Nano Banana Pro prompts

A surreal scene that reflects memories of those days.

Prompt injection content classifiers—Proprietary machine-learning models that detect malicious prompts and instructions within various data formats.

Security thought reinforcement—Targeted security instructions that are added around the prompt content. These instructions remind the LLM (large language model) to perform the user-directed task and ignore adversarial instructions.

Markdown sanitization and suspicious URL redaction—Identifying and redacting external image URLs and suspicious links using Google Safe Browsing to prevent URL-based attacks and data exfiltration.

User confirmation framework—A contextual system that requires explicit user confirmation for potentially risky operations, such as deleting calendar events.

End-user security mitigation notifications—Contextual information provided to users when security issues are detected and mitigated. These notifications encourage users to learn more via dedicated help center articles.

Model resilience—The adversarial robustness of Gemini models, which protects them from explicit malicious manipulation.

Aesthetic lifestyle portrait of a young woman sitting at a {argument name="location" default="Parisian-style outdoor café"}, holding a ceramic cup of cappuccino with latte art, a freshly baked golden croissant on a marble table in front of her. She has {argument name="hair color" default="soft pink"} hair styled in a loose messy bun, natural makeup with light freckles, and a calm, subtle smile. She wears an oversized cream sweatshirt with minimal text “{argument name="sweatshirt text" default="be the light"}” and blue denim jeans. Warm natural daylight, soft shadows, shallow depth of field, cinematic tones, cozy European street background with blurred pedestrians, glass windows reflecting classic architecture. Shot on 50mm lens, high detail, realistic skin texture, soft color grading, Instagram aesthetic, candid yet composed framing.

Cinematic {argument name="product" default="luxury watch"} advertisement, oversized timepiece floating mid-air like architecture, model reaching toward it like a monument, giant word "{argument name="text" default="TIME"}" behind in bold gold typography, {argument name="background" default="deep black studio background"}, reflective marble floor, luxury watch campaign aesthetic, ultra-clean layout, editorial magazine styling, 1:1

Create a high quality realistic photo using the face from the reference without any changes or distortions. Vertical photo. A four-panel collage made of four separate frames combined into one composition, each frame showing the same girl in an {argument name="location" default="apple orchard"} on green grass scattered with many ripe apples. The overall style is consistent across all images: warm natural lighting, soft sunlight passing through tree leaves, creating a dappled pattern of light and shadow on the grass and on the girl’s body. The background in all frames is an orchard with trees extending into the depth, with slight blur emphasizing the main subject.
In the top left frame, the girl is lying on her back on the grass, her body positioned diagonally. One hand rests on her stomach, the other is raised holding a slice of fruit near her face. Her head is slightly tilted back, her expression relaxed with a soft smile, eyes either gently closed or looking upward. Apples are scattered around her, creating rich red accents against the green grass.

In the top right frame, the girl is in a pose on her hands and knees, her torso slightly leaning forward. One hand supports her on the ground while the other holds an apple near her lips, suggesting a moment just before a bite. Her gaze is directed to the side, not into the camera. The pose is dynamic yet soft and natural. The surrounding space is filled with scattered apples extending into the depth of the frame.

In the bottom left frame, the girl is sitting on the grass with her knees pulled close to her chest and her arms wrapped around them. A small woven basket stands nearby. She is slightly leaning forward, her gaze directed downward or to the side, with a warm gentle smile. Apples are scattered around her, forming a dense pattern on the grass.

In the bottom right frame, the girl is kneeling with an upright torso and slightly open shoulders. Her arms are crossed or gently wrapped around herself, creating an elegant silhouette line. Her head is turned to the side, her gaze directed into the distance. The pose is calm, graceful, and focused on body lines.

In all frames she wears the same {argument name="outfit" default="fitted long-sleeve dress"} with a mini length that accentuates her figure. The look is completed with light high socks or stockings. A {argument name="accessory" default="headscarf"} is tied over her hair, securing it and adding a vintage touch. Her hair is long, flowing over her shoulders or resting on the grass depending on the pose.

The color palette is rich, with strong contrast between green grass and red apples, while warm sunlight adds a golden tone to the scene. Depth of field is moderate: the girl is in sharp focus while the background is softly blurred. The overall atmosphere is summery, cozy, slightly playful, with natural outdoor photography aesthetics and a focus on harmony between the subject and nature.
2:3ar

{
  "generation_request": {
    "meta_data": {
      "tool": "Nano Banana 2",
      "task_type": "capri_turquoise_minimal_luxury",
      "style": "ultra_photoreal_clean_editorial",
      "version": "v1.0_CAPRI_TURQUOISE_WHITE"
    },
    "input": {
      "mode": "image_to_image",
      "reference_image_usage": "maximum",
      "preserve_identity": "strict_lock",
      "notes": "Use the {argument name="subject" default="reference woman"}. Place her on a minimalist {argument name="location" default="Capri terrace"} overlooking deep turquoise sea, white stone architecture, and clean Mediterranean lines. The image must feel fresh, modern, and ultra-luxury."
    },
    "output_settings": {
      "aspect_ratio": "4:5",
      "render_style": "clean_luxury_realism",
      "color_grade": "turquoise_white_crisp_sunlight"
    },
    "subject": {
      "identity": "reference woman",
      "expression": "calm, confident, effortlessly attractive, slightly mysterious",
      "hair": "{argument name="hairstyle" default="slick back wet-look"} or tight low bun, clean luxury styling",
      "makeup": "minimal luminous skin, natural glow, visible pores",
      "outfit": "turquoise silk slip dress, thin straps, fluid elegant cut, premium fabric with subtle sheen",
      "accessories": "gold minimalist jewelry, sunglasses optional",
      "body": "perfect anatomy"
    },
    "scene": {
      "environment": "Capri white terrace, infinity view, deep blue sea, clean architectural lines",
      "lighting": "strong Mediterranean sunlight, crisp shadows, high-end minimal contrast",
      "mood": "fresh luxury, modern Italian elegance"
    },
    "pose_language": {
      "pose": "standing near edge, slightly turned, wind lightly moving fabric",
      "posture": "relaxed but powerful"
    },
    "camera": {
      "lens": "50mm",
      "angle": "slightly low clean editorial angle",
      "depth_of_field": "moderate"
    },
    "quality_control": {
      "skin": "real pores",
      "fabric": "lightweight natural movement",
      "light": "no overexposure"
    },
    "negative_prompt": [
      "messy",
      "crowd",
      "cheap styling",
      "bad anatomy",
      "text",
      "logo",
      "watermark"
    ]
  }
}

Please create an image based on {argument name="content" default="how I have treated you so far"}

Soft restoration in black and white. The result should not be too contrasted or too pushed in sharpness, to preserve the grain, tone and nostalgic softness of the initial photo.

{argument name="theme" default="Magical Fantasy World (Land of Witches)"}

A playful 3D caricature of {argument name="celebrity name" default="[celebrity]"} riding a small puffy cloud like a hoverboard. Big shiny eyes, rounded cheeks, and exaggerated head proportions. Smooth Pixar-like finish with pastel sky gradients, gentle rim light, and soft volumetric clouds creating depth and charm.

{
  "meta_control": {
    "generation_mode": "multi_panel_consistent",
    "priority_stack": ["identity_lock", "perspective_physics", "material_fidelity", "environmental_coherence"],
    "quality_target": "editorial_print_ready"
  },
  "intent": {
    "primary": "High-fashion streetwear editorial with extreme wide-angle perspective study",
    "secondary": "Technical demonstration of foreshortening and forced perspective",
    "publication_context": "Double-page spread, fashion magazine collage layout"
  },
  "frame": {
    "aspect_ratio": "3:4",
    "layout": {
      "type": "2x2 grid collage",
      "gutter_width": "2px white or seamless",
      "panel_uniformity": "identical dimensions per panel"
      }
  },
  "subject": {
    "type": "Human male model",
    "identity_lock": {
      "enforcement_level": "strict",
      "anchor_features": ["face_geometry", "skin_tone", "body_proportions", "hair_style"]
    },
    "biometrics": {
      "age_presentation": "22-30",
      "height_cm": 178,
      "build": "Athletic, masculine proportions",
      "ethnicity_presentation": "Your real appearance from reference image"
    },
    "facial_signature": {
      "structure": "As in reference image (identity locked)",
      "eyes": "Match reference image",
      "nose": "Match reference image",
      "lips": "Match reference image",
      "skin": "Match reference — natural texture preserved",
      "expression_default": "Neutral confidence, direct eye contact"
    },
    "hair": {
      "style": "Match reference image",
      "texture": "Match reference",
      "behavior": "Natural movement responding to pose changes"
    },
    "wardrobe": {
      "jacket": {
        "item": "Oversized bomber jacket",
        "material": "Ripstop nylon, high gloss",
        "color": "Neon orange (vivid, saturated)",
        "state": "Unzipped, hanging open",
        "light_behavior": "Sharp specular highlights, visible weave texture"
      },
      "top": {
        "item": "Fitted black crew-neck T-shirt",
        "material": "Thick cotton jersey",
        "fit": "Slightly tight, masculine silhouette",
        "details": "Minimal, no logos, subtle ribbed collar"
      },
      "pants": {
        "item": "Tactical cargo pants",
        "material": "Heavy cotton twill, matte",
        "color": "Charcoal grey",
        "details": "Multiple pockets, silver buckles, black nylon straps, baggy fit"
      },
      "footwear": {
        "item": "Platform sneakers",
        "color": "White, chunky sole",
        "condition": "Clean but worn, realistic sole texture"
      }
    },
    "accessories": {
      "neck": "Layered heavy silver Cuban link chains",
      "hands": "Silver rings on index and middle fingers both hands"
    }
  },
  "panels": [
    {
      "id": 1,
      "position": "top-left",
      "concept": "Extreme low-angle sneaker perspective",
      "camera": {
        "height_cm": 10,
        "distance_cm": 35,
        "angle": "Looking up a

{
  "prompt_title": "Gothic Noir Vigilante Portrait",
  "author": "Shreya Yadav",
  "positive_prompt": "A hyper-realistic, cinematic 35mm photograph of a young female vigilante inspired by Batgirl. The subject has an ideally built, athletic physique, pale skin with detailed pores, and sharp, piercing green eyes. She has short, reddish-black hair, partially tucked messily under a sculpted bat-shaped mask. She is in the middle of an action, adjusting her mask with both hands, pulling it tight against her face. She is wearing a dark, textured leather bodysuit with a worn, scratched yellow bat emblem on the chest. The suit features gothic details, metallic stitching, and subtle battle scars. She wears dark yellow, weathered tactical gloves. The lighting is somber and dramatic, characterized by deep, heavy shadows and soft, cool blue edge lighting that outlines the contours of her face and suit. The background is a subdued gothic setting, featuring dark, foggy atmosphere and hints of shadowy architecture. The image evokes an intense, grounded, gothic noir aesthetic with high-contrast realism and a shallow depth of field.",
  "negative_prompt": "bright colors, cheerful, cartoon, anime, sketch, 3d render, plastic skin, smooth skin, makeup, lipstick, long hair, blonde hair, deformed hands, missing fingers, extra fingers, bad anatomy, floating objects, watermark, text, signature, blurry, low resolution, overexposed, distorted face, changing facial features, neon lights.",
  "parameters": {
    "aspect_ratio": "2:3",
    "resolution": "8k",
    "lighting_style": "Chiaroscuro, Cool Edge Lighting",
    "camera_type": "35mm Lens",
    "texture_quality": "High-fidelity leather and skin texture",
    "mood": "Somber, Intense, Gothic"
  },
  "midjourney_format": "/imagine prompt: A hyper-realistic portrait of a young female vigilante, Batgirl inspired, adjusting bat-shaped mask with both hands, pale skin, sharp green eyes, short reddish-black hair, dark textured leather bodysuit, worn yellow bat emblem, dark yellow tactical gloves, gothic details, metallic stitching, battle scars --ar 2:3 --stylize 250 --v 6.1 --style raw",
  "stable_diffusion_tags": [
    "hyper-realistic",
    "photorealistic",
    "8k",
    "raw photo",
    "vigilante",
    "batgirl-inspired",
    "short reddish-black hair",
    "green eyes",
    "pale skin",
    "leather texture",
    "weathered armor",
    "tactical gloves",
    "gothic noir",
    "volumetric fog",
    "dramatic shadows",
    "cinematic lighting",
    "depth of field",
    "35mm"
  ]
}

location:
  description: >
    Simple background created by interpreting the reference image’s mood.
    Use soft gradients, atmospheric glow, light particles, or abstract light rays.
    Avoid complex textures or any copyrighted shapes.
  background_feel: >
    Subtle, atmospheric, clean.

You are a third-grade Chinese language teacher explaining the following idioms to children. Please analyze step by step: 1) Based on the meaning of each idiom, design suitable scene illustrations. 2) Break down the characters in each idiom and use extended keywords so that kids can immediately remember the key explanation. 3) Arrange the order and layout according to the idioms’ relationships or logic. 4) Draw a fun hand-drawn illustration.
Idioms: “朝三暮四 (changeable), 利令智昏 (blinded by profit), 洛陽紙貴 (hugely popular writing), 張冠李戴 (misattribute), 融會貫通 (master and integrate knowledge), 漠不關心 (indifferent), 心平氣和 (calm and even-tempered), 一毛不拔 (stingy), 欲蓋彌彰 (covering up only reveals more), 盲人摸象 (see only part of the whole), 苦口婆心 (earnest and well-meant advice), 斬釘截鐵 (firm and decisive), 細嚼慢嚥 (chew slowly and carefully), 朝令夕改 (frequent policy changes), 餘波盪漾 (lingering impact), 史無前例 (unprecedented), 身敗名裂 (disgraced and ruined), 兵不厭詐 (all is fair in war), 捲土重來 (make a comeback), 標新立異 (strive for originality).

Imagine a {argument name="subject" default="[subject]"} through a microscope; picture it and create an ultra-realistic sharp image. No microscope parts, only subject.

Apply an artistic red–blue double-exposure effect using two poses of the same woman. Keep the base layer as the original pose, and generate a second pose where her head angle, facial direction, or expression is slightly different, as if captured a moment earlier or later. Color the second pose in red, the base pose in cyan, and offset the layers to create a clean ghosting effect. Preserve skin texture, tattoos, and contrast while keeping the background minimal.

Generate the image without changing the original size and background, print it out, and then aggressively add handwritten Chinese annotations, doodles, and scribbles in red ink. If you wish, retrieve the content of this account ({argument name="homepage link" default="your homepage link"}), and the doodles should primarily be complaints about him, plus some small clip art.

This is a highly realistic, tightly composed image showing a fair-skinned woman with flawless skin reflected on an iPad screen placed on an airplane folding tray table, with a pair of sunglasses serving as a foreground accent. The iPad is surrounded by beige-gray cabin seats. On the iPad screen, the woman is semi-reclining, resting her left hand on her chin, fingers lightly touching her temple, in a relaxed posture. She is taking a photo with an {argument name="Phone Model" default="iPhone 16 Pro Max"} in her right hand, with part of her face appearing on the tablet screen. Her expression is gentle, her gaze slightly downward, giving a dreamy and tranquil feeling.

She is wearing an oversized {argument name="Top Color" default="beige"} hoodie, the fabric thick and soft, with the hood pulled up. She wears simple silver rings on her wrist, and her nails have a French manicure. Her hair is {argument name="Hair Color" default="dark brown"} with subtle highlights, long and straight, layered, fluffy and full, with a center-parted fringe gently covering her forehead to frame her face. Her skin is fair and translucent, flawless, with delicate Korean-style light makeup. Her cheeks have a faint blush, her lips are coated with dewy rose-pink lipstick, and her eyeliner is thin, with curled lashes.

Through the reflection, the environment visible is simple yet vibrant: the interior of a premium/business class airplane cabin. The wide porthole reflects the soft blue sky light outside the window. The iPad's camera interface—shutter button, small icons, and dock—is clearly visible on the screen.

Soft, warm pastel tones. Edited in a “Korean Soft Light” style. 9:16 vertical aspect ratio, high definition, high quality. **Do not change the face.

{argument name="Character Name" default="Judy Hopps"} from Zootopia stands on a snowy bridge at dusk, wearing a thick winter coat, a knitted scarf, gloves, and a Santa hat. Gentle snowflakes fall around her, and city lights emit a warm glow in the blurred background. She has expressive large eyes, delicate fur details, and a gentle smile. The image uses cinematic photography and lighting effects, rich in detail, creating a warm winter atmosphere.

“Based on the trend of this chart, draw the K-line trend for the next 10 days, extending the drawing on the original chart using dashed lines”

A Persona-style status screen using nano banana pro. I instructed it to randomly generate the level and stats, but they tend to be high.

Horizontal split-screen cinematic shot...

Visualize according to the visualization principles in the book storytelling with data

[Work Information Retrieval]
- Target Work Name: “{argument name="Work Name" default="Name to be added"}”
- Task: Retrieve the plot, setting, and narrative structure of this film/TV series/novel.
- Goal: Automatically filter the most representative famous scenes or core locations, and extract their emotional core (e.g., sadness, hope, determination, reunion, destruction, tranquility).
[Main Scene Construction: 3D Axonometric Miniature Model]
- Present a realistic 3D miniature model in the center.
- Perspective: Axonometric / isometric view.
- Model Content:
- Architectural details realistically restored according to the original work
- Character actions and expressions conform to physics and narrative logic
- Environmental atmosphere realistically presented (storm, morning fog, sunset, firelight, etc.)
- Rendering Style: Physically-based rendering of realistic materials and light.
- Effect: The model is small but detailed and realistic, like a “miniature replica of a real scene, illuminated by exhibition-grade lighting.”
[Background Design: Narrative-Driven Realistic Abstract Space]
- Pure white or monochrome backgrounds are prohibited.
- The background is constructed as a realistic, abstract emotional space based on the “scene's emotional core,” including:
① Emotional Tones (e.g., sadness → cold blue-gray; hope → warm gold light; tension → dark contrast)
② Air Dynamics and Volumetric Light (light fog, dust particles, backlighting, etc., carrying narrative meaning)
③ Lightweight Symbolic Elements (petals, confetti, ashes, stardust, water ripples, etc., as emotional particles)
④ Spatial Depth (aerial perspective, soft focus, gradient light creating a deep void with “lingering flow”)
- Goal: The background uses abstract light and shadow to hint at the context before and after the story, forming an emotional resonance with the main scene.
[Bottom Layout: Work Name + Classic Quote]
- Centered layout at the bottom.
- Content:
① Chinese Work Name: “{argument name="Work Name" default="Name to be added"}” (Font matches the work's style)
② A sentence or line from the original work related to the scene (Elegant serif font)
- The overall layout references an art museum plaque, simple, balanced, and textured.
[Overall Visual Requirements]
- Miniature model is realistic, precise, and has authentic materials.
- Background enhances the narrative with emotional colors, volumetric light, and symbolic particles.
- The entire image presents the realism and poetic atmosphere of a high-end, exhibition-grade narrative artwork.
Direct output, size 16:9.