GPT Image 2 prompts

Browse GPT Image 2 prompts for fashion portraits and graphic compositions. Compare how each prompt describes its subject and the way the image is arranged.

Explore prompts

10,039 prompts

Comic / Storyboard - Blue Pen Cringe Manga Battle Page — output

Comic / Storyboard - Blue Pen Cringe Manga Battle Page

平成ワロスちゃんねるGPT Image 2
A hand-drawn manga page on off-white notebook paper, created entirely with rough blue ballpoint pen lines, messy teenage doodle energy, uneven panel borders, scratchy shading, exaggerated action effects, and intentionally amateur "cringe black-history notebook" style. The page has 6 panels total arranged vertically: 1 wide top panel, 1 wide second panel, 1 wide third panel, 1 narrow horizontal impact panel, and 2 small bottom panels side by side. In the top panel, a round cute hero resembling a pink puffball swordsman crouches dramatically at left with a long sword planted upward behind him, glaring intensely, while a delinquent-looking or office-worker man with curly hair stands at right in a shirt, tie, and slacks, hands in pockets, on a barren rocky plain with sketchy clouds and speed-scratch background. In the second panel, the round swordsman leaps diagonally through the air with the sword raised, surrounded by vertical motion lines; large handwritten Japanese sound-effect text fills the panel with exactly 2 text groups: "断タネ" on the left and "超時空" on the right. In the third panel, the hero flies low from left to right and releases a piercing energy slash or scream-like attack toward the man on the right; across the panel is 1 giant handwritten Japanese shout: "ズギャアアアン!!!". In the fourth narrow panel, the entire frame is filled with smoke, impact scribbles, and explosive chaos, with 1 large handwritten Japanese effect: "ドォォォン!!!". In the bottom-left panel, after the smoke clears, the man is unharmed and casually catches or stops the tiny sword between two fingers near his face; a tiny handwritten caption appears near the fingers reading "ピタ…". In the bottom-right panel, the round hero appears in close-up, shocked and screaming with huge eyes, sweat, and dark streaked shading on the face; along the right side is 1 vertical handwritten Japanese reaction: "なっ!?". Keep the faces on the human character obscured by soft rectangular blur blocks. Overall tone: comedic overdramatic battle manga parody, middle-school notebook doodle, chaotic composition, monochrome blue-ink pen sketch, no polished digital rendering, visible scribbles and imperfect anatomy.
Profile / Avatar - Helicopter Cabin Selfie at Sunset — output

Profile / Avatar - Helicopter Cabin Selfie at Sunset

aBaZeD 𝕏GPT Image 2
A candid close-up selfie inside a small helicopter cabin, shot from the front-facing phone camera, with one adult passenger seated on the left side of the frame. The person’s face is obscured by a large rectangular privacy blur block centered over the face, while reflective rainbow-tinted wraparound sunglasses remain visible above it. The subject has short dark hair and wears a dark jacket, holding one hand near the chest as if gripping a strap or collar. The helicopter interior is dark and enclosed, with a black ceiling, circular air vents overhead, curved cabin framing, visible wiring near the center roofline, and an empty black leather passenger seat on the right. A bright rounded window on the far right reveals sunlit blue water outside and a distant shoreline or low city skyline. Warm golden-hour light streams through the window, creating strong contrast, orange highlights on the cabin surfaces, and a moody cinematic travel-photo look. Realistic smartphone photography, slightly grainy low-light exposure, tight framing, natural perspective, casual authentic vacation helicopter ride atmosphere.
Profile / Avatar - Childlike Rainbow Goggles Doodle — output

Profile / Avatar - Childlike Rainbow Goggles Doodle

aBaZeD 𝕏GPT Image 2
A crude childlike digital doodle made in a simple paint program on a white background, showing a close-up selfie-style scene with 1 main person in the lower left and center. The person has messy medium brown hair, a dark blue jacket over a pale skin-toned neck and chest, and oversized ski goggles or visor glasses with a bright rainbow lens band arcing across the eyes in red, orange, yellow, green, blue, and purple. The face is largely obscured by a large square beige blur or censor block centered over the middle of the head and upper torso. One pale hand is raised near the bottom center as if giving a thumbs-up or holding something close to the camera. Around the figure are simple black-outline background doodles: 2 small cloud shapes near the top, 1 large angled airplane or rocket-like shape in the upper right, 1 gray rounded standing object to the right of the person that resembles a rock, backpack, or bundled figure, and 1 tall white rectangular object at the far right with a yellow sun drawn near the top and blue zigzag scribbles below. Use rough uneven hand-drawn lines, messy coloring outside the lines, minimal shading, a naive children's drawing aesthetic, and low-detail playful composition.
E-commerce Main Image - Ice-Cold Cola Splash Ad — output

E-commerce Main Image - Ice-Cold Cola Splash Ad

Creative DiffusionGPT Image 2
A high-end studio advertising photo of a single aluminum soda can standing upright at the exact center of the frame on a wet reflective black surface, shot straight-on at product height. The can is dark navy to black metallic with heavy cold condensation droplets and a sleek modern label. The visible label has 4 text elements: a white water-drop icon near the top, the large word {argument name="brand name" default="REFRESH"} in bold condensed uppercase with a subtle red outline, the smaller line {argument name="product subtitle" default="CHILLED COLA"} beneath it, and the lower line {argument name="tagline text" default="ICE COLD"}. A dramatic crown-like water splash explodes around the can from both sides and behind it, with dozens of frozen droplets suspended in midair, crisp high-speed photography style, dynamic arcs and scattered beads of water, plus smaller splashes at the base. Lighting is cinematic and commercial: strong cool white rim lights from both sides, glossy specular highlights on the aluminum, deep shadows, bright reflections in the splash, and a dark moody background fading to near-black. Emphasize ultra-sharp detail on the can and splash, premium beverage advertising, refreshing icy mood, photorealistic macro product photography, vertical composition, shallow depth of field but with the main splash sharply frozen, luxury e-commerce hero image quality.
E-commerce Main Image - Paris Autumn Street Style Photo — output

E-commerce Main Image - Paris Autumn Street Style Photo

Creative DiffusionGPT Image 2
A high-end lifestyle e-commerce photo of a stylish woman walking along a quiet Parisian street in autumn, captured from behind in a candid editorial moment. She is centered slightly left, mid-stride on a cobblestone-and-pavement sidewalk, turning her head gently toward the elegant Haussmann apartment buildings lined with wrought-iron balconies and flower boxes. She wears a long tailored wool coat in {argument name="coat color" default="camel beige"}, dark straight-leg trousers, and dark brown leather ankle boots, with a structured leather crossbody satchel in {argument name="bag color" default="warm tan"} hanging at her hip. She has shoulder-length wavy dark brown hair and holds a folded newspaper or magazine in one hand. The street includes exactly 6 black metal bollards visible in the foreground and midground, scattered dry autumn leaves on the ground, and tall trees on the right side with golden-brown foliage. In the background, softly blurred pedestrians walk down the boulevard, and a corner café with the visible sign {argument name="cafe sign" default="CAFÉ LE PARISIEN"} appears on the left, with the same café name faintly repeated farther down the street. Warm golden-hour lighting, shallow depth of field, natural skin tones, creamy background bokeh, refined neutral color palette, luxury travel editorial styling, realistic photography, vertical composition, 4:5 aspect ratio, premium advertising image quality.
Product Marketing - Beard Oil How-To Ad — output

Product Marketing - Beard Oil How-To Ad

𝑱 𝑬 𝑭 𝑭 𝑹 𝑬 𝒀 🇬🇭GPT Image 2
Create a bold square social media advertisement for a beard-growth product tutorial. Use a vivid royal blue gradient background with a high-contrast, editorial grooming-brand look. Show an extreme close-up of a Black man’s cheek, jawline, ear, and beard area on the right side of the frame, with detailed skin texture and short coarse beard hair. His left hand is holding a glass dropper near the beard line, and a clear droplet is about to touch the skin beneath the sideburn area; his other hand lightly presses the beard from below. In the blurred background near the center-left, place a white bottle with a blue label resembling minoxidil packaging, clearly out of focus so it reads as the product without stealing focus. At the very top, add small spaced uppercase branding text: {argument name="brand name" default="SAUCY BEARD HAVEN"}. Below it, place a huge condensed bold white uppercase headline spanning nearly the full width: {argument name="headline text" default="HOW TO USE IT"}. In the lower-left quadrant, add exactly 4 instructional bullet points with small gold diamond icons and clean white sans-serif text: 1) {argument name="tip 1" default="Apply 1ml directly to beard skin — not hair"}, 2) {argument name="tip 2" default="Massage in gently for 1–2 minutes"}, 3) {argument name="tip 3" default="Use twice daily: morning + night"}, 4) {argument name="tip 4" default="Don’t wash face for 4 hours after applying"}. At the bottom center, include a small circular beard-themed logo above a dark blue nameplate with the text “SaucyBeardHaven”. Lighting should be glossy and commercial, with crisp focus on the hands, dropper, and beard edge, creating a premium men’s grooming ad designed for Instagram.
Profile / Avatar - Bitcoin Monkey MS Paint Doodle — output

Profile / Avatar - Bitcoin Monkey MS Paint Doodle

zac.eth 🧙🏻‍♂️♦️GPT Image 2
A simple childlike digital doodle on a plain white background, centered and isolated, showing a cute cartoon monkey standing upright and facing forward. The monkey has a round beige face, brown fur outline, two round ears, small black dot eyes, and a thick wavy black smile. It wears a gray ushanka-style winter hat with brown ear flaps, and on the front of the hat there is a yellow circular patch with a red Bitcoin symbol. The monkey is dressed in a bright purple open jacket over a white shirt, with a gold chain necklace holding a round gold medallion marked with a black Bitcoin symbol. One arm is extended outward holding a purple handheld game console with a green screen and black control buttons; the other arm hangs to the side. The legs are short and simple with beige feet. Render it in a rough MS Paint style with uneven hand-drawn lines, flat colors, scribbly fills, playful proportions, and a naive internet-meme aesthetic, like a viral GPT Image 2 crayon sketch.
Infographic / Edu Visual - French AI Newspaper Front Page — output

Infographic / Edu Visual - French AI Newspaper Front Page

Creative DiffusionGPT Image 2
A realistic close-up editorial photograph of a French newspaper front page laid slightly diagonally on a dark tabletop, designed like a polished national daily. The masthead is a large blue rectangle with white newspaper lettering reading {argument name="newspaper name" default="Le Parisien"} and a thin red underline. The dominant central headline, in oversized bold black serif type, reads {argument name="main headline" default="ChatGPT Vs Gemini : Le match des images"}. Directly underneath, a smaller italic serif subheadline in French reads {argument name="subheadline" default="Deux intelligences artificielles s’affrontent dans une bataille visuelle sans précédent"}. In the center of the page, place a wide rectangular feature image showing exactly 2 futuristic boxing gloves colliding from left and right: the left glove is dark graphite and black with subtle glowing circuit patterns, the OpenAI knot logo near the wrist, and the word {argument name="left glove label" default="ChatGPT"} in bright white; the right glove is metallic silver-blue with luminous blue circuitry and the word {argument name="right glove label" default="Gemini"} in glowing blue-white. The gloves meet in the middle dramatically, lit like a high-end tech advertisement. Surrounding the main story are exactly 4 smaller newspaper teaser blocks: 2 at the top corners and 2 stacked in the right sidebar, each with dense French placeholder-style article text, thin divider lines, small page references such as "Pag. 2" or "Page 4", and some blue all-caps section tags like "LE AMIT", "LE PARISIEN", and "CONFIANTS". Add another line of italic serif text below the image repeating the visual-battle theme. Use authentic newspaper layout proportions, crisp print texture, black ink on off-white newsprint, subtle paper creases, and soft natural lighting for a believable photographed front page.
YouTube Thumbnail - King Kong Reborn Movie Poster — output

YouTube Thumbnail - King Kong Reborn Movie Poster

Creative DiffusionGPT Image 2
A hyper-detailed cinematic movie poster for a giant monster reboot set in Manhattan at sunset. A colossal enraged gorilla resembling King Kong stands on top of a heavily destroyed skyscraper in the foreground, roaring with mouth wide open and teeth exposed. The creature is massively muscular, covered in dark brown fur, with multiple visible battle scars and fresh wounds across the chest, arms, shoulders, and legs. One hand grips the broken steel spire and shattered crown of the building, while one huge foot crushes the rooftop. The city below is New York, with the Empire State Building clearly visible in the mid-right background and a dense skyline fading into dramatic golden haze. The sky is filled with dark storm clouds split by warm orange sunset light. Include exactly 3 military helicopters: 1 near the upper right shining a bright searchlight toward the ape, 1 smaller helicopter near the center-right skyline, and 1 lower-left helicopter sweeping a searchlight across smoky buildings. Add fires, smoke plumes, glowing embers, street-level destruction, and a sense of large-scale urban chaos. Compose it as a polished modern Hollywood theatrical one-sheet with the monster centered and towering over the city. In the lower third, add the tagline text: {argument name="tagline text" default="The legend rises again."} Above the credits, place the huge metallic embossed title in two lines: {argument name="movie title" default="KING KONG"} and below it {argument name="subtitle" default="REBORN"}. Beneath that, add a dense realistic film-credit block with multiple producer, director, cast, and screenplay lines in small condensed type. At the very bottom, add the release line: {argument name="release text" default="SUMMER 2026"}. Use ultra-realistic lighting, dramatic contrast, blockbuster poster composition, volumetric smoke, sharp details, photoreal fur, and premium action-adventure disaster-film aesthetics.
Product Marketing - AI Boxing Gloves Showdown — output

Product Marketing - AI Boxing Gloves Showdown

IAFeedGPT Image 2
A dramatic hyper-realistic studio image of 2 black leather boxing gloves colliding mid-air in the center of the frame, shown in a tight close-up against a dark navy-to-black background. The left glove enters from the left and is labeled {argument name="left glove text" default="GPT-Image 2"} in large glowing icy-blue sans-serif letters, with futuristic blue circuit-trace graphics wrapping across the glove and wrist. The right glove enters from the right and is labeled {argument name="right glove text" default="Nano Banana 2"} in large bold warm-gold sans-serif letters, with angular gold accent stripes and a stylized gold emblem on the cuff. Capture the instant of impact with bright metallic sparks and tiny particles bursting outward between the 2 gloves. Emphasize glossy leather texture, visible stitching, dramatic rim lighting, high contrast, subtle reflections, and a premium tech-versus-sports showdown aesthetic. Cinematic composition, centered clash, symmetrical balance, ultra-detailed, sharp focus, commercial advertising style.
Social Media Post - Childlike Sketch Photo Transform — output

Social Media Post - Childlike Sketch Photo Transform

peterpriew 🔴✨🥷GPT Image 2
Using REFERENCE_0, recreate the exact same photo composition, person, pose, outfit, drink, and background layout, but transform the whole image into a playful childlike hand-drawn crayon-and-colored-pencil sketch on a clean white page. Keep the main subject centered with the face still obscured by a simple beige blur block. Preserve the Thai text on the black T-shirt and the Café Amazon cup branding. Simplify all environmental details into naive doodles with uneven outlines and scribbly coloring: 1 gray car on the left, 1 blue accessible parking sign, 2 streetlights, 3 visible trees, 1 black-roof Amazon storefront, 1 small person in the distant doorway, 1 curb ramp with rails, and the tiled ground drawn as loose perspective grid lines. Make it look intentionally cute, rough, and humorous, like a quick kids' sketch version of the original photo.
Product Marketing - Futuristic AI Era City Poster — output

Product Marketing - Futuristic AI Era City Poster

架构师张SirGPT Image 2
A cinematic vertical sci-fi poster set on a rooftop observation deck above a vast futuristic megacity at sunset, viewed from behind. In the foreground, 2 central figures stand side by side: a tall adult man in a fitted dark business suit, black shoes, and white shirt, seen from the back, and a glowing translucent blue female humanoid AI hologram with a slim body made of light particles, wireframe lines, and constellation-like nodes. The human stands confidently facing the skyline, while the holographic AI raises one hand and projects a luminous holographic city blueprint made of neon-blue architectural outlines and transparent UI panels. The man holds 1 glowing golden octagonal device in his left hand, designed like a compass or navigation emblem with bright radial lines. The city is dense with skyscrapers, aerial traffic, digital billboards, and cyberpunk lighting in blue, cyan, and magenta accents; 1 flying car is visible on the right side. The sky transitions from warm orange sunlight near the horizon to deep blue night above, with dramatic clouds and a high-tech optimistic atmosphere. Add 4 major holographic interface clusters: 1 large projected city model above the AI’s hand, 1 mid-center analytics panel with charts and circular diagrams, 1 upper-right transparent data screen, and 1 lower-right billboard-like screen showing large “AI” text. At the top center, place a huge futuristic framed headline in bold glowing Chinese characters with metallic white-gold lettering: {argument name="headline text" default="智能体时代:想象定边界,行动决胜负。"}. The composition should feel visionary, corporate, inspirational, and premium, with ultra-detailed lighting, reflective wet rooftop surfaces, volumetric glow, sharp focus, epic scale, and polished gpt-image-2 poster aesthetics.
Infographic / Edu Visual - Hybrid Cache Execution Flowchart — output

Infographic / Edu Visual - Hybrid Cache Execution Flowchart

kwindlaGPT Image 2
Create a clean vertical technical workflow infographic on a light gray background, using a minimalist modern product-diagram style with rounded white cards, thin colored outlines, simple vector line icons, dark navy text, and navy connector arrows. The composition is a single centered top-to-bottom flowchart with 7 numbered main steps, plus 2 parallel cache-group panels branching from step 4 into step 5, and a thick dark return arrow on the far left looping from the bottom back to the top. Use crisp sans-serif typography, generous spacing, subtle pastel accent colors, no gradients, no shadows, and presentation-slide clarity.

At the top center place step card 1 with a blue outline and a code/chat icon on the left. Title text: "1. {argument name="step 1 title" default="chat completions request"}". Subtitle beneath: "conversation_id + cache_salt + new suffix messages".

Below it place step card 2 with a blue outline and a document/list icon. Title: "2. Frontend conversation ledger". Subtitle: "lease same id + track committed messages".

Below it place step card 3 with a cyan outline and a database-with-magnifier icon. Title: "3. Exact conversation cache lookup". Subtitle: "conversation_id  committed turn state".

Below it place step card 4 with a purple outline and a branching scheduler icon. Title: "4. Scheduler cache attachment". Subtitle: "set num_computed_tokens + attach committed state".

From step 4, branch downward into 2 side-by-side group panels.

Left group panel: a pale green rounded container titled "Full-attention KV cache group". Inside it, stack 2 inner cards. First inner card has a green block-grid icon, title "Committed block refs", subtitle "share aligned full KV blocks". Second inner card below has a green layered-sheets icon, title "Tail COW copy", subtitle "copy unaligned KV tail". At the bottom of the green panel add small footer text: "paged K/V tensors for transformer layers".

Right group panel: a pale purple rounded container titled "Mamba terminal-state cache group". Inside it, stack 2 inner cards. First inner card has a purple database/network icon, title "Committed terminal state", subtitle "exact state at committed length". Second inner card below has a purple wavy-lines icon, title "Request-owned terminal copy", subtitle "copy SSM + conv state". At the bottom of the purple panel add small footer text: "align-mode terminal state placement".

Merge both group-panel outputs into a centered step card 5 with a blue outline and a microchip icon. Title: "5. Hybrid model execution". Subtitle: "run only the uncached suffix". Inside the bottom area of this card, include 2 pill-shaped labels side by side: "Transformer layers" and "Mamba layers".

Below it place step card 6 with a blue outline and a sparkle icon. Title: "6. Decode assistant tokens". Subtitle: "stream response token by token".

Below it place step card 7 with a warm yellow-orange outline and a database-with-check icon. Title: "7. Commit completed turn". Subtitle: "publish pending state or discard on failure".

Add a thick dark navy loop arrow running down the far left side, entering step 1 near the top from the left and returning from step 7 at the bottom back upward. Along this left loop, near the lower half, place stacked annotation text: "next request reuses committed conversation head".

Add 2 dashed publish arrows rising upward from step 7 toward the cache-group panels: one green dashed arrow on the left pointing to the green cache panel, labeled "publish new state"; one purple dashed arrow on the right pointing to the purple cache panel, also labeled "publish new state".

Keep the exact total count of 7 numbered main cards, 2 cache group panels, 4 inner cache cards, and 2 pill labels. Preserve a portrait aspect ratio similar to a conference-slide architecture diagram.
Infographic / Edu Visual - Sci-Fi Light Freighter Schematic HUD — output

Infographic / Edu Visual - Sci-Fi Light Freighter Schematic HUD

kwindlaGPT Image 2
{"type":"futuristic spaceship technical schematic dashboard","style":"high-contrast sci-fi HUD interface, black background with faint grid, thin neon linework, blueprint-like wireframe rendering, minimalist aerospace UI, crisp vector graphics","subject":{"vehicle":"compact light freighter spacecraft","model":"{argument name=\"ship model\" default=\"RAVEN-03\"}","class":"light freighter","manufacturer":"Gradient Bang","views":[{"name":"top view","position":"upper center","render":"detailed wireframe spacecraft outline with internal structure and glowing blue engine thrusters"},{"name":"side view","position":"lower center","render":"wireframe side profile of the same spacecraft on landing gear with a highlighted midship cargo or power compartment and blue rear thrusters"}],"callouts":{"count":5,"items":[{"label":"01","color":"cyan","target":"forward cockpit or nose section"},{"label":"02","color":"yellow-green","target":"central reactor or power core module"},{"label":"03","color":"cyan","target":"rear maneuvering or thruster systems"},{"label":"04","color":"yellow-green","target":"main engines at the stern"},{"label":"05","color":"cyan","target":"lower cargo bay or ventral module"}]},"specs":{"count":8,"items":["length: 28.7 m","beam: 14.2 m","height: 8.6 m","mass: 32,650 kg","crew: 2","cargo capacity: 96 SCU","max velocity: 420 m/s","range: 1.3 AU"]}},"layout":{"header":{"position":"top full width","elements":["Gradient Bang // Technical Diagram","class: light freighter","designation: Raven-03","schematic version: 1.4.7","date: 2045-05-14","3 small square control icons at top right"]},"left_panel":{"position":"left column","sections":[{"title":"model info","count":1,"content":"large ship name block with bold lime text for {argument name=\"ship name\" default=\"RAVEN-03\"} and smaller subtitle LIGHT FREIGHTER plus the 8-line specification list"},{"title":"system legend","count":5,"labels":["01 cockpit","02 power core","03 maneuver thrusters","04 main engines","05 cargo bay"]}]},"center_panel":{"position":"center wide","sections":[{"title":"top view","count":1},{"title":"side view","count":1}]},"right_panel":{"position":"right column","sections":[{"title":"power distribution","count":4,"labels":["42% engines","28% weapons","20% life support","10% reserves"],"graphic":"donut chart in blue and yellow-green"},{"title":"shield coverage","count":4,"labels":["front 85%","left 70%","right 70%","rear 60%"],"graphic":"radar chart over a small ship outline"},{"title":"cargo bay","count":3,"labels":["72 / 96 SCU","75% capacity","16 slot configuration, 2 SCU unit size"],"graphic":"grid of cargo cells with most squares filled"}]},"footer":{"position":"bottom full width","elements":["status: operational","location: orbit // Perseus sector","clearance level: green"]}},"color_palette":{"background":"deep black","grid":"dark charcoal","primary_lines":"cool gray","accent_1":"neon yellow-green","accent_2":"electric cyan-blue","text":"muted white and gray"},"composition":"16:9 widescreen interface screenshot, balanced three-column layout, left data column, central spacecraft schematics, right analytics panels, clean margins, angular panel borders, cinematic monitor display","quality":"ultra-clean, precise, polished, game UI concept art, high detail"}
Comic / Storyboard - Retro Sci-Fi Casualty Desk Front Page — output

Comic / Storyboard - Retro Sci-Fi Casualty Desk Front Page

kwindlaGPT Image 2
A retro-futurist black-and-white sci-fi newspaper front page designed like a casualty report bulletin, with a distressed paper texture, halftone grain, thin technical border lines, and a slightly worn photocopied print look. The layout is a single printed page in landscape orientation with a bold masthead tab at the top reading {argument name="section label" default="CASUALTY DESK"}. On the left third of the page, a huge condensed all-caps headline in heavy sans-serif type reads {argument name="headline text" default="TWENTY-FIVE HULLS LOST AS THREE GARRISONS HOLD THEIR LINES"}, stacked across 5 lines. Beneath it are 2 dense newspaper-style body text blocks in narrow columns of small monospaced or typewriter-like text, with a few bolded ship and faction names embedded in the copy. The article text should feel like military logistics reporting from an interstellar war, mentioning exact times, sectors, casualties, garrisons, probes, toll positions, and damaged ships. The right two-thirds of the page is a detailed monochrome ink illustration: in the upper right sky, 1 enormous wedge-shaped capital ship or dreadnought hovers diagonally from left-lower side toward right-upper side, covered in layered armor panels, antennae, gantries, and dense structural detailing. Below it, occupying the lower right half, is 1 industrial checkpoint or garrison gate spanning a wide road or landing lane, built from brutalist sci-fi frames, vertical pylons, gantry towers, and utility structures, with perspective lines drawing the eye toward the center distance. Add 1 small mid-distance flying craft near the horizon under the gate. In the far right background, include 1 cluster of tall refinery-like towers and industrial buildings. Overlay faint hexagonal grid motifs on the upper right and lower right background, subtle and partially faded into the paper texture. Use only grayscale tones, black ink linework, etched concept-art hatching, and newspaper-print contrast. The overall mood is bleak, militarized, archival, and editorial, like a war correspondent page from a far-future space empire newspaper.
Comic / Storyboard - Epic Yasuo Fantasy Poster — output

Comic / Storyboard - Epic Yasuo Fantasy Poster

乐鱼JoyfishGPT Image 2
A dramatic vertical fantasy poster of {argument name="character name" default="Yasuo"} from League of Legends, depicted as a lone wandering swordsman in a dark imperial-war aesthetic. The composition is a single unified poster with two integrated figure scales: a massive semi-profile close-up of the character’s head and upper torso filling the upper half, and 1 full-body heroic figure standing in the lower center on a stone pedestal. He has long black hair tied into a high warrior topknot with loose strands whipping in the wind, stern features, and layered samurai-inspired armor in deep navy blue, charcoal, and black with ornate gold trim. His long tattered cape and waist cloth stream to the right, and he holds 1 glowing katana angled downward in his right hand. A bright ribbon of golden wind energy spirals from the lower figure upward through the center, connecting into the larger portrait above, with countless ember-like sparks and luminous brushstroke trails. Behind him is a vast army scene with 2 visible battle flags, ranks of soldiers, and a distant fortress city of tiered pagoda-like rooftops fading into smoke and haze. The palette is moody midnight blue, ash gray, black, and warm metallic gold, with cinematic high contrast lighting, painterly concept-art detail, ink-splatter textures around the edges, and a mythic, solemn, epic mood. Include stylized vertical Chinese calligraphy on both sides: on the right, 3 stacked text elements reading “疾风剑豪”, large “亚索”, and small vertical “YASUO”; on the left, 1 vertical quote reading “死亡如风,常伴吾身。” Add large serif gold title text at the bottom with 3 lines: “YASUO”, “THE UNFORGIVEN”, and “LEAGUE OF LEGENDS”. Make it look like a premium character key art poster, ultra-detailed, dynamic wind motion, glowing particles, heroic stance, dark fantasy wuxia-samurai fusion.
Social Media Post - Paris Eiffel Tower Vacation Selfie — output

Profile / Avatar - Eiffel Tower Low-Angle Selfie

Danna R.GPT Image 2
A photorealistic travel selfie shot from a low angle directly beneath the Eiffel Tower in Paris on a bright cloudless day, with the tower rising dramatically overhead and centered in perfect vertical symmetry against a vivid blue sky. In the foreground, a young woman with {argument name="hair color" default="medium brown"} shoulder-length straight hair stands very close to the camera, holding the phone slightly below chest level for an upward-facing selfie perspective. Her face is mostly neutral and relaxed, with a casual candid vacation-photo feel. She wears a fitted ribbed strapless tube top in {argument name="top color" default="light pink"}, high-waisted {argument name="bottom color" default="white"} jeans, and 2 thin layered silver necklaces. Her skin is warmly lit by strong midday sunlight, with crisp natural shadows from the tower structure and subtle highlights on her shoulders and collarbone. Frame the subject from mid-thigh to head, with one arm extended toward the camera in a natural selfie pose. Emphasize realistic smartphone photography, sharp architectural detail in the iron lattice beneath the Eiffel Tower, authentic tourist snapshot composition, natural body proportions, clean summer styling, and high-detail photorealism. Make it look like a real handheld vacation selfie of {argument name="character name" default="a stylish young woman"} in {argument name="location" default="Paris"}, not a studio image.
Profile / Avatar - Luxury Apartment Mirror Selfie — output

Profile / Avatar - Luxury Apartment Mirror Selfie

Danna R.GPT Image 2
A photorealistic full-length mirror selfie of a slim young woman standing indoors in a warm, upscale apartment living room hallway. She is wearing a fitted ivory-white one-shoulder bodycon midi dress with soft ruched gathering through the waist and hips, elegant minimal styling, and a sleek date-night look. Her hair is straight, dark brown, shoulder length, parted near the center, falling naturally over both sides. She holds a smartphone up in her right hand, partially covering her face, with a black phone case decorated with red cloud motifs. Her left arm rests naturally at her side, with a silver bangle bracelet and delicate rings visible. The composition is vertical, realistic, and casually luxurious, like a genuine personal outfit selfie taken in a wall mirror. The setting includes 1 beige fabric sofa on the right, 1 patterned throw pillow in taupe and cream on the sofa, and 1 small brown leather top-handle handbag placed on the seat cushion. Behind her is a textured bronze-brown accent wall; on the left is a dim hallway with 3 framed wall artworks, dark doorways, cream walls, and polished light tile floors. Use warm indoor ambient lighting, soft shadows, subtle phone-camera realism, natural skin texture, realistic reflections, clean apartment styling, centered subject with the upper body and dress as the focus, and an understated luxury aesthetic.
Profile / Avatar - Flash Night Beach Portrait — output

Profile / Avatar - Flash Night Beach Portrait

Danna R.GPT Image 2
A candid photorealistic night beach portrait of a young woman standing on wet sand near the shoreline, framed from mid-thigh up, facing the camera with a relaxed posture and one arm hanging naturally at her side. She has long straight dark brown hair parted near the center, smooth light-to-medium skin, and wears a fitted strapless bodycon dress with a soft vintage floral print in muted cream, pale yellow, sage green, and dusty blue. Add a delicate gold necklace with a small round pendant and subtle rings on her fingers. The scene is lit with direct on-camera flash, creating sharp realistic highlights on the skin, a crisp subject against a very dark background, and a visible band of foamy ocean waves behind her. The beach and sea should look natural and dim, with the horizon fading into black night sky. Smartphone snapshot aesthetic, realistic skin texture, slight flash harshness, casual social-photo composition, shallow ambient detail, centered subject, authentic nightlife beach vibe.
Comic / Storyboard - Hand Drawn Sketch Storyboard Sheet — output

Comic / Storyboard - Hand Drawn Sketch Storyboard Sheet

𝗦𝗮𝗻𝗶𝗮GPT Image 2
A professional hand drawn sketch storyboard sheet, pencil and ink illustration style, rough artistic linework, cross-hatching for shadows, loose expressive strokes, monochrome black and white on aged cream/off-white paper texture background, 2x2 grid layout with four equal storyboard panels bordered by thick hand-drawn black ink frames. Top-left panel sketch: {argument name="first panel" default="abandoned rusted cargo ship at dock, heavy hatching for rust texture, broken railings, algae, seagulls, no humans, dark moody pencil shading"}, handwritten label below: "SCENE 01 — ABANDONED STATE | Static wide dock shot | Overcast | No humans". Top-right panel sketch: {argument name="second panel" default="same ship with workers using pressure washers, dynamic water spray motion lines, figures in safety gear, debris piles"}, handwritten label: "SCENE 02 — CLEANING & STRIP-DOWN | Pressure wash + debris clear | Cloudy daylight". Bottom-left panel sketch: welding sparks as burst star lines, scaffolding structure, worker figures grinding and painting, primer sections with hatching, handwritten label: "SCENE 03 — REPAIR & REBUILD | Welding sparks + scaffolding | Primer applied". Bottom-right panel sketch: fully restored ship, clean hull, workers standing back, golden hour rays as radiating diagonal lines, handwritten label: "SCENE 04 — FULL RESTORATION | Final paint + golden hour | Completion". Bold hand-lettered title at top: "{argument name="title" default="SEA HARVEST VALLETTA — RESTORATION STORYBOARD"}". Handwritten production notes at bottom: "Cam: Static Wide-Angle Dock | Lens: Wide | Progression: Linear | Style: Photorealistic". Pencil graphite texture, ink pen outlines, rough paper feel, professional film storyboard aesthetic.
Product Marketing - Playful Velvet Chocolate Poster — output

Product Marketing - Playful Velvet Chocolate Poster

𝐌GPT Image 2
A playful food advertisement poster. A happy young woman in a {argument name="outfit color" default="caramel-brown"} outfit hugging a {argument name="giant item" default="giant chocolate bar"} 3x her height with "{argument name="brand name" default="VELVET"}" on the wrapper, melted chocolate dramatically dripping down. Warm golden caramel studio background with floating cocoa powder particles. Bold chunky typography "VELVET" in background. 

Tagline bottom: "Melt into the moment." Small text top-right corner reads "Designed with GPT Image 2" in grey. 

Photorealistic, warm cozy food commercial lighting.
Comic / Storyboard - Time Traveler Night Market Grid — output

Comic / Storyboard - Time Traveler Night Market Grid

⁠ luciaAIGPT Image 2
A 2x2 cinematic grid showing different time travelers experiencing modern street food in a neon-lit night market. Each panel represents a different era character reacting to food, ultra realistic, cinematic lighting, highly detailed, vibrant colors, storytelling composition, 8K quality, shallow depth of field, dramatic atmosphere, steam and neon glow, cohesive visual style across all panels. Top left: Mughal-era prince holding a modern burger, confused expression, neon food stall background. Top right: medieval knight eating french fries, humorous reaction, street night lights. Bottom left: Victorian lady tasting spicy street taco, surprised expression, cinematic lighting. Bottom right: futuristic cyborg drinking chai, glowing blue eyes, neon cyber street food setting. consistent lighting, unified color grading, cinematic grid composition, ultra-detailed faces, storytelling coherence Animate this image into a single continuous cinematic scene. The 2x2 grid layout should dissolve into one unified street food night market where all characters exist in the same space and interact naturally. Transform the scene so the Mughal-era prince, medieval knight, Victorian lady, and futuristic cyborg are all standing in the same neon-lit street food market at night. Remove the grid separation completely and merge all panels into one cohesive world. Camera slowly pans across the scene in a smooth cinematic motion, revealing each character one by one. The Mughal prince examines a modern burger with curiosity. The medieval knight eats fries with exaggerated confusion. The Victorian lady reacts to spicy street food with surprise. The futuristic cyborg calmly drinks chai with glowing eyes. Add subtle natural movements: blinking, chewing, steam rising from food, neon reflections shifting, soft crowd motion in background. Maintain cinematic lighting, ultra realistic style, shallow depth of field, vibrant neon night market atmosphere, film-like color grading. Smooth camera movement, slow cinematic reveal, no grid lines, no panel separation, fully merged world, consistent environment, high detail, 8K cinematic realism.
Product Marketing - Surreal Top-Down iPhone Fashion — output

Product Marketing - Surreal Top-Down iPhone Fashion

waheeb mohammedGPT Image 2
A hyper-realistic top-down photograph of a young {argument name="model" default="male model"} with a clean skin fade and short curly textured hair, standing in a confident, relaxed pose directly on the glowing screen of a {argument name="giant device" default="giant iPhone 16"}. The phone screen is active, displaying a dark-themed Spotify playlist with the song title "Sajanka - Sun is Coming" clearly visible beneath him. He wears {argument name="headphones" default="2025 AirPods Max"} in a neutral metallic finish, an oversized white hoodie-style shirt with subtle drape, black athletic shorts, and crisp white Air Jordan sneakers. The top-down high angle flattens the scene and emphasizes the surreal scale—the model’s feet rest on digital buttons and album art. Lighting is soft, minimal, and diffused, with a cool neutrality that makes the white clothing and bright screen pop without harsh shadows. Colors are constrained: brilliant white, deep black, titanium grey, and a small vivid accent from the Spotify album cover. Textures contrast smoothly: matte cotton fabric, glossy headphone surfaces, and the glass screen's slight reflectivity. Style is sleek, minimal, fashion-forward, and futuristic, blending tech advertising aesthetics with editorial portraiture. The mood is confident, fresh, and effortlessly cool.
Product Marketing - Neon Cyberpunk Portrait — output

Product Marketing - Neon Cyberpunk Portrait

TaarukGPT Image 2
Moody cinematic portrait of a stylish {argument name="subject" default="man"} wearing black sunglasses and {argument name="accessory" default="premium over-ear headphones"} resting around his neck, confident expression, looking slightly to the side. Dark studio background with dramatic {argument name="neon lighting" default="teal and magenta neon lighting"} casting split-tone colors across the face. High contrast shadows, glossy reflections on sunglasses and headphones, ultra-detailed skin texture, sharp jawline, minimal composition. Cyberpunk-inspired color grading, soft haze, subtle film grain, 85mm lens, shallow depth of field, ultra-realistic, luxury tech advertisement style, 4K
Browse by model, style or topic

Find your next direction

ASTORIE CANVAS

Take the idea further.

Bring your prompts, references and results together in one creative space.

Open your canvas ↗