續保持。

事實上，每一次AI應用登頂App Store，都可以被視為行業的新高峰。

無論是ChatGPT、DeepSeek，還是這一次的Gemini，背后其實都在標注著一個個“App Store時刻”——它不僅僅是榜單數字的勝出，更是某家公司的AI產品影響力、用戶接受度和市場格局變化的集中體現。

也正因此，我們也能理解為什么馬斯克之前會指控蘋果控制應用排名這件事。

就在上個月，馬斯克向OpenAI和蘋果公司正式提起反壟斷訴訟，指控蘋果在Apple Store里操縱應用排名榜單，偏袒OpenAI和ChatGPT，同時打壓馬斯克自家的Grok。

當時網友們發現，不僅打開蘋果商店鋪天蓋地都是ChatGPT的廣告，而且多個榜單下ChatGPT也是名列前茅，而其它生成式AI應用的身影則寥寥無幾。

不過現在嘛，谷歌Gemini的登頂則被網友們調侃為：

可以作為打破蘋果操控應用市場的證據之一（手動狗頭）。