Masterpiece, best quality, historical photo, large format film photography (8×10 analog plate), The Beatles performing their famous rooftop concert in London, 1969.
Location: The rooftop of Apple Corps building, Savile Row, London.
Background: Overcast grey London sky, cold winter day, blurry London chimneys and brick rooftops in the distance.
Vibe: Raw, candid, documentary style, wind blowing their hair and coats.
Camera: Shot on a Linhof large format camera, Kodak Portra 400 film stock.
Quality: Incredible detail in fabric textures (fur, wool), realistic film grain, soft natural overcast lighting, depth of field slightly blurring the background buildings.
A bottle of Bombay Sapphire Gin submerged in crystal clear water, caustic light patterns dancing across surface, underwater photography, pristine clarity, suspended weightlessness, aquatic elegance, high-speed capture, refreshing aesthetic. Add the relevant brand logo and slogan for marketing use.
This high-resolution bird’s-eye view photograph was taken with a LOMO Ic-a. The ground is covered with countless black and white billboard advertisements of the actress Shuqi, and standing on top of the advertisements is the characters from the reference picture.
Google DeepMind 開發者推廣大師維納德（Guillaume Vernade）在社群平台X上，發布了該模型的完整指南，強調 Nano-Banana Pro 已從上一代好玩性質的圖像生成，躍升為具備功能性的專業資產生產工具，適用於多種實用情境，從財報視覺統整、電影分鏡、房屋裝修等都能夠自己DIY。
動手前，先懂4個提示詞的黃金法則
Nano-Banana Pro 是思考型模型，能理解意圖與物理規則，維納德認為， 要達到最好的產圖效果，必須捨棄傳統零碎的關鍵字堆疊（Tag Soups），像是只寫狗、公園、4K、真實感等關鍵字，而是以創意總監的思維下達清晰、具體且帶有上下文的指令 。
Generate a clean, modern infographic summarizing the key financial highlights from this earnings report. Include charts for ‘Revenue Growth’ and ‘Net Income’, and highlight the CEO’s key quote in a stylized pull-quote box.
Make a retro, 1950s-style infographic about the history of the American diner. Include distinct sections for ‘The Food,’ ‘The Jukebox,’ and ‘The Decor.’ Ensure all text is legible and stylized to match the period.
Create an orthographic blueprint that describes this building in plan, elevation, and section. Label the ‘North Elevation’ and ‘Main Entrance’ clearly in technical architectural font. Format 16:9.
Summarize the concept of ‘Transformer Neural Network Architecture’ as a hand-drawn whiteboard diagram suitable for a university lecture. Use different colored markers for the Encoder and Decoder blocks, and include legible labels for ‘Self-Attention’ and ‘Feed Forward’.
The “Viral Thumbnail” (Identity + Text + Graphics):Design a viral video thumbnail using the person from Image 1. Face Consistency: Keep the person’s facial features exactly the same as Image 1, but change their expression to look excited and surprised. Action: Pose the person on the left side, pointing their finger towards the right side of the frame. Subject: On the right side, place a high-quality image of a delicious avocado toast. Graphics: Add a bold yellow arrow connecting the person’s finger to the toast. Text: Overlay massive, pop-style text in the middle: ‘3分钟搞定!’ (Done in 3 mins!). Use a thick white outline and drop shadow. Background: A blurred, bright kitchen background. High saturation and contrast.
Create a funny 10-part story with these 3 fluffy friends going on a tropical vacation. The story is thrilling throughout with emotional highs and lows and ends in a happy moment. Keep the attire and identity consistent for all 3 characters, but their expressions and angles should vary throughout all 10 images. Make sure to only have one of each character in each image.
Create 9 stunning fashion shots as if they’re from an award-winning fashion editorial. Use this reference as the brand style but add nuance and variety to the range so they convey a professional design touch. Please generate nine images, one at a time.
Remove the tourists from the background of this photo and fill the space with logical textures (cobblestones and storefronts) that match the surrounding environment.
移除背景中的遊客，並用符合周圍環境的邏輯紋理（鵝卵石和店面）填補空白。
在物件移除方面，複雜的人群也可以刪除乾淨。
圖／ 數位時代製圖
▶ 漫畫上色（須先上傳黑白漫畫）
官方提示詞範例（英）
官方提示詞範例（中）
Colorize this manga panel. Use a vibrant anime style palette. Ensure the lighting effects on the energy beams are glowing neon blue and the character’s outfit is consistent with their official colors.
Take this concept and localize it to a Tokyo setting, including translating the tagline into Japanese. Change the background to a bustling Shibuya street at night.
以此照片概念為基礎，將其在地化為東京場景，包括將標語翻譯成日文。將背景改為夜晚繁忙的涉谷街頭。
圖／ Google AI Studio
▶ 季節與光影控制（須先上傳參考照片）
官方提示詞範例（英）
官方提示詞範例（中）
Turn this scene into winter time. Keep the house architecture exactly the same, but add snow to the roof and yard, and change the lighting to a cold, overcast afternoon.
2D 轉 3D： 上傳平面配置圖，指令生成擬真的 3D 室內設計簡報板。 3D 轉 2D： 將 3D 渲染圖轉換為像素藝術 (Pixel Art) 或技術線稿。
▶ 2D 平面圖轉 3D 室內設計（須先上傳2D 平面圖）
官方提示詞範例（英）
官方提示詞範例（中）
Based on the uploaded 2D floor plan, generate a professional interior design presentation board in a single image. Layout: A collage with one large main image at the top (wide-angle perspective of the living area), and three smaller images below (Master Bedroom, Home Office, and a 3D top-down floor plan). Style: Apply a Modern Minimalist style with warm oak wood flooring and off-white walls across ALL images. Quality: Photorealistic rendering, soft natural lighting.
根據上傳的 2D 平面圖，生成一張專業的室內設計提案板。版面配置：拼貼形式，上方為一張大的主圖（起居區的廣角透視），下方為三張小圖（主臥室、家庭辦公室和 3D 俯視平面圖）。風格：在所有圖片中套用現代極簡風格，搭配溫暖的橡木地板和米白色牆面。品質：照片級渲染，柔和的自然光。
圖／ 數位時代製圖
▶ 2D 轉 3D 迷因
官方提示詞範例（英）
官方提示詞範例（中）
Turn the ‘This is Fine’ dog meme into a photorealistic 3D render. Keep the composition identical but make the dog look like a plush toy and the fire look like realistic flames.
將「This is Fine」狗狗迷因圖轉變為照片級真實的 3D 渲染圖。保持構圖完全相同，但讓狗狗看起來像毛絨玩具，火看起來像真實的火焰。
Harness native high-fidelity output to craft a breathtaking, atmospheric environment of a mossy forest floor. Command complex lighting effects and delicate textures, ensuring every strand of moss and beam of light is rendered in pixel-perfect resolution suitable for a 4K wallpaper.
Create a hyper-realistic infographic of a gourmet cheeseburger, deconstructed to show the texture of the toasted brioche bun, the seared crust of the patty, and the glistening melt of the cheese. Label each layer with its flavor profile.
Solve log_{x^2+1}(x^4-1)=2 in C on a white board. Show the steps clearly.
在白板上解出 log_{x^2+1}(x^4-1)=2$ in $C$。清楚展示步驟。
圖／ 數位時代製圖
▶ 視覺推理
官方提示詞範例（英）
官方提示詞範例（中）
Analyze this image of a room and generate a ‘before’ image that shows what the room might have looked like during construction, showing the framing and unfinished drywall.
Create an addictively intriguing 9-part story with 9 images featuring a woman and man in an award-winning luxury luggage commercial. The story should have emotional highs and lows, ending on an elegant shot of the woman with the logo. The identity of the woman and man and their attire must stay consistent throughout but they can and should be seen from different angles and distances. Please generate images one at a time. Make sure every image is in a 16:9 landscape format.
創作一個包含 9 張圖片、令人著迷的 9 部曲故事，主角是一男一女，拍攝一支獲獎的豪華行李箱廣告。故事應有情緒起伏，並以女性與 Logo 的優雅鏡頭作結。男女主角的身分和服裝必須全程保持一致，但應從不同角度和距離拍攝。請逐一生成圖片。確保每張圖片皆為 16:9 橫向格式。
Create a ad for a [product] following this sketch.
依照此草圖，為 [產品名稱] 製作一則廣告。
圖／ Google AI Studio X
▶ 線框圖轉 UI（須先上傳手繪草圖）
官方提示詞範例（英）
官方提示詞範例（中）
Create a mock-up for a [product] following these guidelines.
依照這些準則，為 [產品名稱] 製作模型圖 (Mock-up)。
圖／ Google AI Studio X
▶ 像素藝術與網格（須先上傳 64×64 網格圖片）
官方提示詞範例（英）
官方提示詞範例（中）
Generate a pixel art sprite of a unicorn that fits perfectly into this 64×64 grid image. Use high contrast colors.(Tip: Developers can then programmatically extract the center color of each cell to drive a connected 64×64 LED matrix display).
Sprite sheet of a woman doing a backflip on a drone, 3×3 grid, sequence, frame by frame animation, square aspect ratio. Follow the structure of the attached reference image exactly.
import torch
from diffusers import OvisImagePipeline
# 加载模型 (建议使用 bfloat16 以节省显存)
pipe = OvisImagePipeline.from_pretrained("AIDC-AI/Ovis-Image-7B", torch_dtype=torch.bfloat16)
pipe.to("cuda")
# 提示词示例：生成一个带有 "OVIS" 文字的 3D 艺术字
prompt = "A creative 3D artistic render where the text 'OVIS' is written in a bold style..."
image = pipe(prompt, num_inference_steps=50, guidance_scale=5.0).images[0]
image.save("ovis_result.png")
![生成式 AI 新霸主？Black Forest Labs 重磅发布 FLUX.2 [klein]：亚秒级出图，仅需 13GB 显存](https://fluxbbs.com/wp-content/uploads/2026/01/2026011903282883.png)
