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

10,050 prompts

Social Media Post - Spring Daisy Field Portrait — output

Social Media Post - Spring Daisy Field Portrait

KashbergGPT Image 2
A young woman lying on a lush field of {argument name="flowers" default="small white and pink daisies"}, looking up at the camera. She has fair skin, soft makeup, and dark hair styled in a {argument name="hair style" default="loose side bun with bangs"}. She wears a {argument name="clothing" default="light yellow zip-up top and a black backpack"}, with sunglasses resting on her head. One hand makes a peace sign near her face while the other holds a trekking pole. Bright natural sunlight, soft shadows, vibrant green background, fresh spring atmosphere, high detail, photorealistic, shallow depth of field.
Profile / Avatar - Sorrowful Night Cinematic Portrait — output

Profile / Avatar - Sorrowful Night Cinematic Portrait

ShinningGPT Image 2
32K ultra high definition, night scene, long flowing hair, partially covering a beautiful {argument name="mood" default="sorrowful"} face, slightly tipsy feeling, delicate and natural expression, dark-toned background, {argument name="lighting" default="soft hair rim light"}, clear facial details, smooth elegant lines, close-up portrait, masterpiece, premium aesthetic, mysterious atmosphere, tears on the face, glossy tearful eyes.
Comic / Storyboard - Hand-Drawn Storyboard Previs Sketch — output

Comic / Storyboard - Hand-Drawn Storyboard Previs Sketch

KōdaGPT Image 2
Create a rough hand-drawn PREVIS + rescue chase storyboard page in 16:9 horizontal format.

Use an extremely simple 2D previs sketch style:
- stick figures / mannequin silhouettes only
- no facial detail, no costume detail, no anatomy detail
- no texture, no shading, no polished rendering
- black loose sketch lines
- red boxes for camera framing only
- blue arrows for motion / force / breath / direction only
- rough director thumbnails, not concept art
- if unsure, draw less detail, not more

Show 8 numbered panels on one page with slightly irregular but readable placement.

Subject: {argument name="subject" default="two close friends racing on skateboards through the sky above the clouds"}
Environment: {argument name="environment" default="bright open sky, fluffy cloud pathways, floating cloud banks, distant sunlight, then a darker storm-cloud zone with wind, rain and lightning"}
Mood: playful, adventurous, fast, funny, suspenseful for a moment, then uplifting and triumphant
Sequence: during a fun cloud-skate race, one friend accidentally drifts into dangerous storm clouds and loses control, then the other friend makes a last-second rescue

Beats:
1. Wide establishing shot. Two friends on skateboards surf above the clouds, side by side, racing playfully through the sky.
2. Side tracking shot. The race speeds up. One friend leans forward and gains a little lead while the other follows close behind.
3. 3/4 front angle. The leading friend accidentally veers toward a dark storm-cloud area ahead while still focused on the race.
4. Overhead shot. The storm cloud swallows the lead friend. Strong wind arrows, rain and lightning. The skateboard wobbles violently.
5. Close-up / medium action shot. The second friend notices the danger, brakes hard for a split second, then pivots and dives toward the storm.
6. Dynamic low angle. The rescuer shoots into the storm clouds on the skateboard, reaching forward through wind and lightning toward the trapped friend.
7. Hero side shot. Last-second rescue. The rescuer grabs the other friend by the arm or hoodie and pulls them free from the storm cloud just as lightning strikes behind them.
8. Wide payoff shot. Both friends burst back into the sunny clouds, regain balance, keep riding together and continue the race laughing, now side by side.

Use varied camera angles: close-up, wide, low angle, overhead, side profile, rear, 3/4.
Add short handwritten notes near panels.
Maintain clear continuity of subject, props, environment and movement direction.

Focus on staging, camera, motion, timing and continuity.
Prioritize readability over drawing quality.
Avoid detailed illustration, clean UI and infographic design.

Tone target: fun family-animation energy, clear visual storytelling, simple readable action be
Comic / Storyboard - Ghibli Style Pastoral Village — output

Comic / Storyboard - Ghibli Style Pastoral Village

Chidanand TripathiGPT Image 2
[Subject]: {argument name="subject" default="Villagers in simple rural clothing"}. [Action]: {argument name="activity" default="Tending crops and harvesting vegetables"}. [Environment]: {argument name="scene" default="Idyllic pastoral village with cozy cottages and rolling green hills"}. [Cinematography]: Wide establishing shot, vibrant perspective. [Lighting/Style]: Studio Ghibli aesthetic, bright summer daylight, lush watercolor backgrounds. [Technical]: 2D animation style, vibrant colors, nostalgic atmosphere.
Comic / Storyboard - Cinematic Storyboard Production Board — output

Comic / Storyboard - Cinematic Storyboard Production Board

Olivio SarikasGPT Image 2
story = {argument name="story subject" default="a beautiful woman in a white dress enjoying a amazing sunset evening at a luxury mansion build into a cliff"}, 

Scenes:
1) wide angle drone shot
2) wide angle walk at pool
3) medium wide over shoulder walk at pool
4) medium wide lean on railing
5) close-up hand in water
6) look over bay
7) close-up smile
8) wide angle smile holding champagne with elegant font text "LuxLife Retreats"

Create a cinematic production board / visual planning sheet that presents a complete concept for a short film or commercial. The layout should be clean, grid-based, and divided into clearly labeled sections.    

Include:  Shared creative direction (top bar): overall constraints such as number of shots, unified color palette, and general environmental context.      

Character + styling reference section:  A model shown from multiple angles (front, back, side, close-ups, relaxed pose), accompanied by wardrobe and accessory references. Emphasize consistency of identity while allowing minor variations for specific scenes.      

Environment and set design section:  A scenic outdoor location with dramatic natural features, plus a top-down diagram illustrating movement through the space. Include camera positions and labeled shot types mapped along a route.      

Storyboard section: A sequence of numbered frames (about 8 shots) showing progression of the scene. Each frame includes:  Camera type / lens feel  Shot size (wide, medium, close-up, macro)  Movement (static, tracking, handheld, etc.)  Brief description of action and emotional progression      Lighting / mood / style notes:  Visual examples paired with short descriptions of lighting conditions, atmosphere, and texture. Include transitions across time of day and variations in light quality.    Mood and keywords block: A concise list of emotional tones and thematic descriptors guiding the piece.      

Audio / tone section:  Indications of ambient sound, music style, and overall sonic atmosphere.      

Cinematography notes:  General visual philosophy including lens characteristics, movement style, and post-processing feel.     
 
The entire board should feel cohesive, cinematic, and professionally designed—like a director’s pre-production guide that communicates tone, pacing, and visual storytelling at a glance.
Product Marketing - Origami Furniture Editorial Poster — output

Product Marketing - Origami Furniture Editorial Poster

ShamsGPT Image 2
Architectural Photography. Luxury furniture editorial poster, crumpled paper origami armchair centered in dramatic chiaroscuro lighting, warm sand and charcoal tones, oversized serif headline "FORM IN CHAOS", architectural minimalism, high-end magazine aesthetic. Male model in all-white structured tailcoat, standing beside a sculptural crumpled-paper armchair in a raw concrete interior, soft raking light, editorial fashion photography, muted warm tones, Vogue interiors crossover.
E-commerce Main Image - Hotel-Style Real Estate Bathroom Staging — output

E-commerce Main Image - Hotel-Style Real Estate Bathroom Staging

そう|Claude Codeで始めるAI自動化GPT Image 2
Please take this photo of the {argument name="location" default="bathroom"} and naturally organize the lived-in clutter into a {argument name="atmosphere" default="clean, well-ordered, hotel-like"} bathroom without changing the layout or structural elements like the tub, shower, mirror, lighting, walls, or flooring. Specifically, remove or organize the numerous bottles, refill bags, small items, cleaning supplies, nets, and extra storage baskets found on the tub lid, counter, floor, and shelves into just a few uniform bottles. Clear the floor and areas around the tub to make the space look larger. Naturally remove mirror fog, water spots, and stains from the walls and counter for a bright, clean finish. Maintain a warm, natural lighting atmosphere while making the overall photo slightly brighter and correcting distortions or dark areas. However, keep the bathroom shape, door position, tub, shower fixtures, mirror, lighting, wall panels, and floor textures faithful to the original image. Do not add new furniture or unnatural decorations. Aim for a natural, realistic finish similar to actual real estate or professional cleaning before-and-after photos.
Comic / Storyboard - School Textbook Historical Figure Doodle — output

Comic / Storyboard - School Textbook Historical Figure Doodle

SSSS.CRYPTOMAN⚡️AIGPT Image 2
Create an image of a page from a {argument name="subject" default="history"} textbook used by {argument name="grade level" default="middle school students"}, featuring student doodles. Include poor, messy handwriting, graffiti on the faces of historical figures, and unskilled drawings.
Social Media Post - Sports Car Advertisement with Japanese Girl — output

Social Media Post - Sports Car Advertisement with Japanese Girl

iXGPT Image 2
A scene for a fictional sports car advertisement, sunlight, {argument name="subject" default="a cute Japanese girl"}, in her 20s, {argument name="outfit" default="a tight one-piece dress"}, a woman standing next to a car, strong perspective, dynamic pose, low angle, shot with {argument name="camera" default="iPhone 17"}.
Social Media Post - Clumsy MS Paint Redraw — output

Social Media Post - Clumsy MS Paint Redraw

shinizokSWCGPT Image 2
Redraw the attached image in the most {argument name="quality" default="clumsy, scribbly, and utterly pathetic"} way possible. Use a {argument name="background" default="white"} background, and make it look like it was drawn in MS Paint with a mouse. It should be vaguely similar but also not really, kind of matching but also off in a confusing, awkward way, with that low-quality pixel-by-pixel feel that really emphasizes how ridiculously bad it is. Actually, you know what, whatever, just draw it however you want.
Infographic / Edu Visual - Ancient Greek Philosophers Gathering — output

Infographic / Edu Visual - Ancient Greek Philosophers Gathering

ToroJushiAiGPT Image 2
Two thousand five hundred years ago, {argument name="philosophers" default="Plato, Socrates, and Aristotle"} were sitting in the {argument name="location" default="streets of Athens"} chatting, giving birth to the source of world civilization. The background can include the content of their conversation, following a timeline, overlaid on the city landscape of ancient Greek Athens.
Profile / Avatar - Manga Sketch Doodle Portrait — output

Profile / Avatar - Manga Sketch Doodle Portrait

루피노드 🐰💕GPT Image 2
Create an illustration of the ‘me’ you imagine, in a {argument name="art style" default="Japanese-style illustration style"}, with {argument name="traits" default="distinctive character traits"}, natural emotional expressions, a {argument name="composition" default="half-length composition"}, a dynamic pose, exquisite clothing details, a hand-drawn doodle style, splashed ink brushstrokes, free-flowing lines, a blend of pastel and ink colours, a manga sketch texture, a simple white background, and embellished with stylised elements around the edges, strong atmosphere, high detail, high quality.
Comic / Storyboard - Cinematic Action Movie Storyboard — output

Comic / Storyboard - Cinematic Action Movie Storyboard

ZaraGPT Image 2
Create a high-quality 4K cinematic action movie storyboard with EXACTLY {argument name="panel count" default="8"} PANELS ONLY (no more, no less), showing a {argument name="protagonist" default="female protagonist"} in a realistic fight sequence where she wins. Use dramatic lighting, high contrast shadows, realistic environments ({argument name="location" default="abandoned warehouse, rooftop, or underground fight arena"}), and a gritty film tone. No text anywhere.
The storyboard must include exactly these 8 scenes:
Wide establishing shot of a dark, intense location (rain, dust, or low light atmosphere), both fighters facing each other
Close-up of the woman’s focused expression, controlled breathing, tension building
Opponent attacks first with aggressive movement (punch or kick)
She narrowly dodges—dynamic motion, fast reaction, camera tracking
Close combat exchange—blocks, counters, and impact moments with cinematic slow motion
Turning point—she reads the opponent and lands a clean, powerful counter move
Decisive takedown—opponent falls hard, dramatic impact, environment reacting (dust, water splash, etc.)
Final frame—she stands strong and calm, slightly injured but dominant, looking forward under dramatic lighting, clear victory
Use varied camera angles (wide, close-up, over-shoulder, low angle), realistic fight choreography, motion blur, and physical impact details.
Tone should feel like a Hollywood action film, focusing on tension, realism, and character strength—not stylized or social media aesthetic.
Strict rule: only 8 panels, no repetition, no extra frames.
Infographic / Edu Visual - Science Book Illustration with Cutaway Diagram — output

Infographic / Edu Visual - Science Book Illustration with Cutaway Diagram

simeon-sanaiGPT Image 2
Create a highly detailed {argument name="aspect ratio" default="vertical (3:4)"} educational illustration in the style of a {argument name="illustration style" default="modern children’s popular science illustrated book"} with a {argument name="diagram type" default="cutaway diagram"}.
Infographic / Edu Visual - Printable Paint by Numbers Generator — output

Infographic / Edu Visual - Printable Paint by Numbers Generator

TheRoaringToadyGPT Image 2
Create a professional high-resolution paint-by-numbers template from the provided image as a single PNG only. Use an {argument name="canvas size" default="A4 portrait ratio canvas"} at 300 DPI with a pure white background. The main artwork must be a clean black-and-white line drawing containing only black outlines, black numbers, and white unfilled paintable areas. Do not create a PDF, document, mockup, multi-page layout, or colored version. Do not use color, gray, shading, texture, gradients, transparency, or pre-filled areas in the main artwork.

Analyze the original image and choose the number of colors adaptively based on image complexity, from 1 to a maximum of {argument name="color count" default="14 colors"}. If the image has only 1–2 important colors, use only 1–2 colors; for simple images use 3–6 colors; for medium complexity use 7–10 colors; for complex, photographic, or highly detailed images use 11–14 colors. Do not force unnecessary colors. Assign each selected color one unique number and merge similar shades unless separation is essential for recognition.

Convert the image into simplified, fully closed, easy-to-paint regions while preserving the recognizable composition, main objects, characters, text, logos, foreground, background, and key details. Every paintable white region must contain the correct black number, centered clearly inside the matching area, readable, upright, and not touching outlines. Large black or dark areas from the original must remain white paintable regions with the correct number, not filled black. Only tiny permanent black line details, such as mouth lines, nostrils, pupils, eyelashes, seams, or small decorative strokes, may remain unnumbered.

At the bottom of the same PNG, add a neat legend section with the heading “Instructions”, the sentence “Paint the areas with the matching colors.”, and a list of every used number with a small color swatch and the English color name. Color swatches may appear only in the legend. Ensure the numbering exactly matches the legend, every paintable area is numbered, all regions are closed, and the final result is clean, professional, print-ready, and recognizable as the original image.
Social Media Post - Candid Nightclub Curb Scene — output

Social Media Post - Candid Nightclub Curb Scene

Changning LiuGPT Image 2
Create a gritty, candid flash-photography street scene at night outside a neon-lit nightclub on an urban sidewalk. Two young women sit closely together on the curb in the foreground with their faces deliberately anonymized by soft square blur blocks. The left woman has {argument name="left woman's hair color" default="blonde wavy shoulder-length hair"}, wears a sparkly silver sequined strapless crop top, a short black skirt, and clear platform heels, sitting cross-legged and holding a clear plastic cup with a red drink. The right woman has {argument name="right woman's hair color" default="dark curly hair"}, wears a hot-pink satin mini dress with fuzzy pink trim, pink fishnet tights, and heels, leaning into her friend while holding a smartphone and a cigarette. The scene includes a wet-looking curb and asphalt gutter with spilled liquid, cigarette butts, a crushed can, a plastic cup, and small street debris. In the background, show a city street with bright car headlights, a yellow streetlamp glow, graffiti-covered walls, a black nightclub entrance with bouncers and patrons, queue stanchions, an electric-blue OPEN sign, and a large magenta neon sign reading {argument name="neon sign text" default="LUXE"}. Use strong mixed lighting: purple and pink neon from the club, warm sodium streetlight, harsh phone-camera flash on the subjects, deep night shadows, realistic lens noise, slight motion blur on a passerby at the far right, wide-angle smartphone composition, documentary party-after-hours mood, photorealistic, unpolished, high detail.
Social Media Post - Candid Nightlife Street Snapshot — output

Social Media Post - Candid Nightlife Street Snapshot

Changning LiuGPT Image 2
Create a photorealistic candid nighttime street photo with a gritty flash-photography party snapshot aesthetic. The scene shows {argument name="number of seated women" default="two"} adult women sitting close together on a city sidewalk curb outside nightlife venues, both wearing {argument name="outfit color" default="black"} mini party dresses and small chain-strap purses. Their faces are intentionally anonymized by flat opaque brown square blocks placed over each face. The woman on the left has long dark wavy hair, a deep V-neck black dress, tanned skin, one knee raised, and motion-blurred arms as if she is gesturing or dancing while seated. The woman on the right has shoulder-length blonde hair, a strapless black dress, crossed legs, a delicate necklace, and one hand holding a small dark object near her knee. Include 3 prominent human figures total: the 2 seated women in the foreground and 1 tall adult man in dark clothing walking or standing behind them on the sidewalk, partially cropped at the top. The environment is an urban nightlife street at night, with a concrete sidewalk, parked cars along the road, leafy trees, storefronts and bar entrances, purple neon lighting on the left, warm streetlights, and a visible sign on the left reading {argument name="sign text" default="ENTRANCE ON 3RD STREET"}. Use a wide horizontal 16:9 composition, low eye-level perspective, dim ambient lighting, harsh on-camera flash, slight underexposure, realistic skin highlights, motion blur on moving hands, noisy high-ISO texture, and an unpolished smartphone snapshot look. Keep the background dark and slightly soft while the foreground subjects dominate the frame.
Social Media Post - Candid Nightclub Sidewalk Scene — output

Social Media Post - Candid Nightclub Sidewalk Scene

Changning LiuGPT Image 2
Create a gritty cinematic street-photography scene at night outside a jazz club, shot in a realistic documentary style with warm amber streetlights and high-ISO film grain. Three young women are sitting and lounging on a city sidewalk beside a brick wall: one woman is partially cropped at the far left with her back and black spaghetti-strap dress visible, one woman sits in the center wearing a sparkly dark sleeveless top and black pants with one arm lifted near her hair, and one woman sits against the brick wall on the right wearing a blue denim jacket over a black dress with her legs extended. Their faces are intentionally anonymized with soft rectangular blur blocks. In the background, show an illuminated neon club sign reading {argument name="club sign text" default="THE BLUE NOTE CLUB"}, glowing blue and pink above the sidewalk, with empty city streets, parked cars, street signs, dark buildings, and bokeh lights receding into the distance. Use a wide horizontal composition, 16:9 aspect ratio, eye-level candid angle, deep urban perspective, textured pavement, brick façade, moody nightlife atmosphere, natural imperfect posing, realistic shadows, warm color grading, and subtle lens flare from a bright streetlamp. The overall look should feel like a candid analog photo taken after a night out in {argument name="city setting" default="a downtown American city"}, with {argument name="lighting mood" default="warm sodium-vapor street lighting and neon glow"}.
Product Marketing - Seedance 2.0 Waiting Queue Poster — output

Product Marketing - Seedance 2.0 Waiting Queue Poster

Hailuo AI (MiniMax)GPT Image 2
Create a clean square promotional poster with an isometric miniature 3D diorama on a warm off-white background. At the top, place huge bold rounded sans-serif headline text reading {argument name="headline text" default="Seedance 2.0 No More Waiting"}, split across 2 lines, with a vibrant left-to-right gradient from blue and violet through magenta to orange. Below the headline, show a long serpentine queue of tiny stylized people waiting in front of a row of minimalist white cube buildings; include 12 visible white building units receding into the distance, each with simple rectangular windows and doors, and one prominent open doorway on the right. The crowd should contain dozens of small diverse figures in casual clothing, arranged in a winding line that creates depth, with one purple-uniformed staff member near the open doorway gesturing people inside. Use soft studio lighting, shallow depth of field, subtle shadows, glossy clean surfaces, and a premium tech-advertising look. At the bottom center, place a colorful circular gradient app-style icon followed by the black wordmark {argument name="brand name" default="HailuoAI"}. Keep the composition airy and minimal, with the headline dominating the upper half and the queue scene occupying the middle and lower area.
Profile / Avatar - Ice Codex Robot Avatar — output

Profile / Avatar - Ice Codex Robot Avatar

ICEGPT Image 2
Create a single full-body chibi codex avatar mascot on a clean white background with faint icy blue paint splatters and a soft frozen-ground shadow. The character is a small futuristic robot in an oversized dark navy-black hooded parka and chunky boots, rendered as a high-detail 3D digital illustration with painterly texture, glossy sci-fi materials, cyan rim lighting, and a cold arctic color palette. The hood is round and helmet-like, framing a black rounded-rectangle visor face with two sleepy half-lidded glowing cyan eyes and no mouth, giving a calm unimpressed expression. Add exactly 7 translucent jagged ice crystals protruding from the top and sides of the hood, with the tallest crystal at the center top, glowing electric blue edges, frosty refractions, and snow-like speckles. Put exactly 2 glowing atom emblems on the suit: one large cyan atom symbol on the left side of the hood and one smaller atom symbol on the chest/left shoulder area. The torso armor is puffy and segmented with cyan circuit-like accents, small luminous panels, scuffs, scratches, and the glowing chest text {argument name="chest text" default="DL"}. In the character’s left hand, show exactly 5 stacked translucent glowing cyan crystalline data sheets or code pages fanned together; in the right hand, show exactly 1 open miniature laptop angled toward the viewer, with a cyan-on-black screen filled with tiny unreadable code lines. Use a centered composition, cute proportions with a large head and short limbs, dramatic icy blue highlights, detailed snow/ice texture on the ground, and a premium mascot-avatar look suitable for a developer profile picture. Customize the avatar as {argument name="avatar theme" default="ice codex robot"}, with {argument name="primary color" default="deep navy blue"} armor and {argument name="glow color" default="cyan blue"} lighting.
E-commerce Main Image - Luxury Perfume Fashion Mockup — output

E-commerce Main Image - Luxury Perfume Fashion Mockup

Uttam BakoriGPT Image 2
Using the provided reference image as the product base, transform the simple perfume-bottle shot into a studio-quality fashion advertising mockup. Keep the perfume bottle design, label text, black cap, amber liquid, and glass shape accurate and readable, but place it in the foreground being held close to the camera by one model's hand. Add exactly 1 fashion model in the background, posed dynamically in a low-angle wide-lens composition, wearing a {argument name="suit color" default="bright orange"} suit with a black shirt, black belt, and glossy black dress shoes. The model should stand in a confident editorial stance with one leg extended forward and the product exaggerated in scale by perspective. Use a clean warm beige studio backdrop, professional softbox lighting, crisp commercial product reflections, shallow depth of field, and a premium luxury fragrance campaign look. Keep the face unobtrusive or softly blurred so the product remains the hero. Overall mood: bold, modern, high-fashion, polished studio mockup.
Product Marketing - Luxury GPT Images 2.0 Launch Poster — output

Product Marketing - Luxury GPT Images 2.0 Launch Poster

Hailuo AI (MiniMax)GPT Image 2
Create a luxurious vertical promotional poster for {argument name="product name" default="GPT Images"} {argument name="version number" default="2.0"}, in a premium cinematic 3D style. The scene features one iridescent mosaic chameleon perched on top of one large pearly seashell, both covered in tiny reflective mirror tiles and mother-of-pearl surfaces, sparkling with rose-gold and cool cyan highlights. Use a deep teal-to-navy gradient background filled with glittering particle dust, thin elegant orbital light trails, starburst lens flares, and a shimmering reflective floor with scattered sparkling bokeh. Place the typography prominently in the upper half: 4 visible text elements total, consisting of the oversized metallic serif headline “{argument name="headline text" default="GPT Images"}”, the separate small version text “{argument name="version text" default="2.0"}” to the right, the left-side stacked tagline “{argument name="tagline" default="Words are your vision."}”, and the bottom-right brand mark reading “{argument name="brand name" default="HailuoAI"}” beside a colorful rounded swirl icon. Use elegant high-contrast Didot/Bodoni-style serif lettering for the main title, pale silver chrome material, subtle beveling, and refined spacing. The composition should feel like a high-end technology launch ad: glossy, magical, fashion editorial lighting, ultra-detailed 3D render, reflective caustics, soft volumetric glow, sharp focus on the chameleon and shell, vertical 2:3 aspect ratio.
Profile / Avatar - Chibi Boutique Mirror Selfie — output

Profile / Avatar - Chibi Boutique Mirror Selfie

伟 翟GPT Image 2
{"type":"scrapbook-style fashion mirror selfie with chibi character overlays","scene":"A vertical full-length mirror selfie inside a softly lit minimalist clothing boutique, warm beige and cream tones, polished concrete floor, clothing racks on the right, folded clothes and a black handbag on wooden shelves on the left, tall indoor plants, track lights on the ceiling, elegant lifestyle shopping atmosphere.","main_subject":{"description":"A fashionable young woman taking a mirror selfie with her phone held in front of her face, standing relaxed in the center of the mirror.","outfit":{"cardigan":"{argument name=\"cardigan color\" default=\"heather gray oversized knit cardigan\"}","top":"black fitted camisole or ribbed tank top","jeans":"{argument name=\"jeans style\" default=\"high-waisted wide-leg light blue jeans\"}","shoes":"black pointed flats","bags":"two cream canvas tote bags, one on the shoulder and one held by hand, plus a small black crossbody bag"},"hair":"{argument name=\"hair style\" default=\"long wavy black hair\"}","face":"softly anonymized or obscured for privacy, realistic body proportions"},"chibi_overlays":{"style":"cute anime chibi mini versions of the main subject, oversized head, glossy black wavy hair, round glasses on some variants, same gray cardigan and blue jeans outfit, blended into the photo like hand-drawn scrapbook stickers with soft shadows","count":5,"poses":[{"position":"mid-left on the shelf","description":"one sleepy chibi resting her head on folded clothes, leaning on the wooden shelf"},{"position":"upper-right floating near the subject's head","description":"one joyful chibi jumping in the air with arms raised and one leg bent"},{"position":"right side behind clothing rack","description":"one shy chibi peeking from behind hanging clothes, smiling with round glasses"},{"position":"bottom-left on the floor","description":"one curled-up chibi sitting cross-legged with sleeves covering her hands"},{"position":"bottom-right near the shopping bag","description":"one seated chibi holding a small drink or phone, surrounded by hearts"}]},"scrapbook_details":{"doodles":"white hand-drawn hearts, sparkles, motion marks, and tiny decorative lines placed around the main subject and chibis","text_elements":{"count":4,"labels":["NEW ARRIVAL on a wall poster","Arles on the canvas tote bag","depound beneath the tote text and poster","Simplicity is the ultimate sophistication. Leonardo da Vinci on a framed sign"]},"mood":"cozy, fashionable, playful, diary-like, premium lifestyle scrapbook aesthetic"},"composition":{"camera":"smartphone mirror selfie, straight-on full-body framing, vertical 3:4 aspect ratio","lighting":"warm indoor boutique lighting, soft highlights, gentle shadows","quality":"photorealistic background with clean high-resolution anime chibi overlays, seamless integration, no clutter, polished social-media-ready image"},"custom_text":"Optional handwritten caption in the scrapbook style: {argument name=\"handwritten caption\" default=\"shopping day\"}"}
Infographic / Edu Visual - Chinese Game News Daily Front Page — output

Infographic / Edu Visual - Chinese Game News Daily Front Page

MSBGPT Image 2
{"type":"vertical game news daily newspaper front page poster","language":"Chinese newspaper layout with some English labels","format":"single-page editorial infographic, retro print design, cream paper background, thick black borders, red and green accent tabs, halftone shadows, pixel-art screenshots mixed with bold Chinese typography","header":{"left_sidebar":"red vertical masthead with newspaper icon and text GAME NEWS DAILY","main_title":"{argument name=\"newspaper title\" default=\"今日游戏要闻\"}","date":"{argument name=\"issue date\" default=\"2026-05-02\"}","right_box":"GAME NEWS, DAILY, VOL.0502","decorations":"horizontal rule lines, small red pixel corner marks"},"layout":{"sections":[{"title":"HEADLINE","position":"large upper-left feature card","count":1,"content":"Main story about the game Red Desert version 1.05.00 update introducing a Mountain God Wild Boar boss","headline_text":"{argument name=\"main headline\" default=\"《红色沙漠》1.05.00更新,‘山神野猪’登场。\"}","visual":"large pixel-art fantasy wild boar with red eye, tusks, braided mane and bone ornaments in a pine forest with distant mountains and castle spires","details":"Chinese body copy in small newspaper columns, red READ MORE button, black version tag reading 版本:1.05.00"},{"title":"INDUSTRY","position":"upper-right column","count":2,"items":[{"label":"FINAL FANTASY XIV EVERCOLD","description":"blue icy expansion/news card with snowy crystal mountains and headline FF14柏林粉丝节揭秘 ‘Evercold’ 资料片, plus green READ MORE button"},{"label":"Survios工作室裁员动态","description":"Survios logo and photo of people in a meeting room, Chinese summary about VR studio layoffs, green READ MORE button"}]},{"title":"COOPERATION","position":"middle-left wide card","count":1,"headline":"新加坡资媒局与腾讯推健康数码游戏计划","visual":"Merlion statue spraying water in front of a bright city skyline, IMDA logo, Tencent 腾讯 logo, blue cooperation label"},{"title":"ESPORTS FLASH","position":"middle horizontal strip","count":3,"items":[{"label":"HLE击败T1","description":"red-and-black match card showing HLE vs T1 logos and gold trophy, Chinese note that HLE defeated T1 2:1 in LCK regular season"},{"label":"无锡TCG晋级《挑战者杯》八强","description":"blue card with WUXI TCG shield logo, pagoda and sky background, gold trophy icon"},{"label":"ACL选手BOROS禁赛","description":"dark red card with banned symbol over a player silhouette and large BANNED stamp"}]},{"title":"NEW GAMES COMING SOON","position":"bottom row","count":3,"items":[{"label":"《无敌少侠VS.》","description":"cartoon fighting-game screenshot with two characters punching, platform tags PS5 / XSX|S, 2026 release, yellow gamepad icon"},{"label":"《极限竞速:地平线6》","description":"orange sports car racing along a tropical coast, platform tags including Xbox Series X|S / PC, steering wheel icon"},{"label":"《耀西与不可思议的图鉴》","description":"green Yoshi in a colorful side-scrolling landscape, Nintendo Switch 2 tag, handheld console icon, small blue label 期待新作"}]}]},"footer":{"left":"red gamepad icon and slogan STAY INFORMED. STAY AHEAD.","center":"small black pixel navigation icons","right":"THANK YOU FOR READING! with red pixel corner decoration"},"style":{"art_direction":"Japanese/Chinese gaming newspaper demo, dense but clean editorial grid, bold Ming/Song-style Chinese title typography, mixed serif English labels, faux printed ink texture, comic-news clipping aesthetic","color_palette":"cream, black, deep red, forest green, navy blue, muted yellow","image_treatment":"pixel art and retro game screenshot thumbnails with crisp borders","composition":"portrait 3:4 aspect ratio, all cards aligned to a strict newspaper grid, high information density but readable hierarchy"}}
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 ↗