灵感图库
探索和使用精选的 AI 图像生成模板 (共 6,519 个)
Cinematic Scene of a Man with Roses on a Wet City Street
A prompt to generate a cinematic, moody urban image of a confident man in a black suit and overcoat, wearing sunglasses, standing on a wet city street after the rain, holding a huge bouquet of red roses while talking on the phone.
Melancholic Portrait in Coastal Rain
A detailed prompt for generating a profile portrait of a man with a melancholic expression, wearing a baseball cap and headphones, with heavy dark hair tousled by the coastal wind, emphasizing visible raindrops and a heavily blurred, dark, rainy background.
Hyper-realistic High-Fashion Editorial on a Luxury Yacht
A highly detailed JSON prompt for generating a hyper-realistic, cinematic high-fashion editorial image of a female model seated on a plush bed aboard a luxurious red yacht, holding a large bouquet of red roses, emphasizing skin micro-texture and golden-hour lighting.
Close-up Selfie of a Woman in Leopard Print and Metallic Shirt
A photorealistic prompt for generating a close-up selfie of a young woman with specific facial features and attire, including a leopard print crop top over a shiny silver metallic shirt, focusing on high detail and soft indoor lighting.
Apple Carving Art Prompt
A prompt for Nano Banana Pro requesting an image of an apple carved into a detailed Jiangnan water town scene (pavilions, bridges, flowing water), rendered in a 4K high-definition art museum photography style.
Multilingual Figure Product Introduction Layout Prompt for Nano Banana Pro
A detailed, structured prompt designed to transform a reference image of a character into a photorealistic PVC figure product introduction layout, complete with product information, logos, and close-up views. The prompt supports Japanese, English, German, and French text generation for the product details and requires a reference image of the character.
Social Game Special Move Production Prompt for Nano Banana Pro
A highly detailed, multi-section prompt designed to generate a screen capture of a social game's special move sequence (cut-in, move name, damage display). It strictly requires maintaining the character's original art style from a reference image while inferring dramatic effects, UI, and a random, chuunibyou-style Japanese move name and damage value.
Image-to-Image Workflow for RPG Maker Pixel Maps using Nano Banana
A detailed, multi-step workflow guide for using Nano Banana (specifically Nano Banana 2 or Pro) in image-to-image mode to generate assets like RPG Maker pixel maps or knowledge graphs. It emphasizes using reference images (like RM tiles or game screenshots) to maintain style consistency and provides a sample prompt for generating a dark fantasy RPG map.
Nano Banana Pro Banner Creation Prompt
A simple prompt for Nano Banana Pro used to create a banner image announcing the release of Nano Banana Pro. It specifies a 16:9 aspect ratio, a color scheme (yellow, gray, black), a pop art style, and requires incorporating an attached character image.
Eraser Gun Style Prompt for Nano Banana Pro (Fighting Pose Stage)
A multi-stage prompt designed to generate a character performing an 'Eraser Gun' style energy wave attack, similar to Dragon Ball techniques. This is the first stage prompt, which changes the character's pose to a fighting stance while strictly preserving the original art style from a reference image.
Hyperrealistic Anime Portrait with Split Lighting Prompt
A highly specific, detailed prompt for Nano Banana Pro to generate a hyperrealistic anime portrait of a female character. It mandates a pure black background and uses dramatic, narrow, hard-edged side lighting (split lighting) to create extreme chiaroscuro contrast, emphasizing micro-details only in the illuminated area.
Adding Santa Claus to a Photo using Nano Banana Pro
A prompt designed for Nano Banana Pro or ChatGPT to seamlessly add a realistic Santa Claus figure into an existing photograph of a sleeping child, making it appear as if Santa is quietly delivering presents. This prompt is intended for image manipulation based on an uploaded photo.
Generating a Magazine Cover for Edogawa Ward Tourism
A user tested a prompt asking Nano Banana Pro to generate a magazine cover filled with information to guide tourism in Edogawa Ward, comparing the output with ChatGPT. The prompt is a text-to-image instruction for a specific editorial design.
New Year's Card Illustration with Seven Lucky Gods Costume Swap
A detailed prompt for generating a New Year's card illustration in a cute, mini-character (SD character) style. It requires the AI to take up to seven input characters, randomly assign them the roles and traditional costumes of the Seven Lucky Gods, and fill in any missing characters to complete the set of seven. The final image must include specific calligraphy text, a treasure ship, Mount Fuji, and the first sunrise.
Futuristic New Year Magazine Cover Design Prompt
A highly structured prompt for Nano Banana Pro to generate a high-end, tech-visual magazine cover with a New Year's motif. It specifies a complex layered composition, including a white background with subtle gold leaf, a dynamic anime mascot in a kimono-suit hybrid, and precise typography for the masthead and feature titles, all adhering to a modern Japanese graphic design aesthetic.
Drone Art Character Projection over Night Sea
A prompt for generating a realistic photo of a character's shape being formed in the night sky over the sea by thousands of glowing drones, creating a spectacular, fantastical illumination event captured with a wide-angle lens. It uses a reference image to define the character's features.
Magazine Page Generation for Travel Guide
A simple prompt used to test the ability of Nano Banana Pro to generate a magazine page layout containing information about a specific tourist spot, in this case, the 'Ijinkan' (Foreign Residences) in Kobe.
Figure Product Introduction Layout Prompt (Multilingual)
A Japanese tweet discussing the 'Figure Conversion + Product Introduction Layout Prompt' (Prompt 13 from the festival list) and its multilingual capability (Japanese, English, German, French). The user notes that the prompt allows for the insertion of catchphrases.
Elven Woman with Ornate Chain Dress
A highly detailed photorealistic fantasy art prompt for generating an elven woman. The prompt focuses on intricate details, including full-body tattoos, platinum blonde hair, and an elaborate metallic chain dress made of gold and silver thorny vines that drapes like armor jewelry, emphasizing dramatic cinematic lighting with cool teal tones.
iPhone Flash Aesthetic of Woman in Bowling Alley
A prompt designed to simulate high-contrast, raw mobile phone photography (iPhone Pro Max, Influencer Flash Aesthetic). It captures an athletic woman in a bowling alley, laughing dynamically over the ball return machine, emphasizing intense neon reflections, computational photography effects (Deep Fusion, ProRAW), and digital noise.
Cozy Evening Lifestyle Photography on Sofa
A structured JSON prompt for Gemini 3.0 Nano Banana Pro to generate a cozy, intimate lifestyle photograph. The scene features a woman lying on a sectional sofa in a modern living room during the evening, emphasizing soft, warm lighting, specific attire (a red lounge set), and detailed props like popcorn and champagne on a coffee table.
High-End Fashion Editorial Portrait with Strict Identity Lock
A detailed JSON prompt designed for the Nano Banana Pro tool to generate a photorealistic, high-end fashion editorial portrait. It features a strict identity lock mechanism (0.99 strength) to ensure the generated subject matches an uploaded reference image exactly, while applying dramatic lighting and luxury styling elements like a silver chainmail dress and long-exposure light streaks.
Ultra Photorealistic Saree Portrait with Identity Preservation
A comprehensive JSON prompt for Nano Banana Pro focused on generating an ultra-photorealistic portrait of a young woman in a black saree. It mandates strict identity preservation from an uploaded reference image, ensuring no facial or body modifications, and specifies detailed camera settings (smartphone lens, 8K resolution) and environment (modern bedroom) for a candid, high-detail result.
Photorealistic Celebrity Encounter Selfie with Controlled Expression
A highly constrained JSON prompt for Gemini Nano Banana Pro designed to generate a photorealistic selfie with a celebrity (implied, but the focus is on the foreground subject). The prompt enforces strict realism constraints and specifies a 'Calm confidence' expression, actively avoiding exaggerated excitement or surprise to achieve an 'Effortless, grounded, cool' aesthetic, typical of a controlled social media post.