AI Prompt Library

Change the character in the reference image to a deformed character illustration. Have the character take various poses within a single image. The background is white.

A candid, realistic still image of a MacBook Pro on a desk. The screen shows Safari open with X (Twitter), displaying my own X account. All UI elements must be accurate and authentic — no generic or incorrect follow buttons. My profile picture is clearly visible, and the same profile image also appears in the macOS side dock. Next to Safari, Photo Booth is open, showing a webcam selfie of me (the same person as in the profile picture). In the selfie, I am looking directly into the camera, making a cute and playful funny face — slightly exaggerated but charming, casual, and natural. Do not change my face or identity in any way. No gibberish or unreadable text anywhere on the screen. The phone (if present) remains completely still. Flat, natural lighting. Normal, realistic image quality — not cinematic, not overly stylized. Photorealistic, everyday desktop environment with a casual, authentic snapshot feel.

JSON structured wet hair gloss fashion portrait 4-panel prompt, emphasizing detailed makeup and emotion

Nano Banana Pro attempts to generate VI (Visual Identity) proposals, which is very interesting. Everyone can also try converting their existing brand identity into various merchandise items.

A hyper-realistic vertical tilt-shift photograph of a cross-section of a typical building in {argument name="city name" default="{city_name}"} during {argument name="current time" default="{current_time}"}. The current weather is {argument name="current weather" default="{current_weather}"}. The scene looks like an intricate miniature diorama. The lighting and sky color accurately reflect the {argument name="current time" default="{current_time}"}, while the street textures and atmosphere visually demonstrate the {argument name="current weather" default="{current_weather}"} conditions. At street level, the environment is lifelike. Tiny detailed figures are visible going about their activities. Strong miniature effect with heavy blur at the top and bottom. 8k resolution, volumetric lighting. --ar 9:16

A hyper-detailed, surreal but believable studio scene where an abstract concept is physically contained and made visible. Main structure: A transparent, museum-grade display container (thick glass or acrylic), placed alone in a neutral studio space. Inside the container is a frozen moment in time. Core subject: A human-scale subject (person or symbolic object) partially transformed into another material that contradicts its original nature — for example: {argument name="transformation example" default="skin turning into stone, soft fabric crystallizing, organic elements embedded in mechanical structures"}. The transformation is incomplete, showing a clear boundary between “before” and “after”. Conceptual twist: The interior of the container is treated like a scientific or archival exhibit: – clearly layered composition – visible cross-sections or cutaway logic – subtle measurement marks, labels, or annotation-style details – the feeling that this object is being studied, preserved, or explained Spatial logic: Gravity behaves normally, but time does not — motion is implied yet completely frozen. Small secondary elements ({argument name="secondary elements" default="dust, droplets, fragments, threads, petals, gears, etc."}) are suspended mid-air, reinforcing the sense of paused time. Lighting: Soft, directional studio lighting with strong material definition. Light emphasizes texture differences (smooth vs rough, organic vs artificial). No dramatic colors — restrained, high-end, museum-like color palette. Camera & composition: Straight-on or slightly elevated perspective. Centered composition, calm framing. Depth comes from internal layers, not camera tricks. Photorealistic, macro-level detail, cinematic clarity. Mood: Quiet, unsettling, contemplative. The image should feel intelligent rather than emotional, poetic rather than decorative. Style constraints: No fantasy clichés. No obvious sci-fi UI. No decorative surrealism. Everything should feel physically possible, even if conceptually strange. Ultra high resolution, extremely sharp details, realistic materials, controlled studio background, premium art photography aesthetic.

“Please remove the overlaid text from the image”

The first one is batch generating realistic 'behind-the-scenes' photos of a Christmas-themed film set 👇

subject: > A studio photograph of a physical cardboard box for a 1/7 scale plastic model. The box is fully printed before photography. The front face functions as a pure package artwork panel, not an information surface. composition: > Three-quarter front view of the box on a neutral studio surface. The front face is fully visible and displays ONLY Reference Image C, full-bleed, edge to edge, with no added elements. Only ONE side panel is visible in the shot. This visible side panel contains a layout combining Reference Image A and Reference Image B, along with assembled model examples, close-up detail views, weapon accessories, and cautionary notes arranged like a real commercial plastic model package. The opposite side panel is turned away from the camera and not visible. action: > Static studio product presentation. location: > Seamless neutral studio background with no props. style: > Photorealistic studio product photography. High-end hobby model kit packaging style. camera_lighting: > Professional studio lighting with soft key light and subtle rim light. Sharp focus on the box, shallow depth of field. colors: > Neutral background tones. Accurate printed colors matching the reference images. text: > Front face: ZERO generated text, ZERO warnings, ZERO symbols, ZERO labels. The only visible text on the front face is the text already embedded within Reference Image C. All g

Input this instruction, allowing the AI to complete the entire process step-by-step: extracting selling points, determining style, determining layout, and finally generating a complete, system-wide prompt. Finally, give the AI-generated prompt to the Nano Banana Pro model (it must be Pro). You can first provide some overall style prompts separately as general constraints. Then, whether generating images individually or in batches using third-party tools, it is possible.

A single prompt can 'dissect' the body structure of any creature?! This universal prompt can generate: ✨ Ultra-detailed 3D anatomical diagrams ✨ Automatically adapted skeletal/visceral systems ✨ Numbered professional medical annotations Whether it's the internal structure of Pikachu or the core of Godzilla, everything can be seen through! 👀

A hand holding a smartphone, with an autumn park featuring fallen leaves and a green bench in the background. The phone screen displays a vivid photo of **{argument name="subject" default="subject"}**. The background landscape within the phone screen perfectly aligns with the real, blurred background behind the phone, creating an illusion of transparency. White handwritten text annotations and arrows are drawn on the screen, pointing to the features of **{argument name="subject" default="subject"}**. Soft natural light, photorealistic, 4k resolution, high detail, creative social media photography style. 3D pop-out effect: the upper body emerges from the screen, while the lower body remains within the user interface. The image of **{argument name="subject" default="subject"}** is as shown, retaining facial and external features without any changes.

Also, restore my house to its bare shell state before renovation, and gradually renovate it into a Christmas-themed house step-by-step. Here, Nano Banana Pro needs to generate at least 5 intermediate process images so that the first and last frames have that video transition effect.

The world is a huge makeshift stage, and also a huge Palace of Versailles. Every day we are in magnificent office buildings, playing the elite, speaking jargon, even if deep down we feel like just a sour pickle, or a soda can repeatedly squeezed by life. The more glamorous the appearance, the more we want to go crazy inside. Forget it, I'll seal the packaging now, and continue to play the emotionally stable adult.

Read the motifs depicted in the attached image, generate multi-angle shots, and create four scenes divided into a 2x2 grid. Remix and edit with dynamic poses. subject: - Close-up portrait of the person. - Looking directly at the camera with a slightly tense or embarrassed expression. - The chest is slightly exposed, showing part of the collarbone and cleavage. - Large black Japanese text (Gothic or bold font) is centrally overlaid across the entire image, obscuring most of the face and body. This text is an announcement in the style of an SNS post, starting with "ご報告" (Report/Announcement). The announcement text is automatically generated by the AI. style: - Graphic design for social media posts. - Ultra-high resolution digital portrait with a strong smoothing filter applied. - Saturation and contrast are intentionally lowered in post-production, functioning as a background to emphasize the text. - High-key and fantastical atmosphere. composition: - Vertical portrait (tall orientation). - Close-up bust shot. The upper part of the woman's face (forehead) is slightly cropped. - The subject is centered in the frame, and the text dominates the center. - The background is completely blurred due to shallow depth of field (bokeh). - The text is vertically aligned with the image. lighting: - Uniform and very soft front light (ring light or softbox) is used. - Almost no shadows, flat lighting. - Overall very bright (high-key) tone. - Color temperature is neutral to slightly cool white light. colors: - Minimal palette consisting mainly of white, light gray, and black for the text. - The color of the woman's skin and lips is very pale, with extremely low saturation. - Overall, a near-monochrome color scheme. technical_specs: - Digital photograph. - Aspect ratio: 4:5 or 3:4 mobile portrait format. - Strong soft focus effect and glow style filter (luminescence). - Reproduction of the overlaid Japanese text (including font size, line spacing, and placement).

A black-and-white portrait. Cinematic style with added grain. The image shows an extreme close-up of half of the girl’s face. She looks directly at the camera, with her skin illuminated. She poses like a model, with her hand raised, elbow resting on her cheek, the hand in a graceful pose. The background is dark. Only her long hair is visible, partially obscuring her face.

{ "subject": { "description": "A stunning high-angle shot of a chic Asian fashion influencer with a cool, alluring attitude. ", "age": "20s", "expression": { "eyes": { "look": "sharp fox-eyes, piercing gaze directed at camera", "energy": "confident, slightly cold dashing sensual ", "details": "defined eyeliner, emphasized aegyosal" }, "mouth": { "position": "relaxed lips, subtle smirk", "energy": "chic" }, "overall": "stunning, high-visual-impact beauty" }, "face": { "preserve_original": false, "makeup": "high-contrast makeup, pale porcelain skin, reddish gradient lips, sharp jawline, V-shape face", "style": "cool-toned beauty, K-pop idol visual" }, "hair": { "color": "black", "style": "long sleek straight hair with full straight bangs", "effect": "glossy, high-fashion finish" }, "body": { "frame": "slim, petite, fragile aesthetic", "pose": { "position": "leaning forward significantly", "overall": "dynamic foreshortening, emphasis on head and upper torso" }, "skin": { "tone": "cold fair skin", "lighting_effect": "brightened face, soft beauty lighting, no dark shadows" } }, "clothing": { "top": { "type": "ultra-fine gauge knit top", "color": "{argument name="top color" default="dark crimson red"} ", "details": "mock neck, skin-tight fit, lightweight thin fabric (not thick)", "effect": "perfectly sculpting body curves, smooth texture" }, "bottom": { "type": "dark pencil skirt", "details": "high waisted with thin luxury belt" } } }, "photography": { "camera_style": "High-end social media snapshot", "angle": "High angle POV", "shot_type": "Medium close-up", "aspect_ratio": "9:16", "texture": "clear, sharp, slightly filtered for beauty", "lighting": "overcast cool daylight, soft diffuse light" }, "background": { "setting": "European classic architecture", "atmosphere": "fashionable street corner", "blur": "bokeh background to emphasize subject" }, "negative_prompt": [ "round face", "plain face", "no makeup", "warm yellow skin", "chunky knit", "thick sweater", "loose clothing", "wrinkled fabric", "dull eyes", "friendly boring smile", "low resolution", "dark lighting" ] }

A girl in a stylish nightclub, lit from one side by accent lighting. People are dancing around her while she reaches her hand directly toward the camera, creating an immersive, energetic perspective. She wears a {argument name="dress color" default="black"} corset dress with a unique, fashion-forward design. Her eyelashes are long and richly coated, the lower lash line is defined with black eyeliner to intensify her gaze, and a soft highlighter on her cheeks gives her skin a healthy glow. A delicate silver chain rests on her neck.

Design a full keyboard phone for a 'vibe coder', output the Nano Banana Pro prompt, and sign the prompt.

A composition where {argument name="Character" default="[Character]"} is formed entirely by negative space, objects framing an empty silhouette, soft lighting, minimalist background, conceptual and clean visual storytelling.

The man in the reference image takes a selfie with his iphone with the main characters of the movie "{argument name="movie title" default="[insert movie]"}", with the background the setting of the studio or scene of the movie, in a behind the scene footage. Keep the man in the reference image same and consistent

A scene where {argument name="Character" default="[Character]"} is implied but not visible — furniture slightly moved, objects mid-air, shadows showing their shape, pastel color palette, minimalist surreal environment, mysterious and playful tone.

{ "image_prompt": { "subject": { "type": "Young woman", "appearance": { "hair": "Sleek blonde hair pulled back into a tight bun", "skin": "Glowing, tanned complexion", "expression": "Playful 'kissy face' with puckered lips" } }, "attire": { "dress": { "color": "{argument name="dress color" default="Nude / Beige"}", "style": "Halter neck with a central keyhole cutout at the chest", "texture": "Embellished with small sparkling rhinestones or crystals throughout" }, "outerwear": "White plush faux-fur coat or stole, draped loosely around the elbows and forearms" }, "accessories": { "eyewear": "Small, sleek rectangular black sunglasses", "jewelry": "Thick gold hoop earrings" }, "action": { "pose": "Sitting relaxed on a sofa", "interaction": "Holding a coupe cocktail glass filled with amber liquid in the right hand, raised slightly" }, "setting": { "location": "Indoors, likely a lounge or club", "background": "Grey curtain drapes", "furniture": "White textured sofa", "lighting": "Direct flash photography style with hard shadows behind the subject" }, "mood": "Glamorous, chic, night-luxe, confident" } }

{ "subject": { "person": "young woman", "seat_position": "front passenger seat", "vehicle": "luxury modern car" }, "camera": { "capture_position": "inside the car", "eye_level": true, "angle": "slightly angled from the side", "framing": "close and intimate, not wide", "aspect_ratio": "3:4", "focus_area": "upper body and torso with part of legs visible", "composition": "editorial, confident" "selfie_type": "front passenger seat car selfie, arm extended slightly forward and inward while holding the camera, shot from inside the car close to the window, natural eye-level perspective, car window edge visible in frame, clear glass reflections and subtle window glare visible on the glass surface, authentic in-car selfie composition" }, "lighting": { "time_of_day": "daytime", "source": "natural sunlight through car window", "effect": "softly hitting face and body", "details": [ "gentle sun flares", "subtle highlights on skin, lips, and jewelry", "natural reflections", "no harsh glare", "no overexposure" ] }, "outfit": { "top": "{argument name="top color and text" default="dark crimson red fitted crop top with bold white 'TOKYO' lettering and small Japan flag detail underneath"}", "jeans": "light blue loose-fit jeans, relaxed and slightly baggy, sitting slightly lower on the waist", "waistband_detail": "very subtle glimpse of Calvin Klein waistband, minimal and tasteful", "shoes": "black Nike sneakers, partially visible" }, "jewelry": { "type": "delicate rings, bracelets, subtle accessories", "appearance": "exactly the same as reference photo", "lighting_effect": "soft sunlight with gentle shine" }, "accessories": { "sunglasses": over head upper side }, "hair": { "style": "loose and natural" }, "makeup": { "style": "soft and clean", "lips": "warm soft pink", "skin": "detailed healthy skin texture with natural glow", "lighting_effect": "light reflections from sunlight for a fresh, radiant look" }, "pose": { "body_position": "confident and relaxed", "orientation": "body slightly turned", "posture": "effortless yet self-assured" }, "facial_expression": { "mood": "calm, composed, confident" }, "background": { "view": "through the car window", "location": "Walmart storefront", "details": [ "large blue Walmart sign", "parking lot", "yellow safety poles", "STOP sign", "waving Japan flag" ], "sky": "clear blue", "atmosphere": "bright American daytime" }, "photographic_style": { "realism": "realistic", "resolution": "high-resolution", "color_balance": "natural", "aesthetic": "premium editorial suitable for social media and fashion content" }, "image_clarity_and_focus": { "sharpness" }