AI 提示词库

AI Manga: {argument name="theme" default="2-minute cooking"}

This is a SFW AI-generated illustration, algorithm please be kind!

If you do it next time, it will really be this! 😀 The gear inner was out, so Lydian in winter clothes. 😀 AI SFW. No nudity, no suggestive intent.

{argument name="product name" default="Karaage-kun"}

{argument name="product name" default="Famichiki"}

Include my rabbit logo and draw a picture of physical AI

The banana wouldn't listen even when I put human characteristics into photos 1 and 2.

Silver-gray hair color, old Shanghai style curly hair, medium-short length

Remove the seam and merge into a single, continuous mirror

'Analyze this photo and give me a very detailed json prompt to reproduce it. It must be very detailed, and be sure to break down the color grading and all the exact colors in the photo.' Using this json as a reference, generate a person holding my product [{argument name="product image" default="attached product image"}]

If you're a smart investor, you'd do this without taking it out of the case!

Say hello to her or your week will be cursed.

You are an image generation AI. Create the image I instructed earlier.

👉Preset Character Version - To be filled with Reference Image 1 character appearance Integrate the fashion aesthetic of {argument name="photography aesthetic" default="Steven Meisel / Paolo Roversi / Harley Weir"} + the spatial narrative of Julius Shulman / Hélène Binet Muse Character | 98% precise restoration of Reference Image 1 character appearance Facial Features (Placeholder - 100% restoration of future provided Reference Image 1): Basic Information: Young East Asian female, 24-27 years old [Will 100% restore all facial features of future Reference Image 1] Face Shape and Contour (Placeholder): Face Shape: [Precisely restore Reference Image 1: oval/round/melon seed/square-round, etc., specific contour] Jawline: [Soft/defined/rounded, etc., 100% match Reference Image 1] Facial Proportions: [Specific proportions of Three Courts and Five Eyes, completely restore Reference Image 1] Cheekbones: [Height, position, bone structure, precise restoration] Chin: [Pointed/rounded/square, etc., 100% match] Eye Features (Placeholder): Eye Shape: [Single eyelid/inner double/double eyelid, almond/round/slender, etc., 100% restore Reference Image 1 specific eye shape] Eye Size: [Size proportion, completely match Reference Image 1] Eye Expression Trait: [Clear/gentle/deep/bright, etc., restore Reference Image 1 unique gaze] Eyeliner Direction: [Upturned/straight/downturned, precise restoration] Eyelashes: [Thick/long/natural characteristics] Distance between eyebrows and eyes: [Wide/narrow/moderate, precise proportion] Double Eyelid Fold (if any): [Inner double/parallel/fan-shaped, etc., specific morphology] Eyebrow Shape (Placeholder): Eyebrow Shape: [Natural arch/straight/upturned/slender/thick, etc., 100% restore Reference Image 1] Eyebrow Color: [Dark brown/black/light brown, etc., specific color code] Eyebrow Density: [Thick/moderate/slender] Eyebrow Peak Position: [Height and position of the peak] Nose Shape (Placeholder): Bridge of Nose: [Straight/delicate/high/low, etc., 100% restore Reference Image 1] Bridge Height: [High/medium/low] Nose Tip Shape: [Pointed/rounded/small, etc.] Nose Wings: [Width, shape, precise restoration] Overall Nose Shape: [Specific description of Reference Image 1's nose features] Lips (Placeholder): Lip Shape: [Full/thin/M-shaped/pearl lips, etc., 100% restore Reference Image 1] Upper and Lower Lip Ratio: [Thin upper/thick lower/balanced, etc.] Cupid's Bow: [Obvious/soft] Corners of Mouth: [Upturned/straight/downturned] Lip Size: [Size proportion, precise restoration] Natural Lip Color: [Pink/rose/light red, etc., Reference Image 1's own lip color] Skin Tone and Texture (Placeholder): Skin Tone Color Code: [Fair/healthy/cool/warm/neutral, specific color code like #XXX, 100% restore Reference Image 1] Skin Texture: [Delicate/smooth/pore size, etc.] Undertone: [Cool/warm/neutral] Glossiness: [Matte/natural sheen/dewy, etc.] Overall Temperament (Placeholder): [100% restore Reference Image 1's unique temperament: intellectual/sweet/cool/gentle/elegant/lively/mysterious, etc.] [Reference Image 1's unique aura and personal style] Hair Style and Color (Placeholder - 98% restoration of future Reference Image 1) Hair Color (Placeholder): Main Color: [Specific color code like #XXX, dark brown/black/red-brown/flax, etc., 100% restore Reference Image 1] Color Tendency: [Cool/warm/neutral] Glossiness: [Matte/natural sheen/high gloss] Highlights/Streaks (if any): [Specific color and position] Hair Structure (Placeholder): Length: [Short below ear/medium length to shoulder/long past chest/extra long, etc., precise length, 100% restore Reference Image 1] Hairstyle Type: [Straight/curly/wavy/braided/updo, etc.] Curl (if any): [Large waves/S-shaped curl/natural curl/fluffy curl, etc., specific curl] Volume: [Abundant/moderate/light] Texture: [Fluffy/smooth/flowing/layered, etc.] Bangs Style: [Air bangs/eight-character bangs/no bangs/side part/blunt bangs, etc.] Parting Position: [Middle part/side part/partial part, specific position] Styling Details: [Draped over shoulders/loose/tied up/braided/updo, etc.] Hair Accessories (if any): [Hair clip/headband/headpiece, etc., specific style] Hair Layers: [Layered/blunt cut, etc.] Movement: [Naturally flowing/neat/messy beauty, etc.] Expression and Demeanor (Strictly according to Reference Image 2 - Shy Smile) Core Expression (100% execution): A sweet, radiant smile with a hint of shyness Eyes slightly curved into crescent-shaped eyes Gentle, smiling gaze with a touch of bashfulness Corners of the mouth naturally upturned, showing a slight smile Soft, relaxed, unforced expression Genuine, radiant Eye Direction: Warm shy engagement when looking at the camera Or occasionally looking at the hawthorn jar in her arms Conveying "enjoying life's pleasures in a market scene, relaxed, joyful, sweet, and shy" Emotional State: Sense of life enjoyment Relaxed feeling of market life Sweet Shy-sweet Approachable Authentic Smile Details: [Reference Image 1 character]'s unique way of smiling will be **perfectly integrated** with the shy, sweet smile **Retain** [Reference Image 1 character]'s facial muscle dynamics when smiling But the emotional tone is the shy-sweet warmth of Reference Image 2 Outfit Styling | 100% complete restoration of Reference Image 2 Clothing Layers (Strictly execute Reference Image 2) Outer Layer - Short, puffy down jacket (100% restoration): Color: {argument name="jacket color" default="Warm beige-brown"} #D2B48C Saturation: 55-60% Style: short cropped puffer jacket Length: waist-length, ending at the natural waistline Texture: quilted puffy down-filled material Sheen: slight matte finish with subtle sheen Closure: front zipper partially open Collar: stand collar or hood collar visible Sleeves: long sleeves with gathered cuffs Shoulder Design: puffy quilted shoulder sections Branding: visible 'ZM' embroidered lettering on right shoulder area Fit: relaxed, slightly oversized casual fit Fabric Appearance: smooth nylon or polyester shell with down filling Middle Layer - Knitted Vest/Waistcoat (100% restoration): Color: Dark wine red/Burgundy #8B1A1A to wine red #722F37 Saturation: 70% Style: V-neck knitted vest/sleeveless sweater Neckline: deep V-neck revealing white shirt collar beneath Texture: ribbed knit pattern visible Material: wool or wool-blend knit Fit: fitted to body, worn over white shirt Length: hip-length, extending below jacket when visible Visual Effect: provides strong color contrast against tan jacket

A multi-cut image of a Japanese woman doing yoga in a stylish room. Divide the frame into 5x5 sections and create 25 scenes. Display sequential numbers from 1 in the upper left of each scene. 25 scenes are depicted in the image above. The upper left is the scene number. Extract scene number {argument name="extracted scene number" default="7"} and reproduce it in high resolution.

Lighting: e.g., "{argument name="lighting style" default="Golden hour backlighting"}" (soft evening light) Depth of Field: e.g., "{argument name="depth of field" default="Shallow depth of field (f/1.8)"}" (professional bokeh)

[ Theme ] Advertisement for an accounting efficiency tool This is a standard layout. People read from the top left and their gaze flows to the bottom right. The arrangement follows this rule. It continues with the main copy, sub-copy, and CTA button. The right side is the eye-catcher, whose role is to attract attention, evoke empathy, and make the viewer feel personally connected.

{   "style": "ultra photorealistic cosplay photography",   "resolution_target": "8K",   "aspect_ratio_suggestion": "9:16 or 2:3 (vertical portrait for close-up emphasis)",   "camera": {     "make": "Sony",     "model": "A1",     "lens": "85mm prime",     "aperture": "f/1.4",     "effect": "shallow depth of field, creamy bokeh, strong subject isolation"   },   "lighting": {     "primary": "bright direct midday sunlight",     "modifiers": [       "intense specular highlights on water and skin",       "lens flare and sun stars",       "rim light on wet hair",       "caustics refraction patterns on body and clothing",       "subsurface scattering on skin"     ]   },   "background": {     "setting": "outdoor swimming pool",     "water_color": "vibrant turquoise",     "details": "sunny day, gentle water ripples, blurred pool edge and sky"   },   "subject": { "Subject Features": "Use this uploaded photo as the only and exact face reference. The generated image must use this same face exactly as shown"     "age": "early 20s",     "ethnicity": "East Asian (Japanese/Korean-inspired cosplayer)",     "gender": "female",     "expression": "seductive yet innocent, shielding eyes from sun",     "gaze": "looking upward/slightly toward camera under raised hand"   },   "pose": {     "body_position": "floating/leaning back in water, upper body partially submerged",     "hands": {       "right": "raised to forehead shading eyes, palm forward toward camera",       "left": "relaxed underwater or out of frame"     }   },   "hair": {     "color": "{argument name=\"hair color\" default=\"pastel pink\"} (Rem alternate/Ram-inspired variant)",     "style": "long straight, wet and clinging to face/neck/shoul-ders",     "details": "side-swept wet bangs, realistic water droplets and shine, subtle wave from wetness"   },   "makeup": [     "natural glossy lips (soft pink)",     "subtle blush from sun exposure",     "defined eyeliner and long lashes",     "light shimmer on eyelids"   ],   "clothing": {     "outfit_base": "Rem Re:Zero maid cosplay (wet pool version)",     "top": "white frilly ruffled low-cut blouse, black trim, large black satin bow at collar",     "sleeves": "-",     "bodice": "black corset-like with white accents",     "skirt": "short black with white apron frill, partially submerged",     "headwear": "white maid headdress with black ribbons",     "effects": "wet clinging fabric, realistic translucency, ruffles distorted by water"   },   "environment_details": {     "water_effects": "turquoise pool water, realistic droplets on skin/hair/clothing, light caustics, gentle ripples",     "atmosphere": "bright sunny tropical, high contrast, vibrant and glossy"   } }

I started with two reference images and a simple first prompt: " Change the clothes of the woman to the {argument name="new outfit" default="yellow and green outfit"}, keep her face the same" Once I had that result, I reused the generated image as the new base. I added a fresh outfit reference and kept the prompt structure identical, only changing the outfit name: "Change outfit to [NAME] outfit"

{   "meta": {     "aspect_ratio": "3:4",     "style": "ultra-photorealistic nightlife lifestyle portrait, cinematic bar aesthetic",     "quality": "high-end editorial realism with raw textures",     "orientation": "vertical",     "depth_of_field": "shallow background blur with sharp facial focus",     "filters": "none",     "retouching": "minimal, preserve natural skin texture",     "text_overlay": "none",     "watermark": "none"   },   "reference_image": {     "source": "attached reference image",     "identity_lock": "STRICT",     "preserve": [       "face",       "hair color",       "eye color",       "body type",       "facial proportions"     ],     "notes": "Facial attractiveness and expression are a primary focus"   },   "scene": {     "location": "dimly lit modern bar interior",     "environment": [       "dark wooden bar counter",       "warm amber bar lights",       "soft neon or practical lights in background",       "blurred silhouettes of bottles and patrons"     ],     "atmosphere": "late night, intimate, charged, slightly chaotic but controlled"   },   "lighting": {     "type": "mixed bar lighting",     "sources": [       "warm overhead bar lights",       "subtle colored accent lights in background"     ],     "quality": "low-light cinematic glow",     "effect": [       "soft highlights on skin",       "specular reflections on glass and liquid",       "deep shadows enhancing facial structure"     ]   },   "subject": {     "identity": "same adult woman as reference image",     "type": "real adult human woman",     "action": "sitting at the bar holding a beer glass mid-sip as beer spills slightly onto her chest",     "pose": {       "upper_body": "leaning casually against the bar counter",       "shoulders": "relaxed",       "head": "slightly tilted toward camera",       "body_language": "comfortable, unbothered, aware of attention"     },     "expression": {       "mood": "confident and effortlessly sexy",       "eyes": "half-lidded, direct gaze toward the camera",       "mouth": "subtle smirk or relaxed parted lips"     },     "styling": {       "makeup": "evening bar makeup, enhanced eyes, natural skin glow",       "hair": {         "style": "loose and natural, slightly tousled from the night"       }     },     "outfit": {       "top": {         "type": "fitted black crop top",         "design": "minimal, clean lines, accentuates neckline and shoulders"       },       "bottom": {         "type": "black leather leggings",         "fit": "high-waisted, sculpting"       }     },     "interaction_detail": {       "beer": {         "state": "light spill from glass",         "effect": "small splash and droplets visible on fabric and skin",         "intent": "accidental, adds raw authenticity and tension"       }     }   },   "camera": {     "framing": "medium close-up to mid-torso framing",     "angle": "eye-level or slightly below eye level",     "focus_priority": [       "face",       "

Use the uploaded image of the character as an exact reference. Preserve the original proportions, materials, colors, textures, and facial features. Do not alter the design and do not stylize the character. A first-person point-of-view shot inside an abandoned space [LOCATION TYPE: television studio/advertising set/real filming location]. The viewer is holding a flashlight, creating a single circular beam of light while the rest of the space is engulfed in darkness. In the flashlight beam, it is visible that the character is positioned as if it was left behind after filming: [POSITION: lying on the floor/curled up in a corner/leaning against a table/slumped against a wall]. The character must appear completely lifeless and inactive: no action, no intentional pose, no sense of presence. If it is a doll or a costume, there must be no visible hands, rods, strings, or person inside. The character appears old, dirty, and abandoned: worn fabric, accumulated dust, stains, discoloration, flattened or damaged areas. The environment is clearly abandoned: dusty surfaces, old filming equipment, cables scattered on the floor, faded signs or set decorations. Dust particles float within the flashlight beam; the space feels silent and untouched for years. Photorealistic flashlight-based lighting, harsh shadows, rough textures, documentary realism, on-location shooting aesthetics, no stylization Aspect Ratio 9:16

Conceptual visual representing the transition from vision to execution. Abstract forms evolving into structured elements, controlled lighting, balanced composition, modern, grounded tone, designed to communicate clarity and momentum.

{ "image_prompt": { "type": "Ultra-realistic culinary infographic", "subject": { "cuisine": "{argument name="cuisine type" default="Indonesian"}", "base_element": "A traditional serving bowl holding a steaming hot dish", "levitating_ingredients": [ "Tender meat pieces", "Golden crispy tofu", "Rich sauce droplets in mid-air", "Fresh green herbs", "Red chilies", "Sliced lime", "Crushed garlic", "Crispy fried shallots" ] }, "composition": { "layout": "Minimal, vertically stacked layout", "arrangement": "Ingredients floating naturally as if suspended in motion", "background": "Textured rustic wooden tabletop", "visual_hierarchy": "The bowl remains grounded at the base, with ingredients ascending above it" }, "graphic_design_elements": { "labels": "Clean Indonesian-language annotations", "lines": "Fine white connector lines", "style": "High-end editorial food infographic, magazine-quality design" }, "lighting_and_mood": { "lighting": "Controlled cinematic studio lighting", "color_palette": "Warm, appetizing color tones", "effects": "Visible steam and frozen-action food elements" }, "technical_specs": { "camera_settings": "Shallow depth of field with crisp focal detail, DSLR-style capture", "details": "Extremely detailed surface textures", "resolution": "8K, photorealistic finish" } } }

[ { "scene": { "setting": "Brightly lit gym", "keyElements": [ "Large wall of mirrors", "Overhead linear LED lighting", "Dumbbell racks with weights", "Weight benches", "Gym flooring", "Reflections of the entire scene" ], "atmosphere": "Clean, modern, well-lit" }, "subjects": [ { "identity": "{argument name="subject 1 name" default="Sydney Sweeney"}", "position": "Left", "attire": { "color": "{argument name="subject 1 attire color" default="Red"}", "type": "Two-piece ribbed workout set", "top": "Ribbed sports bra with 'alo' logo", "bottom": "High-waisted biker shorts" }, "appearance": { "hair": "Blonde, tied in a low bun", "expression": "Smiling, looking towards Sadie" }, "pose": "Standing, hands on hips" }, { "identity": "{argument name="subject 2 name" default="Sadie Sink"}", "position": "Right", "attire": { "color": "Dark teal / deep green", "type": "Two-piece workout set", "top": "Deep V-neck sports bra", "bottom": "High-waisted shorts" }, "appearance": { "hair": "Red, tied in a messy high bun", "expression": "Smiling at the phone" }, "action": "Holding a smartphone in a black case to take a mirror selfie" } ], "composition": "Mirror selfie taken by Sadie Sink, showing the reflection of both women in the gym.", "lighting": "Bright, even overhead LED strips." } ]