AI 提示词库

Please generate an image of Umaibo drawn with a ballpoint pen.

Display the subject from the attached image on a flip phone (garakei) LCD screen from early 2000s Japan. The phone is open, with glossy pink or white shell, physical buttons, and simple beaded straps with pastel colored beads. The screen shows the image with pixelated edges and warm color saturation typical of 2000s mobile displays. Surrounded by nostalgic items like photo stickers, gel pens, and mini notebooks. Nostalgic, kawaii, emotional, soft lighting.

I tried making the image above look like it was viewed from below using Nano Banana lol

I thought an image would be easier to understand than a long text, so I asked everyone's favorite Nano Banana to summarize it.

GENERAL STYLE & MOOD: “Epic Figurative Art.” The prompt requires multi-layered analysis of the user’s provided home screen (articles, headings, used apps, notifications, colors) to condense all “elements” of the year into a single still image. It should be a fusion of philosophical, profound realism and surreal design. TASK & ANALYSIS: 1. Comprehensively scan the text information within the provided home screen to extract frequently used vocabulary, interests, emotional fluctuations, and fragments of daily life. 2. Integrate these “total elements of the year” and select one ultimate “single Kanji character” that symbolizes the user’s journey. 3. Construct the “strokes” of that Kanji character as a three-dimensional collection of concrete events analyzed (e.g., work tools, hobby fragments, motifs from read articles). SUBJECT: The “single Kanji character” embodying the user’s year, centrally positioned. - This character is a “collection of micro-stories.” Upon closer inspection, the parts of the character should be formed by specific objects that colored the user’s year (e.g., designs symbolizing specific news articles, daily tools, fragments of memory). - Maintain perfect readability of the Kanji and ensure it has a strong skeletal structure. ENVIRONMENT & BACKGROUND (The Total Year Narrative): The background should also be depicted not merely as scenery, but as an epic panorama covering “all elements of the year.” - Background composition: Behind the character, the analyzed events of the year should spread out as scenery, either chronologically or thematically (e.g., symbols of challenged projects, the atmosphere of visited places, images of engrossing news). - Consistency: The central Kanji should be the core of the “world” of that year, with all background elements converging towards the character or overflowing from it. LIGHTING & TEXTURE: - Profound texture that conveys “layers of memory.” Metal, organic matter, light particles, and digital data should mix, possessing physically correct reflections and shadows. - Background light sources (dramatic backlighting or sidelight) should illuminate the character, highlighting the multilayered elements of the year through shadow. CONSTRAINTS: - Accurately depict the Kanji shape (hooks, sweeps, stroke count) so it is correctly legible in Japanese. - Arrange “elements of the year” in both the background and the character, ensuring the overall screen is not cluttered and maintains harmony as a single work of art. - 4K high resolution. Completely exclude meaningless symbols, garbled text, or broken forms. Input Information [[ {argument name="input information" default="URL of your home screen/article here"} ]]

Please add the text 'We are best friends forever'. Also, please add handwritten graffiti typical of Heisei-era Purikura. Also, please add arrows and the girls' names. The girl on the right is {argument name="right girl's name" default="Yuka"}, and the girl on the left is {argument name="left girl's name" default="Chieri"}.

Strictly reference the person in the image. Seven images of the same female figure appear in the frame, corresponding to the seven days of the week. Clearly the same person, but allow them to have different postures, expressions, actions, and clothing that fit the theme or scenario. Theme / Scenario: [{argument name="theme / scenario" default=""}] Please instruct the AI to freely design based on this theme: Outfit matching Postures and actions Expressions and temperament Overall atmosphere and style No need for a unified style, No need to deliberately align poses, No need to explicitly specify emotions or actions. Image requirements: Horizontal composition (16:9) Full body presentation Multiple instances of the same person appearing side-by-side Overall natural, realistic, and varied Some scrapbook patterns matching the scene and theme can be added to the background A Chinese title matching the theme is placed at the top The main subject's name is called [{argument name="subject name" default=""}], design the rest of the title content yourself. Do not analyze, generate the image directly.

# ===== USER CONTROLS ===== title_text: "{argument name="display string" default="<<YOUR_TEXT>>"}" title_style_preset: "{argument name="logo design preset" default="cool"}" # cool, cute, cool_cute, luxury, pop, cyber, minimal, retro, kawaii face_zoom: "{argument name="zoom on/off" default="off"}" # off, on subject: > Create a 21:6 wide banner using the provided reference image content. The primary face must be centered inside an invisible safe zone (not drawn), and a title logo (derived from title_text + title_style_preset) must be placed inside the same safe zone. composition: > Aspect ratio 21:6. Invisible safe zone (DO NOT draw it): - Left margin: 15% of width - Right margin: 15% of width - Top margin: 16% of height - Bottom margin: 16% of height Keep the entire face AND the entire title logo fully inside this safe zone. Background may extend to the edges. action: > Place the reference image content with maximum fidelity. Auto-crop/scale/reposition to fit a 21:6 banner with no stretching. Detect the primary face (if multiple faces, pick the largest/most prominent). Center the primary face within the safe zone both horizontally and vertically. Never crop off the face/eyes; keep the full face comfortably inside the safe zone (not near edges). Face zoom behavior: - If face_zoom is OFF: keep the original framing as much as possible while still centering the face in the safe zone. - If face_zoom is ON: zoom/crop to a bust-up portrait centered on the face (head and shoulders visible; include upper chest; do no

[ { "subject": { "gender": "female", "instructions": "The Girl should be the same as reference picture uploaded", "hair": { "color": "blonde", "style": "updo with bangs", "texture": "wavy", "details": "tendrils framing face" }, "eyes": { "color": "blue", "makeup": "winged eyeliner, pink blush" }, "lips": { "color": "nde", "finish": "glossy" }, "attire": { "dress": { "color": "light pink ", "material": "satin", "style": "strapless gown" }, "gloves": { "color": "light pink", "material": "satin", "length": "opera" }, "stole": { "color": "white", "material": "fur" }, "jewelry": { "earrings": "gold" } }, "pose": "seated, looking at camera, hand on chest" }, "setting": { "location": "inside a vintage car", "interior": { "upholstery": "red leather", "details": "chrome door handle" }, "exterior_view": { "time": "night", "weather": "snowing", "elements": "blurred city lights, snow-covered window" } }, "style": { "type": "photograph", "lighting": "warm interior, cold exterior", "focus": "sharp on subject, shallow depth of field", "mood": "elegant, glamorous, wintry", "aspect_ratio": "9:16", "camera_details": { "camera": "DSLR", "lens": "85mm f/1. 8 prime", "aperture": "f/1. 8", "shutter_speed": "1/60s", "iso": "800", "lighting_setup": "soft warm interior fill light, natural exterior bokeh", "post_processing": "natural skin texture, color grading warm vs cold" } }, "text_overlay": { "content": "", "location": "on dress", "style": "" } } ]

# ===== USER CONTROLS ===== title_text: "{argument name="display string" default="<<YOUR_TEXT>>"}" title_style_preset: "{argument name="logo design preset" default="cool"}" # cool, cute, cool_cute, luxury, pop, cyber, minimal, retro, kawaii face_zoom: "{argument name="zoom on/off" default="off"}" # off, on subject: > Create a 3:1 wide banner using the provided reference image content. The primary face must be centered inside an invisible safe zone (not drawn), and a title logo (derived from title_text + title_style_preset) must be placed inside the same safe zone. composition: > Aspect ratio 3:1. Invisible safe zone (DO NOT draw it): - Left margin: 15% of width - Right margin: 15% of width - Top margin: 16% of height - Bottom margin: 16% of height Keep the entire face AND the entire title logo fully inside this safe zone. Background may extend to the edges. action: > Place the reference image content with maximum fidelity. Auto-crop/scale/reposition to fit a 3:1 banner with no stretching. Detect the primary face (if multiple faces, pick the largest/most prominent). Center the primary face within the safe zone both horizontally and vertically. Never crop off the face/eyes; keep the full face comfortably inside the safe zone (not near edges). Face zoom behavior: - If face_zoom is OFF: keep the original framing as much as possible while still centering the face in the safe zone. - If face_zoom is ON: zoom/crop to a bust-up portrait centered on the face (head and shoulders visible; include upper chest; do not crop the top of the head or chin; keep facial features prominent). Create negative space inside the safe zone for the title logo by adjusting crop/reposition/out

{ "shot": "A tight close-up mirror selfie", "subject": { "appearance": "a stunning woman", "hair": "long wavy hair", "pose": "sitting casually sideways on a white bathroom vanity counter", "gaze": "looking at the mirror" }, "outfit": { "bodysuit": "form-fitting sky blue symbiote-inspired superhero bodysuit with subtle dark web texturing", "emblem": "prominent white spider emblem on the chest" }, "phone": { "device": "black smartphone", "case": "red spider logo case", "action": "holding it up to capture the reflection" }, "environment": { "location": "bathroom", "lighting": "dimly lit with warm, soft indoor lighting", "atmosphere": "intimate atmosphere with soft shadows", "visible_elements": "only a partial section of the white sink basin and counter surface visible at the bottom of the frame", "mirror": "mirror edges are cropped out of view" }, "aesthetic": "high quality, photorealistic, lo-fi social media aesthetic", "makeup": { "blush": "prominent soft pink blush on her cheeks", "finish": "glowy makeup", "highlighter": "on the tip of her nose", "lips": "slightly parted soft warm pink lips" }, "skin": "highly detailed skin texture", "lighting_detail": "even, invisible front illumination that softly brightens the face with neutral white light, no visible light source, no shadows, no reflections, no hotspots", "quality": "no blur" }

Create a close-up photo of the young woman wearing clothes. Beside her is the original page exactly as in the attachment, 100% unchanged. Character (Subject): Slim (slender) build, Very fair skin. Very long dark brown hair, slightly covering the face, blown by the wind, lightly layered and slightly messy, loose from a large clip, half-up hairstyle with a pointed ponytail, half released. Facial appearance: Large round brown eyes with long, delicate eyelashes and a soft dewy makeup look. Cheeks and the tip of the nose blurred with a light pink tone. Full lips with glossy pink lip gloss, giving a moist, watery look. She wears a dress according to the second attachment. Location: In front of a white-toned house, she is sitting on a chair. Lighting & Style: Direct flash, flash photography, hard light, bright background, Y2K style, amateur aesthetic, realistic, photorealistic. Create the photo in 4 layouts with different posing styles. She is wearing a silver necklace Image size: 9:16. Do not change the face at all.

Create an ultra-realistic cinematic photograph in a film-still aesthetic, based strictly on the face from the provided reference photo, preserving 100% facial likeness with absolutely no changes to facial structure or hair. The image is captured as a low-angle selfie, with the camera slightly tilted upward, creating a dynamic perspective that emphasizes the grandeur of a wooden mountain chalet in the background, its roof heavily covered in snow. The upper lines of the building recede into perspective, enhancing the dramatic low-angle composition. The woman is framed in a tight close-up. Her face is subtly tilted forward toward the camera, making her facial features appear more expressive: full lips, a clearly defined jawline, and balanced proportions. Her expression is calm and confident, with a soft, sensual half-smile. She is wearing a voluminous, natural fluffy fur coat that fills the lower part of the frame due to the shooting angle. In her hand—raised slightly higher than usual because of the selfie perspective—she holds a large glass of red wine close to the camera, creating an almost three-dimensional effect. The wine has a deep ruby tone with cinematic softness, and gold rings are visible on her fingers. Her straight hair is lightly dusted with snowflakes. Above her head, the sky and the chalet roof are visible, both densely covered in snow. Large snowflakes drift slowly through the air, appearing in both the foreground and background, adding depth and atmosphere. Film look characteristics: soft film grain; pastel, slightly muted color palette; gentle highlights on the glass and hair; warm skin tones contrasting with cool bluish-gray hues of the snow and sky; subtle vignette around the corners; 35mm film effect: smooth light transitions, natural shadows, no digital sharpness; fine dust and microscopic film imperfections (optional). The overall atmosphere is aesthetic, luxurious, relaxed, and wintry, evoking the feeling of a living cinematic moment and true presence in the scene.

{   "portrait_metadata": {     "composition": "Medium Close-up, three-quarter view, high-contrast framing (black clothing against white snow/fur)",     "lighting": "Soft, diffused overcast daylight. Natural fill light provided by surrounding snow. Flat lighting profile, high ambient key.",     "camera_settings": "85mm Prime Lens, Aperture f/4.0, Shutter Speed 1/250s, ISO 200. Full-frame CMOS sensor. Cinematic color grading with cool temperature bias."   },   "subject": {     "demographics": "Woman, early twenties, European/Caucasian, long platinum blonde hair.",     "expression": "Serene and aspirational gaze, looking upwards and to the right. Lips slightly parted with precise, matte crimson lipstick application. Slight smile/smirk visible at the corners of the mouth.",     "skin_micro_details": "Fair, cool-toned complexion showing slight redness from the cold, particularly on the cheeks and nose tip. Makeup is flawless, with minimal visible pores (filtered look). A faint layer of Vellus hair is visible on the cheek contour. Distinct small, white glitter or makeup dots are placed strategically near the temple and outer eye area, simulating frost/snow accents.",     "eyes_micro_details": {       "iris": "Medium brown/hazel color. Visible delineation of the dark limbus ring against the sclera. Detailed radial pattern within the iris texture (Krypten, Furchen).",       "sclera_and_lashes": "Bright, white sclera. Heavy application of false eyelashes or voluminous mascara, forming sharp, separated strands. Precise black liquid eyeliner wing. A small, melted snowflake particle is resting near the lower eyelid crease.",       "reflections": "Soft, expansive reflection of the grey, overcast sky, dominating the cornea surface. Lack of sharp point light sources."     }   },   "environment_and_style": "Upscale suburban exterior during a fresh snowfall. Background features blurred red brick residential architecture and stark, leafless winter trees (shallow depth of field). Large, distinct flakes of snow are visible in the foreground and midground (Snow Bokeh). Style is 'High Fashion Winter Glamour' with high textural contrast (soft fur, ribbed knit fabric).",   "image_quality_tokens": "Hyper-Photorealism, 8k resolution, raw photo quality, cinematic close-up, highly detailed skin texture, masterwork editorial photography, precise fabric texture, winter mood." }

{   "subject": {     "demographics": "{argument name="demographics" default="Young woman, Roughly 20s"}",     "hair": {       "color": "Dark brown",       "style": "Long, wavy, tousled, spread out on pillow",       "texture": "Soft, natural"     },     "face": {       "expression": "Gentle smile, relaxed",       "eyes": "Brown, looking directly at camera",       "skin_tone": "Fair to medium, rosy cheeks",       "makeup": "Natural look, minimal"     },     "pose": "Reclining/lying down on back, head tilted slightly"   },   "attire": {     "clothing": "Black spaghetti-strap tank top or camisole",     "neckline": "Low scoop neck"   },   "accessories": {     "jewelry": [       "Thin gold chain necklace",       "Small dark pendant (possibly heart-shaped or geometric)"     ]   },   "environment": {     "setting": "Bedroom, bed",     "background": "White bed sheets/pillows, soft texture, slightly wrinkled"   },   "photography_style": {     "angle": "High angle, close-up, selfie perspective",     "lighting": "Soft indoor lighting, warm tones, slight shadowing on the neck and side of face",     "focus": "Sharp focus on face and eyes",     "slightly softer background"   } }

{ "prompt": { "subjects": [ { "name": "blonde_woman", "appearance": { "hair": "Long, platinum blonde, straight", "skin_tone": "Fair, lightly bronzed", "eyes": "Dark, wide open, detailed makeup", "lips": "Light pink, open wide in surprise or exclamation", "nose": "Defined, straight bridge", "cheeks": "Slightly flushed, contoured", "expression": "Open-mouthed surprise, looking upward and right" }, "clothing": { "top": "Red bandeau tube top", "bottom": "Light blue denim shorts with white circular details" }, "pose": "Standing behind other woman, hand on her back, leaning forward", "position": "Left side of frame" }, { "name": "brunette_woman", "appearance": { "hair": "Long, dark brown, wavy", "skin_tone": "Medium olive", "eyes": "Dark, looking upwards", "lips": "Nude, slightly parted in a smile", "nose": "Defined, slight curve", "cheeks": "Defined cheekbones, contoured", "expression": "Looking upward with a slight smile" }, "clothing": { "top": "Red ribbed crop top", "bottom": "Black denim shorts", "socks": "White socks with blue patterns" }, "pose": "Bent over at the waist, looking up", "position": "Right side of frame" } ], "environment": { "time": "Night", "location": "Street, parking area", "lighting": "Artificial street and car lights", "background_objects": [ "White sedan (partial, left)", "Grey sedan (right, behind brunette)", "Red octagonal 'STOP' sign on post", "Green rectangular street sign above STOP sign", "Palm trees in background", "Asphalt pavement" ] }, "aspect_ratio": "4:5" } }

Add lots of Korean handwritten doodles, underlines, highlighters, and speech bubbles using a blue colored pencil. The doodles should primarily be compliments about the subject, and it's okay to add a few hand-drawn clip arts.

Re-plate the food to look delicious and Instagrammable. Keep processing such as filters minimal.

Your "pet" becomes a member of the Japan national soccer team!?

We will turn the character in your image into a neon light shining in the night city! [Neon Light Edition] Image-to-Neon light

Using the attached image as a motif, we generated differential images of a woman's face consisting of six scenes divided into a 2x3 grid.

Create an image of this girl visiting the Charles M. Schulz (creator of Snoopy) Museum in America.

Maintain the original person and background as they are. Use a 2x2 grid composition dividing the screen into four equal parts, using four images of the same person. In each frame, change the composition, angle, and viewpoint completely, resulting in different views such as mid-distance, close-up, and profile. A scene of the person playing the piano. Hand-drawn sheet music lines, like those drawn with a crayon, swirl around the body. Yellow stars, musical notes, and doodles are scattered along the sheet music lines. Child's scribble art style drawn directly over the photograph.

{ "layout": { "type": "2x2 grid", "description": "A 2x2 composition dividing the screen into four parts. The same person is used in each frame, changing the distance, composition, angle, and viewpoint in all of them." }, "source": { "mode": "image_reference", "reference_images": { "primary": "base_person_image" }, "preserve": { "same_person": true, "identity_lock": true, "keep_face": true, "keep_hairstyle": true, "keep_outfit": true } }, "subject": { "person": "Japanese woman", "emotion": "hungry but playful, slightly tired, relatable" }, "poses": { "variation_rule": "each frame uses a different composition and angle", "base_shot_type": "middle shot", "frame_variations": [ "sitting at a small apartment table, shoulders slightly slumped, holding her stomach with one hand, faint amused smile", "leaning back in a chair, head tilted up, eyes half-closed, one hand resting on her stomach as if enduring hunger", "standing in the kitchen area, arms loosely crossed over her midsection, looking toward the fridge with a resigned playful expression", "sitting on the sofa, knees drawn slightly up, one hand pressing lightly on her stomach, soft laugh at her own situation" ] }, "accessories": { "handheld_item": "empty plate or nothing in hands" }, "environment": { "location": "small apartment interior", "room_type": "kitchen and living area", "time": "late afternoon", "context": "missed lunch, waiting until dinner", "details": [ "simple dining table", "compact kitchen", "sofa and low table", "everyday lived-in apartment feel" ] }, "lighting": { "primary": "soft natural daylight from window", "secondary": "subtle indoor ambient light" }, "camera": { "shot_type": "middle shot", "lens_feel": "slight wide-angle", "framing": "waist-up, subject centered with gentle variation per frame" }, "color_tone": "natural color, neutral skin tones, realistic indoor daylight balance", "image_quality": { "realism": "photorealistic", "style": "casual everyday snapshot" } }