灵感图库
探索和使用精选的 AI 图像生成模板 (共 6,519 个)
Luxury Hot Tub Selfie with Wet Skin Glow
A highly detailed JSON prompt for generating an ultra-photorealistic 8K selfie of a European fitness model in a sunflower yellow bikini in an outdoor luxury hot tub at night. The prompt specifies complex lighting (jacuzzi LED glow and terrace lights) to create a wet skin glow effect and an intimate, seductive Instagram vibe.
Natural Candid Classroom Portrait with Identity Lock
A structured JSON prompt for generating a hyper-realistic 8K portrait of a young woman in a classroom setting, focusing on a natural, candid aesthetic. It requires exact face preservation from a reference image and specifies details like an oversized dark hoodie and soft, diffused indoor lighting.
3x3 Grid Collage of Emotions in 3D Cartoon Style
A structured JSON prompt for generating a 3x3 grid collage of portraits, all based on a single uploaded reference face with strict identity preservation. Each panel depicts the subject in a high-end smooth 3D cartoon style, expressing a different emotion (joyful, surprised, sad, confident, etc.) with corresponding outfits and solid color backgrounds.
Y2K Flash Portrait at Christmas Cafe
A detailed prompt for generating a hyper-realistic portrait of an Asian woman sitting at a dark wooden table in front of a vintage, Christmas-themed cafe. The image uses high-contrast Y2K digital compact-camera style, combining warm tungsten ambient light with a strong direct flash to make the subject glow.
Photorealistic Leaf Shaped Like a Bird
A simple, photorealistic prompt for generating an image of a single leaf manipulated or naturally shaped to resemble a bird in flight.
Photorealistic Leaf Shaped Like a Dragon
A simple, photorealistic prompt for generating an image of a single leaf manipulated or naturally shaped to resemble a dragon.
Elegant Glamour Portrait on Beige Sofa with Identity Lock
A structured JSON prompt for generating a portrait of a woman reclining on a beige sofa, emphasizing elegant glamour and soft luxury. The prompt requires strict preservation of the subject's identity and lighting from an uploaded reference image, detailing her outfit (white bodysuit, sheer tights, fur coat) and the warm, diffused indoor lighting.
Low-Quality Disposable Camera Aesthetic for Daily Life Photos
A Japanese prompt for generating an image of a cat and a girl with a specific aesthetic: low-quality, disposable camera look, and poor composition, intended for testing long-form film production with VEO 3.1 video generation and Suno music generation.
Generating Posters with Integrated Text and Illustrations
A comparison noting that Nano Banana Pro is effective for generating posters where text and illustrations blend naturally, resulting in a design with high completeness, suitable for practical design work involving text.
High-Speed Photography of Dance Forms in Sauce Choreography
A prompt for generating a conceptual food art image featuring six round white plates. Each plate uses different colored sauces and techniques (splatter, brush strokes) to choreograph a different dance form, captured using high-speed photography to freeze action droplets.
Generating Figure-Style Images from Still Photos
A simple prompt for transforming a still image into two figure-style images, noting the high quality of the resulting image and text on the packaging.
Reverse-Engineering Reusable Prompt Templates for Advertising
A meta-prompting process description (step 4) that instructs the AI to reverse-engineer a reusable prompt template based on a clearly defined visual goal. This template must support custom variables for long-term use in advertising creation.
Generating Various Everyday Scenes
A list of four simple prompts for generating images of common everyday scenes: a ramen stall, a man playing a pachinko machine, a traditional public bathhouse scene, and a cute high school girl's room.
Generating Hollywood Detective Scene Images with Character Reference
A process description for generating a Hollywood detective scene image, which involves uploading a character reference image and pasting a pre-generated prompt (presumably from a tool like Doubao) into the Nano Pro compatible AI tool.
Museum-Quality Animal Portrait with Integrated Luxury Brand Pattern
A highly detailed, structured prompt for generating a museum-quality, ultra-detailed portrait of an animal (e.g., dog, fish, bird) on a pure white or black background. The core feature is the integration of a luxury brand's iconic pattern (like Louis Vuitton's monogram) into the animal's natural markings (spots, stripes, scales) in a clear and recognizable manner, maintaining an elegant, high-end commercial aesthetic.
Miniature Girl Sitting on Coffee Cups
A prompt for generating an image of a miniature girl sitting on cold drink cups from popular brands like Ruixing Coffee and Mixue Bingcheng.
Photorealistic Half-Body Portrait with Vector Graphic Overlay (Chinese Version)
A JSON prompt for generating a photorealistic half-body portrait of a male subject, requiring 100% face preservation from an uploaded image. The image features the subject standing and leaning against a pure white studio wall, accompanied by a black-and-white, sharp angular vector portrait of the subject.
Prompt to Praise an Image's Emotional Quality
A prompt designed to make the AI 'praise' an uploaded image, specifically focusing on the emotional quality ('E-Mosa') of a photo of a traditional Japanese sunken hearth (Irori).
Rainbow Illustration Description
A descriptive text about the physics of rainbows, focusing on how water refracts light at a specific angle (42°). This text was likely used as a prompt to generate an illustration of a rainbow.
Image-to-Painting Reproduction Prompt
A detailed prompt instructing Nano Banana Pro to reproduce an attached image of a woman using specific artistic techniques, resulting in an analog oil painting style with an anime-like line art base, thick paint shadows, and a garden background. The final output should include the original woman proudly presenting the generated painting.
Image Editing Prompts: Removing and Replacing People
A sequence of two image editing instructions given to Nano Banana: first, to naturally remove all people from a photo, and second, to add a few people who appear to be preparing for something.
Educational Image Prompt: Adverbs of Frequency
A prompt used to generate a visual aid illustrating adverbs of frequency, likely intended for educational use on a blackboard or similar setting.
Image Synthesis/Composition Prompt
A prompt used to composite two characters (Ukyo and a ninja girl) into a game screen image from Samurai Shodown (Samurai Spirits). This demonstrates Nano Banana Pro's image synthesis capabilities.
Thumbnail Editing Prompt: Replacing a Person
A simple editing prompt for Nano Banana Pro used to quickly change a person in a thumbnail image for A/B testing purposes.