AI Image Prompts Database

Browse 540+ free AI image prompts for GPT Image 2, Midjourney, Dall-E and more. Every prompt is shown with the picture it produced: copy it, then edit or remix it in our image tools.

540+ Prompts 5 Platforms 100% Free
Image workflow tools

Found a prompt? Turn it into a finished image.

Use the image tools to generate from scratch, edit an existing result, upscale details, remove backgrounds, extend a frame, or repair a specific area.

High-Fashion Tiered Ballgown Editorial

GPT Image 2
High-Fashion Tiered Ballgown Editorial (Photography style, made with GPT Image 2) - AI image prompt example

A photorealistic high-fashion editorial photograph of a young {argument name="ethnicity" default="Asian"} woman with a slim-thick hourglass figure, tall statuesque stature approximately 170cm, well-proportioned with smooth fair skin. She stands on an elegant interior staircase in a precise, dynamic pose: leaning slightly backward, head tilted fully up in joyful laughter, right hand firmly gripping a sleek black staircase railing, left hand resting confidently on her hip. She wears a dramatic, voluminous tiered ballgown crafted from brushed, paint-effect fabric that cascades down the stairs. The gown features a striking 2026 color trend ombré: {argument name="gown colors" default="vibrant electric chartreuse at the bodice, transitioning through bright lime green tiers, and fading into deep forest-charcoal"} at the sweeping hem. Her dark hair is pulled into a sleek, polished low bun. Natural daylight floods through large arched windows, creating luminous highlights on the textured chartreuse fabric and soft shadows across the marble steps. Shot on {argument name="lens" default="50mm"} lens, f/2.8, sharp focus on expression and gown details, high-end fashion magazine aesthetic.

Kyoto Anime Travel Meme Panel

GPT Image 2
Kyoto Anime Travel Meme Panel (Anime / Manga style, made with GPT Image 2) - AI image prompt example

Create a colorful single-panel anime travel meme postcard set in Kyoto. Canvas: landscape 4:3 composition with a thin black rounded border, like the first panel of a four-panel comic. In the top-left corner, place a small white rounded square label containing the black number “1”. Background: a bright spring Kyoto street scene with traditional wooden machiya houses, stone-paved road receding into the distance, a large multi-tiered pagoda near the center-right, Kyoto Tower visible far in the distance, blue sky, mountains, and pink cherry blossoms overhead with petals drifting through the air. Foreground: on the right half, draw an elegant anime-style young woman wearing a pale yellow floral kimono with a dark navy obi, posed like a welcoming guide with one hand extended toward the city. She has vivid {argument name="hair color" default="blue"} shoulder-length wavy hair and a decorative flower hair ornament with dangling gold tassels. Her face is intentionally covered by a large opaque square censor block with a vertical blue-gray to beige gradient, centered over the face and obscuring all facial features. Text: on the upper-left and center-left, add large hand-brushed Japanese calligraphy reading {argument name="headline text" default="京都へ おこしやす"}, with “京都へ” in dark red and “おこしやす” in dark navy, plus a red swoosh underline and two small flower icons. Style: polished GPT-image anime illustration, clean line art, saturated spring colors, soft sunlight, high detail in architecture and kimono pattern, cheerful tourism-poster mood. Constraints: include exactly one numbered panel label, exactly one foreground character, exactly one face-covering square, and do not add extra captions, watermarks, speech bubbles, or additional characters.

Fashion Editorial Illustration Sketch

GPT Image 2
Fashion Editorial Illustration Sketch (Sketch / Line Art style, made with GPT Image 2) - AI image prompt example

Transform this photo into an {argument name="illustration style" default="expressive high-fashion editorial illustration"} while preserving the person’s identity, facial structure, hairstyle, and recognizable features. Convert the portrait into a {argument name="drawing style" default="minimalist hand-drawn fashion sketch"} with elegant elongated proportions. Use bold black ink contour lines, loose confident brush strokes, slightly imperfect asymmetrical hand-drawn linework, simplified facial anatomy, stylized almond-shaped eyes, minimal nose details, and expressive graphic lips. Apply flat marker color rendering with a limited sophisticated palette, artistic abstract blush patches under the eyes, subtle colorful eye makeup accents, and semi-abstract graphic shading. Render hair as bold expressive ink masses with visible white highlight gaps. Simplify clothing into large geometric color blocks with editorial fashion illustration styling. Clean white background, scanned marker-on-paper texture, {argument name="publication aesthetic" default="modern Vogue"}

East Asian Woman Cinematic Portrait

GPT Image 2
East Asian Woman Cinematic Portrait (Cinematic / Film Still style, made with GPT Image 2) - AI image prompt example

Ultra realistic close-up portrait of a beautiful young {argument name="ethnicity" default="East Asian"} woman with the exact facial structure and soft feminine features from the reference image, natural glowing skin, subtle makeup, glossy {argument name="lip color" default="peach"} lips, soft dimples, warm gentle smile, relaxed confident expression, medium-length {argument name="hair color" default="dark brown"} wavy hair with natural volume and soft flyaways, direct eye contact with camera. Keep the exact composition, framing, pose, lighting, shadows, and cinematic mood from the original portrait reference. Warm golden hour sunlight hitting half of the face and body, dramatic soft shadows across the chest and background, dark blurred background with rich contrast and shallow depth of field. Outfit should be elegant minimal aesthetic fashion: cream ribbed knit top, soft beige wool overcoat casually draped over shoulders, delicate gold necklace, luxury clean-girl aesthetic, cozy premium fashion vibe.

High-End Fashion Collage Poster

GPT Image 2
High-End Fashion Collage Poster (Poster / Flyer style, made with GPT Image 2) - AI image prompt example

High-end portrait collage poster in vertical format. The background contains four layered rounded strips displaying black-and-white film-like images of a {argument name="model description" default="curly-haired male model wearing dark sunglasses"} in varied poses. In front, a vivid color cutout of the same character is placed to the left, dressed in an {argument name="clothing" default="unbuttoned soft pink shirt"}, styled like a {argument name="campaign style" default="luxury fashion campaign"} with dramatic lighting and depth.

Interior Selfie Perspective Layout

GPT Image 2
Interior Selfie Perspective Layout (Photography style, made with GPT Image 2) - AI image prompt example

Single-person realistic indoor mobile phone selfie landscape, narrow corner scene, close-up shot from chin to mid-upper thigh, simple background, focus on upper body curves, short skirt sitting posture, leg perspective, and warm lighting. Subject Characteristics: Young female feel, face basically not in frame, only showing a small amount of chin and neck; light blue long curly hair hanging from both sides to the chest. The body is characterized by a slender upper body, fuller chest, significantly tightened waistline, tucked pelvis, fair and straight legs, overall a light cosplay feel, soft but with clear curves. Clothing and Materials: Top is a white long-sleeved shirt with vertical ruffles and small buttons on the chest, smooth and slightly shiny fabric, slightly puffed sleeves; bottom is a gray-black checkered high-waisted short pleated skirt, with a black waistband, thin fabric, skirt naturally flares out and folds after sitting. Bare legs, no shoes/socks info. Action, Camera, Composition Template: Person sitting on gray tile floor, back and left shoulder near the corner, torso leaning forward slightly, right arm extended holding phone for a selfie, left hand naturally holding a doll by the side. Knees forward, legs extended toward the camera, forming a continuous downward-pressing perspective of chest-waist-skirt-thighs. Camera is located slightly higher in the upper right front, shooting downwards, cropping the top of the head and most of the face, making the chest, waistline, skirt, and thighs the main subjects; left white wall and mirror frame, right dark door panel provide a sense of enclosed space, blue doll in the bottom left corner as an auxiliary anchor. Style and Controls: Style: Realistic daily mobile phone selfie, indoor warm yellow ceiling light/side-top light, brighter on the left, darker on the right, overall low contrast, clean and pale skin tone, soft shadows. Key Anchors: Light blue long curly hair hanging in front of chest, white slightly shiny shirt, gray-black checkered short skirt, sitting on floor leaning forward for selfie, obvious chest-waist-leg perspective, left-bright-right-dark warm light. Negative Constraints: Do not show full face, no standing or kneeling posture, no cold white light, no hard flash, do not make legs too long, do not use wide-angle exaggerated distortion, no complex background, do not miss the left doll and the oppressive feeling of the corner.

Fashion Editorial Blueprint Sheet

GPT Image 2
Fashion Editorial Blueprint Sheet (Photography style, made with GPT Image 2) - AI image prompt example

Fashion blueprint sheet of a stylish young woman posing beside a {argument name="wall color" default="bright orange"} wall, half-body fashion editorial view with detailed outfit annotations and luxury styling callouts. Long sleek {argument name="hair color" default="dark"} hair, soft glam makeup, silver drop earrings, layered silver necklaces, fitted dark brown cropped tube top, oversized pastel {argument name="blazer color" default="mint-green"} blazer with structured shoulders, matching high-waisted wide-leg trousers, elegant silver chain detail attached to blazer, relaxed confident pose with one hand in pocket. Surrounding the model are fashion infographic elements, jewelry breakdowns, fabric texture descriptions, tailoring notes, pose analysis, accessory close-ups, cinematic sunlight reflections, modern Korean street-fashion aesthetic, editorial photography style, ultra detailed, professional fashion concept sheet, 8k, 1744x2336

Realistic Korean Schoolgirl Portrait

GPT Image 2
Realistic Korean Schoolgirl Portrait (Photography style, made with GPT Image 2) - AI image prompt example

Use the uploaded reference image as the exact facial identity reference for the {argument name="girl" default="girl"}. Maintain the same facial structure, eyes, nose, lips, hairstyle, skin tone, beauty details, and overall appearance consistency throughout the image. Ultra-realistic portrait of the same girl from the reference image standing beside the large classroom windows in an {argument name="Korean classroom" default="empty Korean classroom"} during daytime, posing from the front side while looking directly at the camera with a soft calm smile. One hand gently resting in her hair, relaxed confident posture, modern youthful Korean fashion aesthetic. Wearing a {argument name="clothing" default="fitted long black ribbed top"} with full sleeves and light gray washed jeans, elegant casual styling. Long silky black hair flowing naturally, glossy eyes, soft natural blush makeup, realistic skin texture, dreamy youthful Korean beauty aesthetic. Bright natural sunlight streaming through the classroom windows, creating soft cinematic highlights and realistic shadows across the room. Authentic Korean classroom interior with wooden desks, black chairs, green chalkboard, South Korean flag on the wall, clean neutral walls, polished floors, and trees visible outside the windows. Calm slice-of-life atmosphere, minimalist Korean school aesthetic, candid model pose, soft daylight photography, shallow depth of field, cinematic composition, highly detailed, photorealistic classroom environment, luxury lifestyle editorial feel, soft glow, realistic DSLR photography, peaceful modern mood.

Taisho Romantic Cafe Trio

GPT Image 2
Taisho Romantic Cafe Trio (Anime / Manga style, made with GPT Image 2) - AI image prompt example

Create a vertical anime illustration of exactly 3 elegant young women in a Taisho romantic cafe setting, a refined Japanese-Western fusion interior filled with warm lantern light, dark carved wood, stained-glass windows, lace curtains, antique furniture, framed paintings, and vases of flowers. The three women wear ornate wa-lolita maid cafe outfits combining kimono sleeves, floral-patterned haori, ruffled white aprons, black lace trim, ribbon bows, and frilled maid headdresses. Character 1 is seated on the left, with very long black hair and a deep red floral kimono-style outfit; Character 2 stands behind them in the center, with short {argument name="hair color" default="lavender"} bob hair, a purple floral kimono jacket, white ruffled blouse, black gloves, and a gentle smile; Character 3 is seated on the lower right, with very long black hair and a teal-blue floral kimono-style outfit. Compose them closely together like a formal cafe portrait, with graceful poses and delicate hands. Use a highly detailed modern anime style with soft painterly shading, intricate linework, muted jewel tones, cream lace, gold accents, and nostalgic early-20th-century Japanese romantic atmosphere. Add an ornate decorative border around the image with large cream and red peonies, flowing gold vines, teal and burgundy patterned panels, and art-nouveau curves. Keep the faces beautiful and expressive, no blur or censoring, no text, no watermark, no extra characters.

Monochrome Engraved Portrait

GPT Image 2
Monochrome Engraved Portrait (Photography style, made with GPT Image 2) - AI image prompt example

Black and white engraved portrait illustration of a {argument name="subject" default="person"}. Drawn in classic {argument name="art style" default="woodcut / linocut engraving style"}, high contrast black ink on {argument name="paper texture" default="textured off-white paper background"}. Fine cross-hatching and line shading to create depth and shadow, bold black ink shadows under chin and around hair, strong contour lines, traditional printmaking aesthetic. Minimal composition, centered portrait, no body visible, clean negative space, vintage editorial illustration style, ultra detailed linework, sharp crisp ink strokes, professional vector-ready engraving look, monochrome palette, dramatic contrast. Negative Prompt: color, watercolor, soft shading, blurred lines, low contrast, realistic photography, 3D render, anime style, cartoon style, messy sketch, thick uneven strokes, background objects, noisy texture, pixelated, distorted face, extra eyes, extra ears, bad anatomy, modern digital painting, glossy skin, overexposed highlights

Whimsical Folk Art Window Scene

GPT Image 2
Whimsical Folk Art Window Scene (Cinematic / Film Still style, made with GPT Image 2) - AI image prompt example

Create a whimsical hand-drawn folk-art illustration with a textured crayon, marker, and gouache look. Show an indoor wall scene filled with decorative floral doodles and bright handmade charm. In the foreground, place an adult woman presenter with {argument name="face style" default="a plain featureless tan square covering the face"}, dark center-parted hair, a black jacket, and a vivid red dress with a rounded red collar, black buttons, and drawstring details; she stands on the right half of the canvas and extends her left arm open toward a large window display. On the left, draw one large cream-colored double window with two tall panels and black hinges, decorated with tiny hearts, dots, and blue leafy borders. Behind the left window, show exactly one seated trumpet player: blue pants, dark jacket, curly gray hair, red cheek, holding a yellow trumpet, with black musical notes floating around; the pink background behind him contains leafy sprigs, white dots, yellow starbursts, and a handwritten vertical date-like note reading {argument name="window note" default="Feb / 13"}. On the far right, draw a second window with a golden yellow frame, teal curtains, pale lace trim, and a green garden-like view filled with flowers and vines. Between the woman and the left window, include a small wall poster reading {argument name="poster text" default="ACQUA PER LA VITA – WATER FOR LIFE"} with blue wave lines. Count and include exactly two windows, one presenter, one trumpet player, one poster, and two visible black musical notes. Surround everything with playful decorative motifs: red hearts, blue leafy branches, pink and red flowers, yellow starbursts, green vines, multicolored dots, and small white speckled texture. Use an off-white background, naïve proportions, thick black sketchy outlines, visible paper grain, and a cheerful Italian folk-art mood. Avoid photorealism, shadows, or digital polish; make it look handmade and slightly imperfect.

Censored Anime Host Portrait

GPT Image 2
Censored Anime Host Portrait (Anime / Manga style, made with GPT Image 2) - AI image prompt example

Create a polished anime-style half-body portrait of an extremely handsome adult man standing in an upscale high-rise bar at night, with a dramatic city skyline visible through tall windows behind him. He has {argument name="hair color" default="platinum blond"} layered tousled medium-length hair with long side bangs and sharp luminous highlights, an elegant neck and broad shoulders, and a confident fashionable presence. His face should be mostly obscured by a centered square privacy censor block in a warm beige-to-dark-gray vertical gradient, covering the eyes, nose, and mouth while leaving hair, ears, jawline edges, neck, and upper torso visible. Dress him in a cream-white tailored blazer over an unbuttoned black dress shirt with exactly 3 visible gold buttons, open low enough to reveal a toned chest and collarbones. The background should show exactly 2 main environment zones: on the left, a nighttime skyscraper cityscape with many blue-white window lights and red antenna dots; on the right, a warm luxury bar shelf area with dark wood, golden lighting, bottles, and a glowing rectangular wall sconce. Use cinematic warm indoor lighting mixed with cool blue city light, crisp clean line art, soft cel shading, glossy highlights, a slightly romantic host-club atmosphere, vertical portrait composition cropped at mid-torso, no text, no watermark, no extra characters.

Ballpoint Pen Style Sneaker Sketch

GPT Image 2
Ballpoint Pen Style Sneaker Sketch (Sketch / Line Art style, made with GPT Image 2) - AI image prompt example

Transform this photo into a {argument name="style" default="rough ballpoint pen sketch"} for a stylish look.

Candid Identity Reference Portrait

GPT Image 2
Candid Identity Reference Portrait (Photography style, made with GPT Image 2) - AI image prompt example

Ultra-realistic, almost indistinguishable-from-real close-up portrait in a casual phone photo style. Use the uploaded image as the identity reference, fully preserving the natural appearance and atmosphere of the same woman. The face and overall appearance must remain 100% identical to the reference image, without altering any facial proportions or features. Do not change: Lip shape or lip size Eyes Nose Face shape Overall facial harmony and identity Full photorealism. No AI-generated feeling — it should look like a random candid photo taken on a mobile phone. Not a polished glossy beauty shoot, but a natural, slightly imperfect phone snapshot. Close-up portrait framed to shoulder level. Soft and elegant pose. Face slightly turned to the side. No direct eye contact with the camera — natural sideways gaze. Expression calm, natural, almost neutral. The image should feel like a spontaneously captured moment rather than a posed photoshoot. Hair styled in a natural slightly messy updo. Face-framing bangs and loose strands around the face. A few flyaway hairs and subtle disheveled texture. Effortless beauty aesthetic with imperfectly styled hair. Ultra-natural skin texture with realistic pores and subtle imperfections. Soft mobile-phone lighting, realistic shadows, natural tonal range, authentic candid atmosphere. The overall result should resemble a genuine smartphone portrait captured casually in real life, with cinematic realism and natural feminine elegance.

Windblown Rose Garden Portrait

GPT Image 2
Windblown Rose Garden Portrait (Photography style, made with GPT Image 2) - AI image prompt example

Create a cinematic low-angle fashion photograph of {argument name="subject" default="a young woman"} standing in a lush red rose garden during golden hour, viewed from below as if the camera is among the flowers. She wears a flowing, semi-sheer {argument name="dress color" default="ivory white"} vintage lace dress with long translucent sleeves, ruffled high collar, delicate embroidery, and soft layered fabric. Her long {argument name="hairstyle" default="brown hair in two loose braids"} is windblown dramatically, with loose strands streaming across the sky. The face is intentionally obscured by a centered matte tan square censor block. Surround her with blooming red roses on both sides and in the foreground, with large blurred roses close to the lens at the lower right and lower center for depth. Fill the air with red rose petals caught in motion, distributed across the sky and foreground, some sharply defined and others motion-blurred. Use a bright blue sky with scattered white clouds, strong warm sunlight flaring from the lower left, backlighting the dress and hair to create glowing edges. The mood should be romantic, surreal, and high-fashion, with shallow depth of field, dynamic wind, warm orange highlights, rich red petals, natural film grain, and an ultra-realistic editorial photography style. Use a vertical {argument name="aspect ratio" default="3:4"} composition, dramatic perspective, no text, no watermark.

Advanced Physics Paradox Infographic

GPT Image 2
Advanced Physics Paradox Infographic (Infographic style, made with GPT Image 2) - AI image prompt example

16:9 -> class theoretical_physics_infographic_dna: def __init__(self): self.subject = "[{argument name="topics" default="4 distinct advanced physics theorems or paradoxes (e.g., bell's theorem, hawking radiation, string theory)"}]" self.parents = { "composition_parent": "large hadron collider blueprints — hyper-complex radial symmetry, intersecting particle beam rings, millimeter-precise drafting", "atmosphere_parent": "deep space observatory photography — pitch black voids, glowing ultraviolet radiation, high-contrast laser illumination", "graphic_parent": "chalkboard maximalism — elegant, dense mathematical notation floating as glowing white vectors", "detail_parent": "victorian brass optical instruments — finely milled prisms, glass lenses, and mirrored refraction planes" } self.mutations = { "medium_mutation": "the mathematical formulas solidify into glowing, three-dimensional glass sculptures bending the light around them", "information_mutation": "particle collision tracks are woven like fine gold thread through the dark background", "semantic_mutation": "the invisible physical law is rendered as a massive, tangible, gravitational machine distorting the grid of the poster itself" } def generate_grid(self): instruction = """ generate a 2x2 grid of vertical luxury infographic posters giving physical form to the chosen [subject]s. invent a magnificent scientific machine or optical diorama for each. explode the layers to show quantum states, gravitational warping, equations, and subatomic scale. the design must feel like a classified schematic from a hyper-advanced, aesthetically obsessed civilization. semantic inference must make the invisible laws of physics breathtakingly visible. """ return render( instruction, format="2x2 grid, vertical luxury posters, conceptual scientific infographic", typography=""" large title: [name of theorem/paradox] subtitle: [the physicist / the era] microtext: [the core equation / metric tensor / explanatory blazon] """, composition="strict radial or gravitational-well symmetry. razor-sharp fine lines contrasting with deep voids.", lighting="harsh, clinical laser light interacting with pure optical glass and vantablack.", constraints="no cartoon atoms, no clip-art planets, no messy chalkboards. only pristine, museum-grade scientific aesthetic." )

Morning Subway Fashion Portrait

GPT Image 2
Morning Subway Fashion Portrait (Photography style, made with GPT Image 2) - AI image prompt example

Create a photorealistic vertical portrait of a young woman standing in an underground train station corridor in the morning. She has {argument name="hair color" default="long rose-gold pink hair with soft waves and darker roots"} and wears {argument name="outfit" default="a fitted white ribbed turtleneck sweater mini dress with long sleeves"}. Her face is intentionally obscured by a plain centered rounded square blur/mask in a muted taupe color, covering all facial features while leaving hair visible. She stands slightly right of center, full body from head to mid-thigh visible, left arm relaxed at her side, right arm extended with fingertips touching the tiled wall. The corridor is long and cool-toned, with glossy wet-looking gray floor tiles, white rectangular wall tiles on the right, fluorescent ceiling lights receding into the distance, a blurred station sign overhead, and a few distant commuters as dark silhouettes in the background. Use shallow depth of field with the woman sharply focused and the background softly blurred, cinematic realistic lighting, cool blue-green subway ambience, subtle reflections on the floor, natural body proportions, high detail fabric texture, and a candid fashion-street-photo feeling. Add a small four-point sparkle/star watermark-like symbol in the bottom-right corner. No readable text, no extra people in the foreground, no exaggerated pose.

Night Baseball Stadium Action

GPT Image 2
Night Baseball Stadium Action (Cinematic / Film Still style, made with GPT Image 2) - AI image prompt example

Create a photorealistic wide-angle night baseball game scene from a low camera position just behind home plate, as if shot with a professional sports camera. The main subject is a right-handed batter in a {argument name="batting team uniform" default="white and gray away uniform with black helmet"} standing in the left foreground, bat raised and ready to swing. Directly behind him are exactly 2 crouched figures: a catcher in dark navy protective gear and an umpire in black uniform leaning forward. On the field show exactly 4 additional visible players: the pitcher in a {argument name="pitching team uniform" default="dark navy jersey and white pants"} mid-delivery on the mound, one infielder near second base, one fielder on the far right, and one distant fielder near the outfield. The baseball should be visible in midair traveling from the pitcher toward the plate. Set the scene in a packed stadium at night with bright floodlights, green outfield walls, a brown dirt infield, crisp white chalk batter's box lines, and a lush green grass field. In the upper right background include a large illuminated Japanese-style scoreboard filled with inning numbers, team rows, colorful statistics, and dense small Japanese text, without needing perfectly readable characters. The stands should be crowded with thousands of spectators wearing mostly light clothing, creating a realistic textured crowd. Use dramatic stadium lighting, deep shadows, high ISO sports photography realism, natural motion tension, sharp foreground detail, slightly softer distant crowd, cinematic 16:9 composition, no watermark, no added captions.

National Sports Celebration Poster

GPT Image 2
National Sports Celebration Poster (Poster / Flyer style, made with GPT Image 2) - AI image prompt example

Create an ultra-detailed cinematic national sports poster inspired by: {argument name="country" default="[ COUNTRY ]"} {argument name="sport" default="[ FAVORITE SPORT ]"} {argument name="event" default="[ MAJOR EVENT ]"} Transform the selected country and sport into a legendary national celebration. The image should feel like an official poster.

Minimalist Conceptual Scene Description

GPT Image 2
Minimalist Conceptual Scene Description (Minimalism style, made with GPT Image 2) - AI image prompt example

Perfect for modern design and conceptual projects, this prompt creates serene and balanced minimalist scenes. These visuals use clean compositions, negative space, and subtle textures to evoke calmness and sophistication.

Sketch Style Anime Seaside Scene

GPT Image 2
Sketch Style Anime Seaside Scene (Anime / Manga style, made with GPT Image 2) - AI image prompt example

Lighthearted sketch-style anime aesthetic, a {argument name="person" default="woman"} walking along the seaside with a {argument name="dog breed" default="fluffy Pomeranian"}, seaside background with {argument name="architecture" default="pastel-colored beach houses"} and a vast blue sky, rough and dynamic freeform shapes, hand-drawn style line art with varying line weights, light and refreshing atmosphere, translucent bright color palette, using pure white, aqua blue, candy pink, and lemon cream for coloring

3D Stone Staircase Evolution Infographic

GPT Image 2
3D Stone Staircase Evolution Infographic (Infographic style, made with GPT Image 2) - AI image prompt example

{ "type": "evolutionary timeline infographic", "instruction": "Using REFERENCE_0 as a structural base, transform the flat vector design into a highly realistic 3D infographic. Replace the smooth ramps with distinct stone steps and upgrade all organisms to photorealistic 3D models.", "style": { "background": "{argument name=\"background style\" default=\"vintage textured parchment paper\"}", "staircase": "{argument name=\"staircase material\" default=\"realistic textured stone blocks\"}", "subjects": "{argument name=\"organism style\" default=\"highly detailed photorealistic 3D renders\"}" }, "layout": { "main_title": "{argument name=\"main title\" default=\"人类演化\"}", "sections": [ { "position": "left sidebar", "count": 8, "labels": ["L0: 单细胞生命", "L1: 多细胞生物", "L2: 动物界", "L3: 脊索动物", "L4: 上陆革命", "L5: 哺乳纲", "L6: 人科演化", "L7: 智人纪元"] }, { "position": "top right", "title": "获得的功能 / 失去的功能", "description": "Legend with plus and minus icons" }, { "position": "bottom center", "title": "演化关键里程碑", "count": 6, "description": "Timeline with a silhouette graphic of 6 figures showing ape-to-human evolution" } ], "centerpiece": { "description": "Winding stone staircase with 25 numbered steps featuring specific organisms.", "count": 25, "notable_elements": [ "Step 07: Jellyfish", "Step 09: Ammonite", "Step 10: Trilobite", "Step 24: Walking human", "Step 25: {argument name=\"future evolution concept\" default=\"glowing cosmic silhouette with a question mark\"}" ] } } }

Anime Martial Arts Battle Illustration

GPT Image 2
Anime Martial Arts Battle Illustration (Anime / Manga style, made with GPT Image 2) - AI image prompt example

An anime-style illustration of a {argument name="action type" default="high-impact martial arts battle"} between two young female fighters in a {argument name="setting" default="traditional wooden martial arts dojo"}. In the foreground, a girl with black hair in a high bun wears a {argument name="character 1 color theme" default="red and white"} Chinese-style martial arts outfit with baggy pants. She is in a dynamic, low, forward-thrusting stance, surrounded by swirling red energy and water splashes. In the background to the right, a girl with light purple hair in twin buns wears a {argument name="character 2 color theme" default="green and purple"} Chinese dress with gold embroidery and black tights. She is leaping through the air in a flying kick pose, surrounded by swirling blue energy. The wooden floorboards are splintering from the intense impact, with debris and dust flying through the air. Above them hangs a weathered wooden sign with the text "{argument name="sign text" default="武術会"}". The scene features dramatic lighting, a low-angle dynamic perspective, and intense action effects.

Momotaro Explainer Slide in Hybrid Style

GPT Image 2
Momotaro Explainer Slide in Hybrid Style (Infographic style, made with GPT Image 2) - AI image prompt example

Create an explanatory slide ({argument name="format" default="ponchi-e diagram"}) for {argument name="theme" default="Momotaro"} that fuses the gentle atmosphere of "Irasutoya" with the overwhelming information density of "Kasumigaseki slides".

Showing 337-360 of 548 image prompts

Browse AI image prompts by platform and style

By platform

By style

Quick Prompting Guide

Be Descriptive

Include specific artistic styles, lighting conditions, and composition details.

Reference Styles

Mentioning specific artists (e.g., "in the style of Van Gogh") helps the AI.

Parameters

Use parameters like --ar 16:9 (Midjourney) for better control.

Frequently Asked Questions

An AI image prompt is a text description that guides an AI image generator to create a specific picture. The prompts in this database were written for GPT Image 2, Midjourney, Dall-E, GPT-image-1 and more.

Yes, all AI image prompts in our database are completely free to use.

GPT Image 2 has the most, with 359 of the 548 prompts. Use the platform links above to see only the prompts made for one generator.