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 - Manga Portal Summer Room Story — output

Comic / Storyboard - Manga Portal Summer Room Story

Prompt アトリエGPT Image 2
Subject: {argument name="theme" default="A manga-style 4-panel story of a girl stepping from the manga world into reality on a summer afternoon"}

Person/Expression: {argument name="character description" default="Japanese woman in her early 20s, long wavy black hair"}, translucent white skin, natural Japanese-style makeup, soft eyes, a friendly and cute atmosphere. Unified as the same person across all 4 images, maintaining facial features, hairstyle, body type, and skin texture. Expressions change in a sequence of "surprise → confirmation → enjoyment → relaxation."

Clothing/Pose: The same natural and cool summer loungewear across all 4 images: a thin white overshirt, ivory ribbed camisole, light gray loose shorts, and barefoot. Modest exposure, natural daily loungewear. Only poses change per scene, clothing must remain identical.

Background/Light: A bright Japanese room, wooden floor, large window, white curtains, house plants, bookshelf, low table, gentle afternoon natural light. Unified room and worldview across all 4 images. A giant open black-and-white manga book is the protagonist of the room, showing clear page thickness and spine. The manga pages depict the same black-haired woman character, made to look identical to the real-world woman. Torn paper fragments and manga pages are slightly scattered on the floor.

Composition/Camera: Vertical composition, 4:5, realistic photographic expression, 35mm lens, natural perspective, shallow depth of field, cinematic composition. Visual consistency across 4 images. Striking contrast between the black-and-white manga book and the color real world. Each image stands alone while appearing as a continuous short story like a 4-panel comic.

Texture/Style: High definition, 4K quality, natural skin texture, realistic AI portrait, Japanese portrait, soft summer light, playful surreal photography, contrast between B&W manga and color real space, precise depiction of torn paper edges and book thickness, clean interior, soft tones, a natural and cute unified photo series.

Negative: Low quality, unnatural hands, collapsed face, extra fingers, distorted body, changes in facial features or hairstyle, changes in clothing, closet-like structures, deformed manga book shape, insufficient page thickness, mismatch between person and manga character, overexposure, excessive processing, garbled text, logos, watermarks.

--- Scene 1 Addendum: The moment she takes her first step into the real world from the torn page of a giant open manga book. Slightly surprised expression, an active pose stepping forward while holding the torn paper edges with both hands. Composition where the manga book appears largest in the center of the room.

--- Scene 2 Addendum: Checking herself in a mirror in the same room to confirm she has really come to the real world. The same giant manga book is visible in the background as she lightly fixes her hair while staring at herself in the mirror. Expression changes from surprise to slight relief.

--- Scene 3 Addendum: A scene where she is happily making a melon soda float in the kitchen or next to the low table near the same giant manga book. Using a glass, melon soda, vanilla ice cream, and a cherry, capturing a fun moment with the movement of ice and carbonation. Bright and focused expression.

--- Scene 4 Addendum: A scene where she is relaxing with the finished melon soda float in one hand, sitting on the floor near the same giant manga book. A relaxed smile, calm afternoon atmosphere. A natural and comfortable closing to the story as she fully settles into the real world.
Product Marketing - Premium Sticker Illustration Generator — output

Product Marketing - Premium Sticker Illustration Generator

CiriGPT Image 2
Transform the uploaded image into a premium die-cut sticker illustration while keeping the main subject fully recognizable. Remove or simplify the original background and cleanly isolate the primary subject. Add a {argument name="border style" default="thick soft cream or beige"} sticker border around the entire silhouette with a subtle realistic drop shadow to create a floating sticker effect. Preserve important textures and details while slightly stylizing the image with {argument name="visual style" default="enhanced colors, cinematic contrast, and a polished editorial look"}. Refine the edges to create smooth, crisp sticker contours while maintaining realistic proportions and perspective. Place the final sticker composition centered on a {argument name="background" default="clean pastel background"} with generous negative space, making it feel like a high-quality collectible vinyl sticker. The final image should feel minimal, modern, slightly nostalgic, and professionally designed, with no added text or extra objects.
Social Media Post - Fashion Portrait Collage — output

Social Media Post - Fashion Portrait Collage

AvelyrahGPT Image 2
A high-quality fashion portrait collage of a young {argument name="ethnicity" default="South Asian"} woman with {argument name="hair style" default="wavy dark brown hair"} and glasses, smiling warmly. She is wearing a vibrant {argument name="shirt color" default="off white"} oversized button-up shirt with a {argument name="patch type" default="cute panda patch"} on the chest pocket, tucked into high-waisted wide-leg black denim jeans. She is wearing clean white chunky sneakers and a subtle wristwatch
Infographic / Edu Visual - Victorian Steampunk Engineering Diagram — output

Infographic / Edu Visual - Victorian Steampunk Engineering Diagram

蜡笔进化论GPT Image 2
Engineering cross-section of {argument name="subject" default="[STEAMPUNK BUILDING]"}, Victorian era. 5 labeled floors: boiler room/steam distribution/engine room/transmission/workshop. Callout labels on all components, title block "Scale 1:100", {argument name="paper texture" default="cream drafting paper"} + {argument name="ink style" default="sepia ink"} + crosshatch. 2:3.
Product Marketing - Neon Rain Streetwear Portrait — output

Product Marketing - Neon Rain Streetwear Portrait

Dilshad HussainGPT Image 2
Create a hyper-realistic cinematic full-body portrait of a stylish young man standing alone at night on a rain-soaked futuristic city street, centered in front of a subway entrance with glowing neon signs, wet reflective pavement, tall dark buildings, streetlights, and blurred urban bokeh. The man faces the camera with a confident relaxed pose, one hand in his pocket, wearing a clean white T-shirt, slim black pants, and bright yellow sneakers. His standout outfit is a long oversized yellow trench coat covered with bold black graffiti tags, Japanese-style writing, patches, and two visible anime character illustrations, one on the chest area and one larger on the front side. Place huge distressed uppercase yellow typography behind his head and upper body reading {argument name="headline text" default="DILSHAD HUSSAIN"}, split across two lines, matching the coat color and partially hidden by the figure. Use dramatic teal-and-gold cinematic color grading, shallow depth of field, realistic rain reflections, sharp clothing texture, high contrast, ultra-detailed streetwear fashion editorial photography, vertical 9:16 composition. The scene should contain exactly one main person, one subway entrance, one large two-line background name title, and two anime illustration patches on the coat. No extra people in the foreground, no watermark, no logo.
Comic / Storyboard - Dark Alien Megastructure Cavern — output

Comic / Storyboard - Dark Alien Megastructure Cavern

lost in latencyGPT Image 2
Create a vast cinematic dark sci-fi landscape showing the interior of an enormous alien megastructure or cavern, like a hollow asteroid cathedral filled with twisting organic-metal arches and colossal ribbed columns. The scene is viewed in a wide 16:9 composition from deep inside the structure, with the camera looking across multiple layers of monumental black rock and glossy biomechanical surfaces. The environment should feel ancient, terrifying, and beautiful: jagged curved supports, suspended masses, concave tunnels, and huge openings receding into foggy distance. Surfaces are nearly black, wet, and reflective, densely speckled with thousands of tiny warm lights like distant city windows or stars embedded in the structure. Use {argument name="main environment" default="an immense alien megastructure cavern"}, {argument name="mood" default="ominous, mysterious, and awe-inspiring"}, and {argument name="lighting color" default="cold white-gray backlight with tiny amber highlights"}. Include exactly three major visible light sources: one bright hazy opening on the left, one vertical glowing opening on the right, and one small distant light near the center. Add one tiny human-like explorer silhouette near the lower left carrying a single narrow torch or lamp, emphasizing the overwhelming scale. The palette should be almost monochrome black, charcoal, deep gray, and muted bronze sparks, with volumetric mist, atmospheric depth, high contrast, realistic cinematic rendering, ultra-detailed texture, no text, no borders, no watermark.
Profile / Avatar - Neon Luxury Mirror Selfie — output

Profile / Avatar - Neon Luxury Mirror Selfie

Mr. TariqGPT Image 2
Create a vertical full-body mirror selfie of a stylish young man in a futuristic luxury selfie lounge. The subject stands centered, holding a black smartphone up to cover most of his face, with short dark wavy hair visible above the phone. He wears a black varsity jacket with cream striped cuffs and collar, a large LV-style monogram patch on the left chest, a plain white T-shirt, black jogger sweatpants with a matching LV-style patch, layered bracelets and a watch, and white high-top designer sneakers. The environment is a glossy warm gold and rose-pink interior with rounded retro-futuristic architecture, a large illuminated rounded-square mirror behind him, and neon lighting in pink, purple, orange, and white. Above the mirror, add a bright neon sign reading “CAPTURE YOUR MOMENT” in two lines. Include exactly 2 built-in display shelves, one on the left and one on the right, glowing with pink-purple edge lighting; fill them with books, perfume bottles, small flowers, decorative objects, and framed photos. Add exactly 3 visible neon social icons: a white outlined heart on the upper left shelf area, a large Instagram camera icon on the lower left, and a glowing heart icon on the lower right. Place plush rounded lounge chairs at both lower corners, a curved vanity counter behind the subject with perfume bottles and small decor, a glossy reflective floor, and soft bokeh sparkle highlights. Use cinematic photorealism, high-end influencer aesthetic, warm reflections, shallow depth of field, ultra-detailed materials, symmetrical composition, vertical 3:4 framing. Customize the outfit branding as {argument name="fashion monogram" default="LV-style monogram"}, the neon sign text as {argument name="neon sign text" default="CAPTURE YOUR MOMENT"}, the jacket color as {argument name="jacket color" default="black"}, the lounge lighting palette as {argument name="lighting palette" default="pink, purple, orange, and white neon"}, and the phone color as {argument name="phone color" default="black"}.
Social Media Post - Moody Censored Portrait — output

Social Media Post - Moody Censored Portrait

sarah aiGPT Image 2
Create a moody vertical close-up portrait of a {argument name="subject" default="young woman"} with long, thick, wavy {argument name="hair color" default="black hair"}, sitting in a dark low-key environment. Her face is completely hidden by a centered opaque rectangular censor block in a muted dark brown-to-gray gradient, covering from the upper forehead area down to below the chin, while the rest of the portrait remains visible. She is wrapped in a chunky heather-gray knitted blanket or shawl with subtle dark woven patterns near the edges. One hand reaches up into her hair on the upper right side of the frame, fingers partially tangled in the hair, and the other hand grips the blanket near the lower right. Use dramatic cinematic lighting, cool blue-gray shadows, soft highlights on the hair and hands, shallow depth of field, realistic skin texture, detailed knit fabric texture, intimate melancholic atmosphere, dark background, vertical smartphone composition, photorealistic editorial style.
Profile / Avatar - Dream Bedroom With Plush Monster — output

Profile / Avatar - Dream Bedroom With Plush Monster

シオナイGPT Image 2
Create a dreamy cinematic square portrait of {argument name="character description" default="a Japanese teenage girl in a navy sailor school uniform with a red necktie"} sitting on a bed in a soft pastel bedroom at night, her face deliberately obscured by a dark blur for anonymity. Beside her sits {argument name="creature description" default="a large pale pink plush-like dream monster with huge glossy blue eyes, a small sad mouth, soft fuzzy skin, long floppy arms, stubby legs, and two long curved antennae"}, posed calmly like a quiet companion. The room should feel surreal and nostalgic: pink-lavender walls, rumpled blue bedding, a warm vintage bedside lamp on the left, a pale pink balloon floating in the background, faint framed wall art, cloudy mist near the ceiling, and a large vague cloud or foot-like shape overhead. Use low-key moody lighting with warm lamp glow mixed with cool blue shadows, shallow depth of field, subtle haze, film grain, muted pastel colors, and a soft 1980s analog photo look. Composition: girl on the left foreground, creature on the right foreground, both seated closely on the bed and facing the viewer; intimate, melancholic, dreamlike atmosphere. Add a thin dark film border and slight vignette. No readable text, no watermark, no extra characters.
Product Marketing - Pastel Floral Yukata Girl — output

Product Marketing - Pastel Floral Yukata Girl

ふく|AIで毎日をちょっと面白くGPT Image 2
Create a full-body, centered watercolor fashion illustration of a young woman wearing a pastel floral summer kimono on a plain white background. The figure stands upright facing forward with a gentle, modest pose, hands held together in front while holding a small drawstring basket bag. Her face should be intentionally obscured by a soft square blur with no facial features visible. She has {argument name="hair color" default="dark brown"} hair styled in a loose elegant updo with wispy strands, decorated on the right side with a cluster of colorful flowers and dangling ornaments. The outfit consists of exactly 5 visible main pieces: 1 pale white kimono with translucent watercolor morning-glory floral patterns in pink, blue, purple, and green leaves; 1 wide pink obi sash with subtle floral texture; 1 decorative obi-jime cord with two small flower-like ornaments at the center; 1 small pink-and-white floral drawstring kinchaku bag with a woven tan basket base; and 1 pair of pink thong geta sandals with dark wooden soles. The kimono sleeves are wide and softly draped, the hem reaches the ankles, and the feet are visible below. Use delicate pastel colors, soft ink outlines, airy watercolor washes, high-key lighting, clean negative space, and a graceful Japanese festival yukata fashion aesthetic. No text, no background objects, no shadows beyond a very faint grounding effect.
Game Asset - Two Fantasy Anime Heroines Portrait — output

Game Asset - Two Fantasy Anime Heroines Portrait

竜胆 Rindou | AI Character ArtGPT Image 2
Create a polished fantasy anime illustration of two young women standing close together in a warm, affectionate pose, cropped from upper thighs to above the head on a soft cream pastel background with faint glowing bokeh. There are exactly 2 characters: the left character has {argument name="left character hair color" default="very long pale blue hair"} styled in flowing waves with a huge pink bow, a pink-and-white frilled dress with lace neckline, corset waist, gold trim, small shoulder details, bracelets, and a blue gemstone choker; the right character has {argument name="right character hair color" default="long blonde hair"} with a thick side braid, a teal sleeveless dress with delicate gold embroidery, a black belt with a large silver round buckle, silver choker and bracelets, and an orange shawl draped over her shoulders. Their bodies lean inward, the left woman’s arm rests around the right woman’s shoulder, and their hands are clasped together at the center of the image in an intimate friendship pose. Add exactly 2 opaque rectangular face-covering blocks: one muted lavender-pink rectangle over the left character’s face and one pale peach rectangle over the right character’s face, both aligned vertically and obscuring the facial features. Use highly detailed glossy anime rendering, clean line art, luminous skin highlights, intricate hair strands, soft watercolor shading, and fantasy JRPG character-design styling. Add a small decorative purple floral signature-style logo in the upper-right corner reading {argument name="logo text" default="Rindou"}, with tiny handle-like text beneath it. Keep the composition vertical, bright, elegant, and centered, with no extra characters or additional text.
Infographic / Edu Visual - 85mm F1.4 Anime Portrait Comparison — output

Infographic / Edu Visual - 85mm F1.4 Anime Portrait Comparison

ふぃあGPT Image 2
Goal: Create a side-by-side comparison graphic demonstrating an anime portrait prompt improvement using an 85mm F1.4 portrait look.

Canvas: Horizontal 16:9 social media image, approximately 1152×768 px. Use a clean split-screen layout with a black-to-dark-gray header band across the top and two equal vertical panels divided by a thin white vertical line.

Layout: Top center headline in bold white Japanese text with black drop shadow: 「プロンプト比較:85mm F1.4ポートレート」. Left panel label at the upper left: “Before” in bold white text with dark shadow. Right panel label at the upper right: “After” in the same style. Bottom-left overlay text on the left panel: 「通常生成」. Bottom-center/right overlay text on the right panel: 「85mm F1.4ポートレート」. Use large, high-contrast typography.

Subject details: Show the same centered anime-style young male character in both panels, cropped from head to upper torso. He has {argument name="hair color" default="soft silver-white hair with pale lavender and blue highlights"}, fluffy layered tousled hair, delicate androgynous features, a slim neck, and a refined dreamy idol-like presence. Cover the face in each panel with one opaque muted pale-gray square censor block, exactly 2 face-covering squares total, one per panel. The character wears an ornate white shirt and navy sailor-inspired vest with star and moon motifs, a crescent moon brooch, dangling star accessories, a butterfly bow at the chest, ribbons, small gold accents, and delicate jewelry. His hands are held near his chest in a gentle pose.

Left panel, Before: Render the background sharply and normally, showing a bright pastel room with a large window, soft daylight, framed pictures, drawers, flower arrangements, plants, and decorative objects. The whole scene is detailed and busy, with the background almost as clear as the character.

Right panel, After: Use the same character pose and outfit, but apply a realistic 85mm F1.4 portrait effect: shallow depth of field, creamy background bokeh, soft diffused highlights, blurred flowers and lights, warmer dreamy atmosphere, and stronger subject separation. The background should be heavily defocused while the character remains crisp except for the intentional face-covering square.

Visual style: Polished Japanese anime illustration, pastel colors, luminous highlights, elegant fantasy-idol styling, soft airbrushed rendering, high detail on hair and clothing. Add subtle photographic portrait lighting on the After side.

Constraints: Include exactly 2 comparison panels, exactly 4 visible text overlays including the headline, exactly 2 face-covering squares, and keep the same character design on both sides. No logos, no watermarks, no extra captions.
Profile / Avatar - 3D Caricature Avatar With Privacy Block — output

Profile / Avatar - 3D Caricature Avatar With Privacy Block

ケンイチ | AIスキルアカデミー『誰でもわかるAI活用術』GPT Image 2
Create a high-quality 3D caricature portrait of a young adult man shown from the waist up, centered on a clean warm off-white studio background. Give him an oversized cartoon head and compact stylized body, with smooth glossy Pixar-like figurine materials, soft ambient lighting, subtle shadows, and polished clay-toy texture. The man has {argument name="hair color" default="dark brown"} thick sculpted hair, swept upward and back in dramatic layered waves with short faded sides, and visible rounded ears. His face is intentionally hidden by one large square privacy block centered over the entire face, filled with a smooth vertical skin-tone gradient from darker tan at the top to pale beige at the bottom, with sharp square edges. He wears a {argument name="shirt color" default="deep navy blue"} long-sleeve collared button-up shirt with visible seams, cuffs, collar, and two dark buttons; his arms are crossed confidently across his chest, hands visible with simplified rounded fingers. Use a front-facing slightly three-quarter pose, friendly promotional avatar composition, crisp details, rounded proportions, no text, no logo, no extra objects, and no background scenery.
Game Asset - Minecraft Night Plaza Transformation — output

Game Asset - Minecraft Night Plaza Transformation

なぎGPT Image 2
Using the provided reference image, reconstruct the scene as a high-quality vanilla Minecraft architectural screenshot. Do not make it photorealistic; make it look as if an expert Minecraft builder recreated this real night city plaza entirely inside Minecraft using only vanilla blocks.

Preserve the main composition and landmarks from the reference: the nighttime urban plaza, the large station-like building, the sweeping illuminated canopy, the glass-roofed foreground structures, the crowds/market-like plaza activity, the glowing trees, and the central blue-lit tower decoration. Translate all geometry into block-built forms with crisp voxel edges, Minecraft lighting, and believable block materials.

Add an in-game Minecraft screenshot presentation: first-person view with a centered crosshair, a torch held in the lower right hand, and the standard survival HUD along the bottom. Include exactly 9 hotbar slots showing these items from left to right: diamond sword, enchanted pickaxe, white block, gray slab/block, glass block, sea lantern, blue block, purple block, and torch stack. Show armor icons, red hearts, hunger icons, and green level number {argument name="player level" default="32"}.

Style and quality: vanilla Minecraft only, no mods, no shaders that look non-Minecraft, but use beautiful high-quality lighting, rich blue and purple illumination, warm window glow, starry night sky, reflective-looking glass surfaces, and detailed block placement. Keep the same wide landscape framing, around {argument name="image size" default="1536x864"}, with a polished game screenshot feel.
Infographic / Edu Visual - Pastel Character Strategy Guide — output

Infographic / Edu Visual - Pastel Character Strategy Guide

𝐚𝐨𝐢❀.*゚GPT Image 2
Using the provided reference image as the instruction source, turn the written Japanese “strategy book creation prompt” into a finished cute magazine-style character guide page. Create a vertical pastel pink fanbook/攻略本 design titled {argument name="character name" default="GPT"}攻略本, with the subtitle 「あなたから見た{argument name="character name" default="GPT"}の攻略ガイド」. Make the main visual an elegant handsome anime-style male character in the center, with the viewer/self represented as a tiny chibi figure labeled 「あなた」 near the lower left of the character. Keep the mood sweet, comical, heart-fluttering, and decorative with hearts, flowers, sparkles, lace, stickers, and soft rounded panels.

Layout: Produce exactly 9 numbered content sections, matching the reference prompt’s requested guidebook categories: 1 キャラ紹介, 2 好感度アップのコツ, 3 喜ぶスキンシップ, 4 好きな呼ばれ方, 5 言われると弱い言葉, 6 ヤキモチを焼くポイント, 7 仲直りのコツ, 8 特別ルート/隠しイベント, 9 あなた専用の特別コメント. Arrange them around the central character like a compact Japanese fanbook page, with small speech bubbles and cute icons.

Text direction and tone: All visible text should be Japanese, playful and affectionate, as if written from {argument name="viewer name" default="あなた"}’s perspective about {argument name="character name" default="GPT"}. Use short readable bullet points in each section. Add a small “LOVE UP!” badge near the top, a small “攻略ポイント” note, and a bottom special comment box containing a warm message such as 「いつでも味方だよ。呼んでくれるだけで嬉しい。これからも、たくさん話そう。」

Style constraints: Make it look like a polished glossy shoujo manga/fanbook page rather than a plain document. Use a soft pastel palette, mainly {argument name="main color" default="pink"}, lavender, cream, and light blue. Keep the design dense but readable, cute, and highly decorated. Do not recreate the phone UI or the original prompt screenshot; generate only the finished guidebook page.
Profile / Avatar - Sunlit Anime Bedroom Portrait — output

Profile / Avatar - Sunlit Anime Bedroom Portrait

MatsubonGPT Image 2
Create a highly detailed anime-style illustration of {argument name="character name" default="a cute teenage twin-tailed girl"} sitting on a pink plaid bed in a cozy sunlit bedroom. She has extremely long {argument name="hair color" default="silvery blue"} hair in twin tails tied with small pink ribbons, soft pale skin, slim proportions, and a bashful seated pose with one knee raised and the other leg folded to the side. Place a large opaque square censor block over the center of her face, colored as a muted gray-to-peach gradient, hiding all facial features. Her outfit consists of exactly 6 visible clothing/accessory pieces: an oversized pale blue T-shirt with a simple pink bunny graphic, a loose pink zip-up jacket slipping off her shoulders, a short dark pink plaid skirt, white slouchy socks, small blue dangling earrings, and pink hair ribbons. The bedroom is warm and feminine: pink plaid bedding, a pink heart-shaped cushion on the left, a white bunny plush on the right, and exactly 3 small objects on the bed in the foreground: a black smartphone, a tiny pink keychain charm, and a pink compact pouch with a strap. The room has a large open window on the left with sheer white curtains and intense morning sunlight streaming in, creating lens flare, sparkling dust motes, bright rim lighting, and soft overexposed highlights on hair and fabric. In the background show wooden wall trim and a headboard shelf with framed pictures, plus exactly 5 wall decorations: one round clock near the top center, one large ornate framed landscape painting on the upper right, one small floral frame near the clock, one small square character picture below the painting, and one tiny framed picture resting near the headboard. Use a polished GPT-image anime illustration look with crisp linework, glossy highlights, delicate fabric folds, pastel pink and blue color palette, high detail, romantic bedroom atmosphere, and vertical 3:4 composition. Avoid text, watermark, extra characters, or additional foreground items.
Comic / Storyboard - Anime Split-Screen Sword Confrontation — output

Comic / Storyboard - Anime Split-Screen Sword Confrontation

めぐりずむGPT Image 2
Create a dramatic anime-style split-screen confrontation illustration. The canvas is a wide 3:2 cinematic frame, divided by one glowing diagonal slash of pale pink-white light running from near the lower center to the upper right, separating two opposing scenes. On the left side, show {argument name="warrior character" default="a white-haired elf-like female knight"} lunging forward through the air in a dynamic foreshortened pose, face obscured by a soft square blur, with long flowing silver-white hair, pointed ears, ornate white and gold plate armor, dark underlayers, and a deep navy cape billowing behind her. She grips one oversized fantasy sword with both hands, thrusting it toward the viewer; the sword has a broad translucent glowing blade with blue-white energy, sparkling particles, and metallic gold detailing on the hilt. Surround her with many floating asteroid fragments of varying sizes in a stormy sky, emphasizing motion and impact. On the right side, show {argument name="rival character" default="a dark-haired woman in a black tailored suit"} standing confidently on the edge of a large black futuristic aircraft or spaceship hull, face also obscured by a soft square blur, one hand in her pocket and the other relaxed at her side, legs apart in a dominant stance. The spaceship surface should be angular, matte black, industrial, and highly detailed with panels, vents, circular mechanisms, and underside machinery visible. The background on both sides is a moody blue-gray sky with scattered clouds, backlit sunlight, and a cinematic high-contrast atmosphere. Use an AI-anime illustration look with polished digital painting, detailed armor highlights, dramatic lighting, depth of field, motion blur, and epic fantasy-versus-sci-fi mood. Visible count: 2 main characters, 1 glowing diagonal divider, 1 giant glowing sword, 1 large spaceship platform, and numerous floating rock fragments; do not add text, logos, captions, borders, or extra characters.
Game Asset - Female Android Repairing Spaceship Hull — output

Game Asset - Female Android Repairing Spaceship Hull

カーブミラーGPT Image 2
Create a cinematic vertical sci-fi scene inside a damaged spaceship maintenance corridor: a kneeling female android technician with {argument name="hair color" default="long flowing white hair"} and a glossy white segmented cybernetic body repairs a scorched wall panel. Her face is intentionally featureless and obscured by a smooth neutral gray rectangular visor/plate, while her exposed mechanical arms and hands hold repair tools against torn wiring. Show exactly two bright orange welding-spark bursts on the right wall, with glowing embers, blackened cables, melted circuitry, wet reflective metal flooring, loose hoses trailing across the floor, and cold blue-white strip lights receding down the corridor. Add a translucent blue holographic diagnostic screen above her right shoulder with the visible text: "HULL REPAIR SYSTEM", "STATUS: ACTIVE", "REPAIR PROGRESS", "63%", and exactly five checklist items: "STRUCTURAL INTEGRITY", "MICRO-FRACTURE SEAL", "CONDUIT REPAIR", "POWER ROUTING", "SYSTEMS CHECK". Use high-detail hard-surface design, realistic metallic textures, volumetric lighting, blue and orange contrast, shallow depth of field, dramatic backlighting, sparks frozen in motion, ultra-detailed futuristic concept art, no watermark, no extra characters.
Infographic / Edu Visual - Japanese Husky Sketchbook Profile — output

Infographic / Edu Visual - Japanese Husky Sketchbook Profile

はすきー|Midjourneyマニア🐺GPT Image 2
Goal: Create a vertical personal sketchbook profile page for a cute Siberian husky named {argument name="character name" default="はすきー"}, in a warm hand-drawn Japanese scrapbook style, like a watercolor pet diary made with GPT Image 2.

Canvas: Portrait 4:5 page on off-white textured paper, filled edge to edge with blue ink doodles, washi tape, paw prints, hearts, stars, dotted travel paths, paper scraps, checklists, and handwritten Japanese notes. Main palette is deep cobalt blue, navy ink, soft gray, cream paper, with tiny red hearts and pale yellow tape accents.

Layout: Put a huge title at the top center reading 「はすきー」 in bold blue brush lettering with an underline and a small heart. At top left, a taped label reads 「ぼくのプロフィール」. The center is dominated by a large watercolor husky head/upper-body portrait with fluffy pointed ears and blue splatter paint behind it, but cover the face area with one large flat bluish-gray square mask. Bottom left shows a full-body standing husky, tail curled, blue-gray fur, with a second small bluish-gray square mask over its face. Right middle shows a small seated chibi husky with a gold crown doodle, but cover its face with a third small bluish-gray square mask. Bottom right contains a cozy window scene of the husky sitting indoors and looking outside at snowy mountains.

Text content and counted elements: Include exactly 5 profile rows under the top-left profile label, each with a paw bullet: 「なまえ:はすきー」, 「犬種:シベリアン・ハスキー」, 「誕生日:???(たぶん春)」, 「性別:♂」, and 「性格:好きじいっぱい! あそぶの大好き! ちょっといたずらっ子♡ やさしくて、家族がだいすき!」. Include exactly 5 checked items in a left memo box titled 「飼い主メモ」: 「お水をわすれない」, 「いっぱい褒める」, 「たくさんあそぶ」, 「ブラッシングするよ」, and 「実はこわいけど 暑さは苦手かも?」. Include exactly 6 bullet traits on the upper right titled 「ぼくのとくちょう」: 「好奇心いっぱい」, 「あそぶの大好き」, 「ちょっといたずらっ子」, 「とっても忠犬!」, 「冒険だいすき」, and 「やさしい目」, with small matching doodle icons such as magnifying glass, ball, teddy face, heart, mountains, and eye. Include a cloud note near the top right reading 「青い目がチャームポイント」 with an eye icon. Include a speech bubble near the chibi dog reading 「今日もマイペース♪」 and tiny text 「えへへっ」 with hearts.

Additional paper notes: Add a ribbon banner below the central portrait reading 「ぼく {argument name="character name" default="はすきー"}!」 and below it 「よろしくね!」. Add a center-lower note titled 「すきなことメモ」 with exactly 5 heart-bullet items: 「おさんぽ」, 「ひっぱりっこ」, 「雪の上をはしること」, 「お水であそぶこと」, and 「家族といっしょにいること」. Add a bottom-left taped note titled 「家族の宝物」 with a loving thank-you message. Add a bottom-right clipped note titled 「きょうのはすきーメモ」 with exactly 3 time-of-day lines: 「朝:いっぱい食べた!」, 「昼:おさんぽたのしかった!」, and 「夜:ぐっすりねんね…Zzz」. Add a small note beside the window scene saying 「窓の外をながめるのがすきなんだ〜♡」. Label the window scene 「いつもの風景」.

Decorations: Include snowy mountain doodles at lower left, pine trees, a compass, a bone, a blue ball, blue paw stamps, a circular postmark-style stamp reading GOOD BOY with a paw, a mug labeled GOOD DAY, paper clips, check marks, washi tape strips, and scattered ink splashes. Use exactly 3 gray mask rectangles total, all opaque and featureless. Keep the whole image handmade, slightly messy, charming, and information-rich, with readable handwritten Japanese text and no photorealism.
Infographic / Edu Visual - Vintage Rosemary Chronicle Grid — output

Infographic / Edu Visual - Vintage Rosemary Chronicle Grid

WenvisAI⚡️GPT Image 2
Goal: Create a vintage botanical photo-chronicle contact sheet titled {argument name="headline text" default="The Slow Garden: A Rosemary Chronicle"}, documenting the life cycle of {argument name="plant name" default="rosemary"} from dry pot to harvest.

Canvas: Square 1:1 poster on warm aged parchment paper, subtle stains and speckles, soft cream background, thin dark-green panel borders, handwritten field-journal typography. Use a large decorative serif/calligraphy headline centered at the top.

Layout: Arrange exactly 12 photographic panels in a clean 4-column by 3-row grid. Each panel has a handwritten green stage label above it, a short uppercase camera-direction caption below it, and an italic poetic quote beneath the caption. Add small downward arrow marks along the far left and far right margins to suggest time passing.

Panel details, count exactly 12:
1. Stage label: "Dormancy". Image: a terracotta pot on a windowsill filled with cracked dry soil, no plant visible. Caption: "WIDE · OVERHEAD · FIXED CAMERA". Quote: "Winter's silence, the seed waits."
2. Stage label: "Dormancy". Image: macro view of a terracotta pot rim and dark soil with a single water droplet running down the clay side. Caption: "MACRO · SLOW MOTION DROP". Quote: "First drop, awakening memory."
3. Stage label: "Germination". Image: low-angle close photo of a pale tiny shoot emerging from dark soil. Caption: "LOW ANGLE · TIME-LAPSE FEEL". Quote: "Root first, shoot later."
4. Stage label: "Germination". Image: close-up of a small cotyledon seedling with two green leaves rising from soil, soft bokeh background. Caption: "CLOSE-UP · COTYLEDON FOCUS". Quote: "Breaking ground, it took seven days."
5. Stage label: "Growth". Image: macro of young rosemary leaves with rim light, dew-like texture on needle edges. Caption: "MACRO · LEAF EDGE RIM LIGHT". Quote: "Every leaf, a map of aroma."
6. Stage label: "Growth". Image: close-up of a human fingertip gently touching a tender rosemary sprig. Caption: "CLOSE-UP · FINGERTIP CONTACT". Quote: "A gentle touch, handful of fragrance."
7. Stage label: "Growth". Image: overhead photo of a woody rosemary branch with green branching needles. Caption: "OVERHEAD · BRANCHING STRUCTURE". Quote: "One year bone, two years flesh."
8. Stage label: "Flourishing". Image: medium shot of a rosemary plant in a terracotta pot with small purple-blue flowers and a bee approaching or hovering near the blooms. Caption: "MEDIUM SHOT · BEE ENTRANCE". Quote: "When flowers open, the whole garden arrives."
9. Stage label: "Flourishing". Image: wide shot of rosemary on a rustic wooden surface in golden sunlight, strong leaf shadows across the boards. Caption: "WIDE · LIGHT & SHADOW CONTRAST". Quote: "Dialogue of light and leaf, repeated daily."
10. Stage label: "Flourishing". Image: close-up of pruning shears cutting a rosemary stem while a hand holds the sprig. Caption: "CLOSE-UP · SCISSORS & STEM". Quote: "Pruning is not an end, it's another beginning."
11. Stage label: "Harvesting". Image: medium shot of a bundled rosemary bunch hanging upside down in a rustic shed or wooden room to dry. Caption: "MEDIUM SHOT · HANGING DRY". Quote: "Drying time, leave it to the wind."
12. Stage label: "Harvesting". Image: wide still-life composition with dried rosemary spilling from a small linen drawstring pouch beside a terracotta pot. Caption: "WIDE · STILL LIFE COMPOSITION". Quote: "Aroma sealed, awaiting the next awakening."

Visual style: Photorealistic macro garden photography mixed with hand-crafted editorial scrapbook design, shallow depth of field, soft natural window light, earthy terracotta browns, rosemary greens, muted purple blossoms, warm sunlight, gentle film grain, slightly imperfect handwritten annotations.

Constraints: Keep the grid aligned and readable, use exactly 12 panels and no extra panels, avoid modern UI elements, avoid watermarks, avoid logos, preserve the vintage botanical journal feeling. Make all visible text legible and in English.
Social Media Post - Pastel Buzz Cut Girls Portrait — output

Social Media Post - Pastel Buzz Cut Girls Portrait

たけみGPT Image 2
Create a soft pastel anime-style illustration of three young women sitting close together in a dreamy pink bedroom, framed as a waist-up group portrait in a 3:2 horizontal canvas. The scene has warm morning backlight from a window on the left, sheer curtains, a vase with pink tulips on the windowsill, a bed or sofa with lavender bedding, and a softly blurred wall with small cute framed pictures and posters on the right. Show exactly three girls, all with very short hair variations: the left girl is completely bald with a smooth shaved head, the center girl has an ultra-short brown buzz cut with visible stubble texture, and the right girl has a short dark pixie/buzz cut with spiky texture. Their faces are covered by flat pale pink rectangular censor blocks, one rectangle per girl, matching the soft color palette. Outfit details: the left girl wears a pale pink ribbed cardigan over a white lace camisole with small pink bows, a muted plaid skirt, and dangling flower earrings while touching her ear; the center girl wears a cream cable-knit cardigan with buttons and tiny bows over a white frilled blouse tied with a pale pink ribbon; the right girl wears a white blouse with a frilled collar and black ribbon bow under a pink plaid pinafore dress, with a small dangling earring. Use delicate linework, soft watercolor shading, luminous highlights, blush-pink atmosphere, cozy feminine fashion, high-detail fabric textures, and gentle depth of field. Keep the mood intimate, cute, and serene. Customize the three hair styles as {argument name="hair styles" default="left bald, center ultra-short brown buzz cut, right short dark pixie buzz cut"}, the setting as {argument name="bedroom setting" default="soft pink bedroom with tulips, sheer curtains, lavender bedding, and cute wall pictures"}, the outfit palette as {argument name="outfit palette" default="pale pink, cream, white, lavender, and muted plaid"}, the face covering as {argument name="face covering" default="flat pale pink rectangular censor blocks over each face"}, and the lighting as {argument name="lighting" default="warm hazy morning backlight from the left"}.
Profile / Avatar - Tropical Wolf Boy RPG Character Sheet — output

Profile / Avatar - Tropical Wolf Boy RPG Character Sheet

WOLFWOLF2025GPT Image 2
Goal: Create a vertical pixel-art fantasy RPG character sheet for {argument name="character name" default="ウルフくん"}, a slim dark-tanned wolf-eared traveling boy in a tropical southern-island setting, with Japanese game UI panels and a bright 16-bit/32-bit JRPG aesthetic.

Canvas: Tall 9:16 mobile poster, approximately 675×1200. Use crisp high-detail pixel art with glowing UI borders, saturated tropical colors, warm sunset light, and a beach-resort background with palm trees, blue sky, ocean, wooden deck, fruit, and a blue drink on a table.

Main character: Center-right full-body anime boy, slender and lightly toned, not muscular, tan skin, long messy {argument name="hair color" default="dark navy blue"} hair, large gray-brown wolf ears, golden eyes, wolf tail, playful confident pose. His face is mostly covered by a centered opaque dark blurred square censor block. Outfit is a blue-and-white open tropical dancer/traveler costume with a bare torso, gold bangles, layered necklaces, blue gemstone pendant, waist chains, sash, short skirt-like wraps, shell ornaments, ankle wraps, and small white rabbit charms. One hand reaches toward the viewer; the other holds a round gold-framed tambourine with a white rabbit silhouette.

Layout: Top-left status card, four stacked portrait cards down the left side, large main character occupying the right and center, two bottom information panels, and two small mascot/chibi figures along the bottom.

Top-left status panel text: Use a translucent navy glass RPG window with icy glowing corners. Include exactly these lines in Japanese: 「【南国ゆるふわ旅芸人】」, large name 「{argument name="character name" default="ウルフくん"}」, 「ジョブ:旅芸人」, 「Lv:27」, 「HP:248/248」 with a green HP bar, and 「MP:25/25」 with a blue MP bar.

Left portrait column: Include exactly 4 square expression portraits of the same wolf-eared boy, each with a glowing blue frame: 1) calm golden-eyed neutral smile, 2) eyes closed laughing joyfully, 3) half-lidded slightly smug expression, 4) gentle confident smile.

Bottom-left belongings panel: Title it 「❖ そうび・もちもの ❖」. Include exactly 5 item rows with small pixel icons and Japanese labels/descriptions: 1) 「うさタムリン」, a gold tambourine with rabbit silhouette; 2) 「うさみみペンダント」, a white rabbit-head pendant; 3) 「うさぴょんブレスレット」, a bracelet with bunny charm and sparkles; 4) 「うさぎポシェット」, a beige rabbit-shaped pouch; 5) 「ミニオトモ:モフうさ」, a fluffy white rabbit companion icon.

Bottom-right skills panel: Title it 「❖ とくぎ(スキル)❖」. Include exactly 4 skill rows with icons and Japanese labels/descriptions: 1) musical note icon, 「ゆるふわビート」; 2) bunny icon, 「うさぴょんダンス」; 3) yellow sparkle icon, 「南国スマイル」; 4) ZZZ sleep icon, 「サマー・ゴロ〜ン」.

Bottom mascots: Include exactly 2 small figures at the bottom center/right: 1) a chibi version of the wolf boy holding the tambourine, with wolf ears and tail; 2) a cute fluffy white rabbit companion wearing a blue flower collar and small gold bell.

Visual style and constraints: Japanese fantasy gacha-game character profile, pixel-art sprite detail, luminous icy-blue UI frames, tropical resort lighting, small pink flower petals drifting, no extra characters, no extra panels, no modern UI outside the RPG windows. Keep the boy slim and youthful; avoid a bodybuilder or bulky muscular build.
Product Marketing - Japanese MNP Campaign Banner — output

Product Marketing - Japanese MNP Campaign Banner

たまコイン@発展途上国底辺FIRE民GPT Image 2
Goal: Create a bright square Japanese social media campaign banner advertising an MNP switching promotion for {argument name="campaign type" default="MNP limited campaign"}.

Canvas: 1:1 square banner, 768×768 style, high-resolution, clean commercial ad design. Use a sky-blue radial burst background with pale rays from the center, dotted halftone texture near the edges, small sparkle stars, and about 28 colorful confetti pieces in pink, yellow, and blue around the border.

Layout: Arrange the design in 5 stacked zones. Zone 1 is a dark royal-blue ribbon at the top with rounded rectangular center and pointed ribbon tails. Zone 2 is a large headline area with bold Japanese text. Zone 3 is the main offer amount, oversized and centered. Zone 4 is a white rounded information card with icons. Zone 5 is a large blue rounded call-to-action button at the bottom.

Text content: Top ribbon text: {argument name="top ribbon text" default="MNP限定キャンペーン"}. Main headline: {argument name="headline text" default="乗り換えで"}. Main offer text must read {argument name="offer amount text" default="最大2万円還元"}, with the number and currency in bright yellow and the surrounding characters in deep blue. Information card text: {argument name="detail text" default="対象プラン申込で ポイント還元"}. CTA button text: "今すぐチェック". Small disclaimer centered below the button: "※表示はダミーです".

Counted visual elements: Include exactly 1 top ribbon banner, 1 main headline, 1 oversized offer amount block, 1 white rounded information card, 1 CTA button, 1 smartphone icon on the lower left, 1 yellow circular gift icon near the center of the card, 1 group of gold coins on the right of the card, 1 white play-arrow circle inside the CTA button, and 2 yellow attention-burst marks flanking the CTA button. In the coin group, show exactly 3 stacked coin columns plus 1 large front coin marked with a capital "P".

Visual style: Bold Japanese advertising typography, thick white outlines, blue drop shadows, glossy gradients, high contrast, celebratory telecom-promotion look. Use deep navy blue, royal blue, cyan, white, and vivid yellow as the primary palette. The main "2万円" should dominate the composition, with heavy outline layering: yellow fill, blue stroke, thin white outer glow, and soft shadow.

Subject details: The smartphone should be tilted slightly left, with a cyan screen and a simple white two-person user icon. The gift icon should be a dark blue present symbol inside a yellow circle with tiny yellow sparkle marks above it. The CTA button should be a glossy rounded rectangle with a white border and soft shadow, containing a white circular play icon on the right.

Constraints: Keep all text crisp and readable, centered, and in Japanese. Do not add logos, brand names, watermarks, QR codes, or extra copy. Maintain a polished Japanese mobile-carrier campaign banner aesthetic.
Infographic / Edu Visual - Anime Cheerleader Pose Sheet — output

Infographic / Edu Visual - Anime Cheerleader Pose Sheet

まるるん@Nikkeアカウントに転身GPT Image 2
Goal: Create a bright anime cheerleader pose reference sheet for a sports-stadium performance, showing {argument name="character name" default="a silver-haired anime cheerleader"} demonstrating exactly 15 cheer motions in separate numbered panels.

Canvas: Wide 16:9 contact-sheet layout, 1280x720 style, divided into a clean 5-column by 3-row grid. Each panel has a thin white border, a blue circular number badge in the top-left, a white slanted title banner across the top with bold blue uppercase English text, and a dark translucent caption bar along the bottom with Japanese explanatory text.

Setting and visual style: Sunny outdoor football stadium with green field, running track, curved grandstands, vivid blue sky, fluffy clouds, energetic idol-cheer atmosphere. High-quality anime illustration, glossy promotional look, dynamic wide-angle camera, bright rim light, saturated blue-and-white palette, crisp details, motion in hair and skirt. The character wears a blue-and-white cheerleader outfit: cropped sleeveless top with star motif, pleated mini skirt, blue ribbons, thigh garter accents, ankle shoes, and large blue-and-white pom-poms. Long flowing {argument name="hair color" default="silver-white"} twin-tail hair with blue bows, cute expressive idol style.

Layout and exact panel list: Include exactly 15 panels, ordered left to right, top to bottom:
1. HIGH V — both arms raised high in a V shape with pom-poms.
2. LOW V — both arms extended diagonally downward in a low V stance.
3. T MOTION — arms stretched straight sideways at shoulder height.
4. TOUCHDOWN — one arm raised high and the other extended diagonally downward.
5. HIGH TOUCH — one hand reaches straight upward as if touching high, one leg lifted playfully.
6. LOW TOUCH — leaning forward with one arm reaching low toward the ground.
7. HALF TIME — hands placed on hips, ready stance.
8. CLAP — pom-poms brought together in front, clapping rhythmically.
9. PUNCH — one arm thrust powerfully upward with pom-pom.
10. SPIN — spinning in place, skirt and hair flaring outward.
11. KICK — high leg kick with energetic balance.
12. LUNGE — one knee bent deeply in a strong lunge pose.
13. JUMP — jumping upward with pom-pom raised and legs tucked.
14. BOW — polite forward bow with pom-poms gathered in front.
15. FINISH POSE — final celebratory pose with one arm raised and smile.

Text content: Use the English motion titles exactly as listed. Add Japanese captions similar to a cheer instruction guide under each panel, including these meanings: basic high V position, calm low V stance, synchronized shoulder-height team motion, one hand high and one diagonal, touch high to appeal height, low touch with sparkle, hands on waist for preparation, clap pom-poms to make rhythm, punch upward with strength, spin for華やか movement, dynamic high kick, strong lunge, jump to express energy, graceful bow of thanks, and smiling finish pose. Main title is not needed.

Constraints: Keep the grid perfectly readable and evenly spaced. Use exactly 15 numbered panels and no extra panels. Maintain consistent character design, outfit, colors, and stadium background across all panels. Make the typography bold and legible. Avoid logos, watermarks, and unrelated objects.
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 ↗