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.

探索提示词

10,043 条提示词

Product Marketing - Anime Ketchup Omurice Art — output

Product Marketing - Anime Ketchup Omurice Art

癒音ちー✨ゆおんちー✨癒やし声ASMRとAIGPT Image 2
Create a realistic, appetizing food photograph of Japanese omurice served on a large pale gray ceramic plate. The main subject is a glossy golden omelet draped over reddish ketchup fried rice, with the rice visibly peeking out along the bottom edge. On top of the omelet, draw a cute anime-style girl face using red ketchup lines: bobbed hair framing the face, short bangs, two large eyes, a small smiling mouth, and simple cheek/jaw lines, as if it is omurice art of {argument name="character name" default="a cute anime girl"}. Place a side salad on the right side of the plate with exactly 3 visible components: leafy green lettuce, dark red/purple leaves, and 1 cherry tomato, plus a light creamy dressing drizzle. Set the plate on a warm wooden café table near a softly lit window. Include exactly 2 background glass items: 1 small glass vase with tiny white flowers on the left and 1 clear water glass on the right, both softly blurred. Use natural morning sunlight, shallow depth of field, warm cozy tones, high-detail food texture, realistic reflections on the omelet, and a horizontal 16:9 composition. No text, no watermark, no hands, no utensils.
Infographic / Edu Visual - Japanese Corridor Vocabulary Poster — output

Infographic / Edu Visual - Japanese Corridor Vocabulary Poster

ぐふとくくGPT Image 2
Goal: Create a dense Japanese reference poster/infographic titled {argument name="headline text" default="廊下・階段・通路演出の用語表"}, a vocabulary chart for illustrating hallways, stairs, and passageway scenes. Make it look like a hand-drawn scrapbook study sheet for AI illustration prompt words, with many miniature scene examples featuring the same mysterious gothic schoolgirl guide.

Canvas: Vertical 4:5 poster, warm ivory aged paper background with visible paper grain, thin ruled grid lines, taped corners, tiny stars, moons, flowers, stationery doodles, ink bottle, envelope, ribbon, and washi tape decorations around the border. Overall palette is sepia beige, muted navy, smoky gray, faded blue, and black ink. Use an analog watercolor, pencil, and ink style with slightly messy handwritten Japanese typography.

Main character: A recurring {argument name="character description" default="gloomy Jitome girl with long messy black hair, dark school uniform, pale skin, sleepy eyes, and a melancholic expression"}. She appears once large at the upper left as the guide and repeatedly inside the example thumbnails. The large portrait has a small label reading 「ジト目女子が案内するよ」. Keep the character’s face visible and consistent where she appears, with wet-looking hair strands and gothic, moody styling.

Header layout: At the top center place the large title 「廊下・階段・通路演出の用語表」. Beneath it add a subtitle line like 「学校廊下・病院廊下・非常階段・地下通路・長い廊下・消失点を整理した、AIイラスト発想補助のための通路演出ワード一覧。」 On the upper right add a decorative note card with a crescent moon and the text 「通路は物語の流れと心の流れをつくるよ。」

Central layout: Use exactly 24 numbered rectangular cards in a 4-column by 6-row grid. Each card must have a colored number tab, a Japanese category title, a few tiny handwritten keyword lines, and a small watercolor scene thumbnail. The thumbnails should show corridors, stairs, passageways, windows, vanishing points, reflections, silhouettes, or the gothic girl in different positions. Count and include these 24 cards exactly:
1. 「学校廊下」 — school hallway with lockers, bulletin boards, afternoon light.
2. 「病院廊下」 — quiet hospital corridor with white walls, curtains, clean unease.
3. 「非常階段」 — emergency stairwell, metal rails, cold light, escape-route tension.
4. 「商業施設通路」 — shopping mall passage with people flow and urban brightness.
5. 「地下通路」 — low ceiling, artificial lighting, tiled walls, damp heaviness.
6. 「長い廊下」 — deep vanishing point, repeating windows and doors.
7. 「手すり」 — railing lines guiding the eye along stairs or corridor.
8. 「消失点」 — one-point perspective corridor converging into distance.
9. 「階段」 — up/down movement, diagonal composition, a person midway.
10. 「踊り場」 — stair landing, pause between floors, quiet turning point.
11. 「外階段」 — outdoor stairs with fence, sky, wind, exposed metal.
12. 「連絡通路」 — connecting passage between buildings, movement and transition.
13. 「渡り廊下」 — covered school walkway with view outside and nostalgia.
14. 「狭い通路」 — narrow passage, close walls, body brushing through.
15. 「薄暗い通路」 — dark corridor, weak light, humid uneasy atmosphere.
16. 「明るい廊下」 — open bright hallway, clean floor, hopeful transparent light.
17. 「窓のある廊下」 — windows, curtains, light and shadow bands.
18. 「曲がり角」 — corner turn, unseen continuation, narrative suspense.
19. 「通路の奥」 — far end of corridor, small figure, depth and destination.
20. 「すれ違い」 — two characters passing each other without eye contact.
21. 「立ち止まる」 — character stopped in passage, back view, quiet hesitation.
22. 「振り返る」 — character looking back over shoulder, hair and skirt movement.
23. 「追いかける背中」 — chasing or following someone’s back in a passage.
24. 「通路の余韻」 — empty corridor after people leave, lingering atmosphere.

Bottom section: Add a handwritten notes area with star bullet points explaining that this is a word list for school corridors, hospitals, stairs, and passage演出, useful for combining with keywords like long hallway, staircase, railing, vanishing point, curve, light, shadow, silhouettes, and passing-by scenes. Keep the text dense but legible, like a Japanese prompt-word cheat sheet.

Visual style: Delicate anime watercolor illustration, sketchbook infographic, hand-lettered Japanese, thin ink outlines, soft blue-gray shadows, warm parchment paper, collage tape, decorative celestial motifs. The poster should feel information-dense, cozy, nostalgic, slightly gothic, and handmade.

Constraints: Use exactly 24 numbered cards in the grid; keep the large title readable; avoid modern flat vector style; no photorealism; no English labels except decorative tiny marks if needed; no watermark or logo.
Comic / Storyboard - Punk Guitarist Comic Cover — output

Comic / Storyboard - Punk Guitarist Comic Cover

ToudaijiGPT Image 2
Goal: Create a vertical American comic book cover in a gritty punk-rock manga/anime style for a fictional issue titled {argument name="comic title" default="HEARTSTRIKE"}.

Canvas: Portrait comic cover, 2:3 aspect ratio, full-bleed illustration with a black distressed print border, halftone texture, ink speckles, worn paper scratches, high-contrast magenta, black, white, and purple lighting.

Main subject: Center a young female punk rock guitarist idol in dynamic low-angle perspective, filling most of the cover. She has blonde twin-tail hair, pointed elf ears, a red plaid beret with a small heart pin, black ribbon hair ties, gothic punk makeup vibe, a black corset top with frills, fishnet/mesh sleeves, studded bracelets, choker, red plaid skirt, belts, chains, lace trim, and a heart-shaped garter detail. Her face is deliberately covered by a plain skin-tone rectangular censor block with no facial features. She is aggressively playing a white Stratocaster-style electric guitar angled diagonally from lower left to mid-right, with detailed strings, pickups, knobs, worn scratches, and a visible headstock signature.

Background: A chaotic concert stage packed with silhouetted fans raising rock hand signs, purple lightning bolts, starburst stage lights, smoke, electric energy, and black speaker amps on the right. The mood is loud, rebellious, dangerous, and glamorous.

Cover typography and layout: Use exaggerated distressed comic lettering with jagged edges, pink shadows, white fills, black outlines, and ink splatter. Include exactly 8 visible text blocks: 1) top-left publisher box: "REBEL INK COMICS" with a pink skull-and-bow emblem; 2) price/issue box: "#1", "$4.99", "US", "APR", "2025"; 3) top tagline across the cover: "SHE PLAYS LOUD. SHE HITS HARD. SHE NEVER MISSES." with the words "LOUD", "HARD", and "NEVER" in hot pink; 4) huge main masthead: "{argument name="comic title" default="HEARTSTRIKE"}"; 5) left promo stack: "1ST SMASH ISSUE!"; 6) left slogan: "LIVE. LOVE. DESTROY." with "DESTROY." in hot pink; 7) right tilted caption: "FEATURING: THE WORLD'S MOST DANGEROUS SOUND!" with "DANGEROUS" in hot pink; 8) bottom-right hot pink tour stamp: "{argument name="tour stamp text" default="BLACKOUT TOUR '25 BEGINS!"}". Add a small vertical barcode box at bottom left with "DIRECT SALES" and barcode numbers.

Visual style: Fusion of American punk comic cover, Japanese anime character rendering, heavy cel shading, detailed line art, distressed screenprint texture, neon magenta rim light, purple concert glow, dramatic foreshortening, sharp inked outlines, glossy highlights on guitar hardware, chaotic composition.

Constraints: Keep the cover busy but readable, preserve the exact count of 8 major text blocks, do not add extra title banners or logos beyond the listed elements, keep the face fully hidden by the plain rectangle, and make it look like a collectible first-issue comic cover.
Product Marketing - Schoolgirl Turned Rural Farmer Classroom Scene — output

Product Marketing - Schoolgirl Turned Rural Farmer Classroom Scene

JpgGPT Image 2
Using REFERENCE_0 as the base for the blonde school-uniform girl, transform it into a realistic cinematic scene from a Japanese classroom. Show the girl now standing indoors, facing a male classmate, with an embarrassed shocked expression and open mouth. Keep her blazer, cardigan, bow tie, plaid skirt, blonde curled hair, and overall fashion-leader schoolgirl identity recognizable, but add rural farmer styling over the uniform: a white floral headscarf tied around her hair, loose dark floral work pants worn under the skirt, and muddy rubber boots. Add exactly 1 other person: a Japanese male student seen mostly from behind/side in a navy school blazer and plaid trousers, standing on the left and facing her. Place them in an old classroom with wooden floors, rows of desks and chairs, a green chalkboard, classroom posters, tall windows, and warm late-afternoon sunlight. Use a vertical full-body composition, photorealistic live-action look, natural lens depth, dramatic novel-scene atmosphere, no captions or extra text.
Product Marketing - Surreal Floral Couture Portrait — output

Product Marketing - Surreal Floral Couture Portrait

NIKKOGPT Image 2
Create a vertical high-fashion fantasy portrait of {argument name="character name" default="an anonymous woman"} from the waist up, posed in three-quarter profile facing left, with her face deliberately covered by a centered opaque peach rectangular block for anonymity. She has voluminous flowing {argument name="hair color" default="strawberry-blonde and copper-red"} hair whipped upward and outward as if caught in wind, merging with enormous painterly floral and fabric forms. Surround her head and body with exactly 6 prominent flower elements: 2 large red hibiscus-like blossoms above and left of the head, 1 large teal-blue flower on the right side, 1 pink daisy near the cheek area, 1 blue flower at the waist, and 1 small pale flower near the bodice. Dress her in an ornate strapless couture gown covered in red, white, blue, and orange petals, sequins, lace, and splattered paint textures, with a jeweled multicolor necklace at the neckline. Add dramatic translucent ribbons and paint-like splashes in vivid crimson, vermilion, coral, orange, teal, cobalt, magenta, and white swirling around her, creating an explosive floral headdress and abstract background. Use a clean white studio backdrop, bright high-key lighting, shallow depth of field, glossy editorial photography realism mixed with surreal botanical couture, extremely detailed textures, dynamic motion, saturated colors, and a vertical 9:16 composition. Keep the face block plain and flat with no facial features or text, avoid logos or watermarks.
Infographic / Edu Visual - WWDC 2026 Highlights Infographic — output

Infographic / Edu Visual - WWDC 2026 Highlights Infographic

다자이너GPT Image 2
Goal: Create a polished Apple-style Korean infographic slide summarizing {argument name="headline text" default="WWDC 2026 HIGHLIGHTS"} from a designer perspective.

Canvas: 16:9 horizontal presentation graphic, 1152×768 feel, white-to-pale-blue gradient background with soft translucent wave ribbons in the top-right corner. Use Apple-inspired glassmorphism, rounded cards, subtle shadows, blue/purple gradients, clean SF Pro-like typography, and a small multicolor Apple logo at the top-left.

Layout: Large centered headline at the top, with “WWDC 2026” in dark navy and “HIGHLIGHTS” in blue-to-purple gradient. Under it, arrange exactly 6 rounded white cards in a 3-column by 2-row grid, each card numbered with a glossy blue-purple circular badge from 1 to 6.

Card 1: Title {argument name="liquid glass title" default="리퀴드 글래스 정교화"}. Show a translucent frosted-glass control panel with exactly 3 horizontal sliders: a toggle slider, a brightness slider with sun icon, and a volume slider with speaker icon. To the right, show a depth-enhancement slider and a stack of translucent glass sheets. Include exactly 3 Korean bullet points: “정밀한 투명도 조절로 더욱 몰입감 있는 경험”, “동적 조명과 섬세한 블러로 깊이감 향상”, “모든 플랫폼에 일관된 리퀴드 글래스 경험 제공”.

Card 2: Title {argument name="design principles title" default="디자인 원칙"}. Subtitle “AI 시대를 위한 7가지 핵심 원칙”. Show exactly 7 circular principle icons in a neat grid, labeled in English: Purpose, Agency, Responsibility, Familiarity, Flexibility, Simplicity, Craft, Delight. Even though 8 label positions are visible, emphasize the subtitle says 7 principles while the visual grid contains these 8 labeled icon circles. Bottom pill caption: “AI 윤리와 책임을 최우선으로 하는 디자인”.

Card 3: Title {argument name="ios title" default="iOS 27"}. Show a realistic iPhone mockup with dynamic island, blue-purple Siri orb wallpaper, and Korean text on screen “Siri가 듣고 있어요...”. To the right, include exactly 3 vertical feature rows with icons and Korean headings: “정리” with smaller text “알림과 앱을 자동으로 정리”, “확장” with smaller text “필요에 맞게 콘텐츠 확장”, and “재구성” with smaller text “내용을 이해하고 재구성하여 제안”. Bottom rounded pill: “더 스마트해진 Siri와 개인화된 경험”.

Card 4: Title {argument name="safari home title" default="사파리 & 홈"}. Show a Safari-like AI tab group module labeled “AI 탭 그룹” with subtitle “AI가 관련 탭을 자동으로 그룹화”. Include exactly 4 visible tab chips plus one plus button: “여행 계획 7”, “리서치 5”, “쇼핑 4”, and a final add button “+”. Below, show a Home security clipping section titled “홈 보안 클립” with subtitle “카메라가 감지한 주요 순간을 자동으로 요약”. Include exactly 4 video thumbnails with time labels: 9:12 AM delivery person, 1:47 PM car, 4:32 PM dog, 8:11 PM living room. Bottom pill: “AI가 더 안전하고 편리한 경험을 제공합니다”.

Card 5: Title {argument name="macos title" default="macOS 골든 게이트"}. Show an iMac display with Golden Gate Bridge sunset wallpaper and a glowing Apple Silicon chip badge. Under it, include exactly 3 benefit icons with Korean headings and short subtext: “성능 향상”, “배터리 효율”, “강력한 보안”. Bottom pill: “Apple Silicon의 힘으로 더 강력해진 Mac 경험”.

Card 6: Title “visionOS”. Create a futuristic spatial-computing scene: a glowing central blue-purple orb labeled “Siri Pro” hovering over a faint perspective grid. Around it place exactly 6 floating translucent app tiles/icons: image/photo icon, play icon, chart icon, person icon, profile silhouette icon, and one small glass panel. Bottom pill: “3D 공간에서 더욱 자연스럽고 지능적인 상호작용”.

Visual style: High-end Apple keynote recap aesthetic, crisp vector UI mixed with soft 3D glass elements, blue/purple glow accents, consistent spacing, rounded 24px cards, light shadows, premium minimalism. Keep all Korean text legible and correctly spelled. Avoid extra logos, watermarks, signatures, or additional cards.
Profile / Avatar - Cinematic 8K Photo Restoration — output

Profile / Avatar - Cinematic 8K Photo Restoration

carpeGPT Image 2
Using the provided reference image, enhance and restore the same photo into an ultra-premium cinematic 8K-quality image. Preserve 100% of the original identity, pose, composition, framing, perspective, and all objects exactly as they are. Recover realistic microdetails and sharpness throughout: crisp eyes, detailed nose texture, individual fur strands, clear flower petals and stems, defined grass, house, trees, vehicle, and background elements. Make it photorealistic with natural sunlight, high contrast, studio-quality clarity, accurate colors, no pixelation, no blur, no artifacts, and no invented changes.
Social Media Post - Ethereal Botanical Portrait — output

Social Media Post - Ethereal Botanical Portrait

newone@見習AI画像生成士 🅜🅐🅘GPT Image 2
Create a dreamy fine-art fashion portrait of {argument name="character name" default="an anonymous young woman"} in a misty botanical setting, vertical 3:4 composition. The subject is centered from the waist up with bare shoulders and a dramatic black tulle dress or corset at the bottom of the frame; her face is intentionally covered by a plain centered square censor block in warm taupe-brown. She has {argument name="hair color" default="dark brown"} loose wavy hair glowing in strong golden backlight. Pose her with exactly two arms visible: the left arm curves over the top of her head, wrist relaxed, fingers long and elegant pointing left; the right arm bends upward across her chest with the hand near her neck, fingers delicately separated. Emphasize anatomically correct hands with exactly five fingers on each hand, natural knuckles, no fused or extra fingers. Add intricate black botanical line-art tattoos or overlays across both arms, shoulders, collarbone, and neck: fine vines, leaves, and small blossoms wrapping over the skin. Surround her with exactly six prominent translucent black ink flowers on curling vines: one large flower at lower left, one large flower at mid-left, one flower near upper right, one large flower at mid-right, one partial flower at bottom left edge, and one dark flower cluster near bottom center; include additional thin tendrils and tiny buds weaving through the background. Use a soft beige-gray foggy background, shallow depth of field, ethereal sun flare behind the hair, delicate semi-transparent ink illustration mixed with photorealistic skin, muted monochrome palette with warm highlights, high detail, elegant gothic botanical mood. No readable text, no watermark, no jewelry, no extra limbs, no distorted hands.
Social Media Post - Times Square Movie Billboard Scene — output

Social Media Post - Times Square Movie Billboard Scene

Cherry 2.OGPT Image 2
Create a cinematic photorealistic night scene in Times Square after rain, viewed from street level with glossy wet pavement reflecting neon lights, crowds on sidewalks, yellow taxis and dark cars streaking through the foreground with motion blur, and tall skyscrapers packed with glowing advertisements. The composition is dominated by exactly two huge side-by-side billboards above a red stair plaza: the left billboard is a dramatic movie poster for {argument name="movie title" default="THE CHASE"}, showing {argument name="character name" default="KAIRO"} as a stylish male action hero in a black overcoat and suit standing on a rooftop at sunset with a warm orange city skyline behind him, coat blowing in the wind, hands in pockets, with the hero’s face intentionally covered by a plain soft-edged rectangular blur; include large white title text at the bottom, smaller gold character-name text above it, and tiny unreadable film-credit lines below. The right billboard is a dark sleek cinematic ad panel with a blue-black blurred city-speed background, faint futuristic corner-line graphics, and a white {argument name="brand logo text" default="Disney"} logo near the lower left. Surround the main billboards with bright real-world-style Times Square signage, including exactly five clearly noticeable side sign clusters: a large M&M’s World sign on the left, a vertical red tkts sign near the stairs, a vertical TIMES SQUARE sign on a building near the right billboard, a stacked Coca-Cola/M&M’s sign column on the far right, and assorted small colorful square ads below the billboards. Use high dynamic range lighting, realistic reflections, deep blue evening sky, sharp architectural detail, energetic tourist crowd, camera flashes, and cinematic wide-angle perspective. Keep the overall image photorealistic and urban, with no extra readable headline text beyond the specified billboard text and signage.
Comic / Storyboard - Pink Princess Idol Character Collage — output

Comic / Storyboard - Pink Princess Idol Character Collage

あまり🖋️AI &フリー素材配布GPT Image 2
Goal: Create an ultra-cute pink Japanese anime character reference collage for a princess idol named {argument name="character name" default="シャソリア"}, drawn like a dense hand-sketched scrapbook page full of hearts, lace, ribbons, plush toys, and handwritten notes.

Canvas: Vertical 3:4 portrait page, pale blush-pink paper background, monochrome rose-pink line art with soft watercolor shading, high detail, sparkles and doodles everywhere. Use a sweet shoujo manga style with delicate pen strokes, rosy gradients, and a slightly messy hand-drawn layout.

Main subject: A young kawaii princess idol girl with {argument name="hair color" default="cotton-candy pink"} long twin-tail hair, big sparkling pink eyes, frilly lace dress, heart tiara, rose hair ornaments, pearl chains, bows, heart accessories, ruffled socks, and pink Mary Jane heels. She should feel adored, shy, fluffy, and doll-like. Add bunny and teddy-bear motifs throughout.

Layout: Make a crowded character sheet collage with exactly 9 visible depictions of the same character: 1 large seated full-body illustration on the right holding a bunny plush; 1 large left-side close-up/back-of-head portrait with ornate heart tiara and roses, partially covered by a centered blank square placeholder; 1 sleeping chibi face in the top-right corner; 1 small chibi face at lower left with puffy sleeves; 1 small neutral chibi head near the lower middle; 1 happy laughing head at the bottom center; 1 tiny full-body chibi at the bottom right; 1 peeking half-body character entering from the left edge; and 1 small shy face/portrait near the center-left. Keep the main full-body figure as the visual focus.

Blank area: Place a large opaque pastel pink square in the upper-left/center area, covering part of the large portrait, as an empty image/name placeholder.

Text content: Use playful handwritten Japanese notes and labels in pink ink. Include a large bubbly title at the top-left reading {argument name="title text" default="シャソリア"}. Add scattered handwritten phrases such as 「すきらきらおひめさま!!♡」, 「しくすさんもだいすき♡」, 「ふわふわのリボンテールさいこーっ♡」, 「かわいすぎ!!! 天才…!? 尊い(;_;)♡」, 「すきなもの うさちゃん、くまさん、いちご、リボン おひめさまっ…!!」, 「ゆめ みんなをしあわせにするアイドルになるっ…♡」, 「ぴんくがいちばんしあわせ♡」, 「リほんいっぱいだいすき!」, and 「お姫さまになりたいの…♡」. Make the handwriting casual, rounded, and decorative, with speech bubbles and cloud-shaped note boxes.

Decorative elements: Include exactly 6 prominent plush or animal mascots: a teddy bear at the top center, a bunny at the top right, a bunny plush held by the main girl, a small teddy near the bottom note card, a small bunny near the heart name balloon, and a tiny animal hair clip on the main girl. Add many hearts, stars, bows, roses, pearls, lace trims, dangling charms, a heart-shaped name balloon, a small cupcake, heart shoes, and tiny crowns.

Color and finish: Predominantly pink and red-pink ink on a light cream-pink background, with white highlights and soft blush shading. Keep everything cute, detailed, cluttered, and hand-drawn, like a scanned idol character concept sheet. No realistic rendering, no dark colors, no modern UI, no watermark.
Product Marketing - Nina 3D Typography Portrait — output

Product Marketing - Nina 3D Typography Portrait

PhotoGPTGPT Image 2
{argument name="subject name" default="NINA"}” full-body studio fashion portrait, leaning casually against large vertical 3D block letters spelling “{argument name="subject name" default="NINA"}”, clean modern editorial composition. Female model in {argument name="clothing" default="relaxed black oversized t-shirt and black cargo pants"}, hands in pockets, subtle confident expression, natural pose, crossed legs, minimal styling, sneakers. Dark neutral studio background (matte charcoal/grey), soft diffused key light from front-left, gentle shadow falloff, studio-grade lighting, soft highlights on skin, realistic skin texture, natural makeup, detailed fabric folds. Typography: bold white 3D sans-serif letters stacked vertically, slightly taller than subject, matte finish, soft shadows, perfectly aligned beside subject. Color grading: neutral, slightly cool tones, high-end fashion editorial look, low saturation, clean contrast. Camera: Sony A1, {argument name="lens" default="85mm"} lens, f/2, shallow depth of field, ultra sharp focus, magazine-quality, 8k, professional studio photography. Negative prompt: cluttered background, extra text, distorted body, harsh lighting, oversaturation, blur, noise, low detail
Profile / Avatar - Face-Consistent Beauty Portrait Collage — output

Profile / Avatar - Face-Consistent Beauty Portrait Collage

WasifAIGPT Image 2
A vertical collage of three {argument name="style" default="YZK"} photos. Using the uploaded selfie as the ONLY and exclusive face reference, keep the facial features, and facial structure exactly the same as the reference image. The character poses against a neutral light background. A girl with a beautiful, voluminous hairstyle, seemingly styled with a brush, wearing {argument name="makeup style" default="foxy makeup and pronounced, angled lashes"}. In the first photo, she's very close to the camera, looking at it with one eye and winking. In the second photo, she's turned away, her head coquettishly turned toward the lens, her hairstyle slightly covering her face, but not too much. In the third photo, she's looking very close to the lens, her hair to the side, thus covering her left eye, pouting and looking forward. Close-up and medium shot, minimalist composition, vintage digital texture, slight blur, glamorous atmosphere. Photo taken on {argument name="device" default="iPhone 17 Pro Max"} with flash.
E-commerce Main Image - High-Fashion Editorial Portrait Edit — output

E-commerce Main Image - High-Fashion Editorial Portrait Edit

Pixel by us ✨GPT Image 2
Edit the reference photo into a high-fashion studio portrait. Keep the same pose, facial structure, hairstyle, body proportions, lighting, and plain light gray background. Change the outfit color from bright pink to {argument name="color" default="rich vibrant red"} while preserving the fabric texture and details. Change the handbag color to matching {argument name="accent color" default="red"} and remove all visible text, logo, branding, and watermark from the handbag or anywhere in the image. Keep the white platform heels unchanged. Make the final image photorealistic, clean, sharp, and editorial-style with natural skin texture and realistic shadows.

Negative prompt: watermark, logo, text, brand name, distorted anatomy, extra fingers, bad hands, blurry face, low quality, overedited skin, cartoon, CGI.
Profile / Avatar - Modern Korean Streetwear Portrait — output

Profile / Avatar - Modern Korean Streetwear Portrait

AliceGPT Image 2
Create image featuring a young {argument name="ethnicity" default="Korean"} woman with mid-length {argument name="hair color" default="brown"} hair styled with {argument name="accent color" default="lime green"} hair clips on both sides, posing against a plain white wall while wearing a cropped black long-sleeve top, black high-waisted pants, and a vibrant lime green snakeskin-patterned saddle bag slung over her shoulder.
Product Marketing - SmartStep Back to School Poster — output

Product Marketing - SmartStep Back to School Poster

𝐌GPT Image 2
A bright {argument name="theme" default="back to school"} advertisement poster. An excited {argument name="subject" default="young girl age 8"} in a neat school uniform skips happily beside a giant shiny black school shoe 3x her height with a silver buckle detail, "{argument name="brand name" default="SMARTSTEP"}" written in bold navy font on the sole. Bright cheerful classroom background with chalkboard colorful pencils and floating gold stars. Friendly bold rounded typography "SMARTSTEP" in navy and yellow filling the background. Tagline bottom: "Step smart every day." Small text top-right corner reads "Designed with GPT Image 2" in grey. Photorealistic, fun back to school commercial style, bright cheerful classroom lighting.
Profile / Avatar - Moody Cinematic Eye Portrait — output

Profile / Avatar - Moody Cinematic Eye Portrait

Duet | AIGPT Image 2
Close-up portrait of a {argument name="subject" default="man"} looking directly at the camera. His face and neck are mostly obscured by deep shadow. A single, narrow horizontal band of light cuts across his face, illuminating only his {argument name="feature to highlight" default="eyes"} and the bridge of his nose. He has a strong, defined jawline and short, textured hair. He is wearing a {argument name="clothing" default="simple black shirt"}. The background is a plain, overcast grayish-blue sky. Dramatic, high-contrast lighting creates a moody, cinematic atmosphere.
Profile / Avatar - Korean Fashion Editorial Portrait — output

Profile / Avatar - Korean Fashion Editorial Portrait

𝗦𝗮𝗻𝗶𝗮GPT Image 2
{argument name="subject" default="Young Korean woman"}, {argument name="accessory" default="black bucket hat"}, {argument name="outfit" default="black turtleneck sweater"}, long black hair in a half-up hairstyle, glossy pink lips, flawless radiant skin, chin slightly lowered with eyes looking upward toward the camera, confident and mysterious expression. Minimal gradient purple studio background, cool dramatic lighting, soft shadows, fashion performance aesthetic, close-up portrait composition, Korean beauty editorial style, ultra-realistic photography, detailed skin texture, natural makeup, cinematic mood, professional DSLR shot, shallow depth of field, luxury fashion campaign, photorealistic, 8K quality.
Social Media Post - Golden Hour Rose Portrait — output

Social Media Post - Golden Hour Rose Portrait

PromptLabGPT Image 2
Overhead cinematic shot looking straight down at a {argument name="subject" default="young woman with wavy brown hair"}, gazing softly up into the camera. She holds a {argument name="item" default="bundle of deep crimson roses"} wrapped in kraft paper. She's wearing a {argument name="clothing" default="black long-sleeve top"} and a yellow crossbody bag, standing on a brick pathway. Warm golden hour sunlight filters through the background creating a hazy, dreamlike glow. Shallow depth of field, heavy film grain, vintage nostalgic color palette.
Comic / Storyboard - Ethereal Silhouette on a Rooftop Edge — output

Comic / Storyboard - Ethereal Silhouette on a Rooftop Edge

Sheikh Sharik 2.0GPT Image 2
A surreal cinematic artwork about the feeling of missing someone, a {argument name="subject" default="lonely man"} sitting at the edge of a {argument name="location" default="rooftop/cliff"} under a {argument name="moon type" default="giant glowing moon"}, beside him an ethereal glowing silhouette of someone no longer there, transparent ghost-like figure made of stardust and soft light, emotional atmosphere, dreamy clouds, city lights far below, melancholic mood, deep emotions, cinematic lighting, ultra detailed, soft glow, starry sky, realistic yet fantasy aesthetic, emotional storytelling, volumetric lighting, masterpiece, 8K, moody colors
Comic / Storyboard - Cinematic Editorial Urban Golden Hour — output

Comic / Storyboard - Cinematic Editorial Urban Golden Hour

BMXGPT Image 2
Cinematic editorial photography of a {argument name="street type" default="quiet urban street"} during {argument name="time of day" default="golden hour"}. A single {argument name="subject" default="young woman in a flowing sleeveless beige orange dress"} walks slowly from left to right along a stone sidewalk beside a {argument name="wall type" default="massive terracotta red plaster wall"}. The woman is positioned in the lower-left third of the frame, captured in side profile, calm and introspective, with her dress gently moving as she walks. A dramatic diagonal beam of warm golden sunlight cuts across the red wall from upper right to lower left, creating strong geometric light and shadow contrast. The architecture is minimal and elegant, with dark window frames, a small upper window, a recessed wooden doorway on the right, textured plaster wall, stone curb, and quiet empty street foreground. Warm amber lighting, deep soft shadows, muted terracotta color palette, cinematic film grain, realistic textures, premium art-house film still mood, poetic solitude, sophisticated composition, 35mm lens, wide 16:9 frame, natural realistic photography, no text, no logo, no extra people.
Comic / Storyboard - Emotion Grid with Gradient Backgrounds — output

Infographic / Edu Visual - Multi-Panel Emotional State Grid

PromptLabGPT Image 2
Grid layout with thin white gaps between panels and a subtle outer white border around the entire composition. Clean, modern UI aesthetic with slight rounded corners on every tile.

Panel 1: {argument name="emotion one" default="Joyful (Yellow)"}. Warm yellow gradient. Arms raised overhead. Eyes shut. Wide open laugh. High-energy pose.
Panel 2: {argument name="emotion two" default="Shocked (Blue)"}. Blue gradient. Both hands cupping cheeks. Eyes wide open. Mouth agape. Eyebrows arched high.
Panel 3: {argument name="emotion three" default="Stern (Red)"}. Solid red background. Arms folded. Brows furrowed. Lips pressed tight. Dark hoodie.
Panel 4: Affectionate (Pink). Soft pink gradient. Cradling a small brown dog. Gentle smile. Cozy knit sweater.
Panel 5: Confident (Purple). Purple gradient. One hand resting on hip. Slight smirk. Graphic tee. Easy, relaxed stance.
Panel 6: Approving (Green). Green gradient. Baseball cap and denim jacket. Thumbs up. Relaxed smile.
Panel 7: Melancholy (Gray). Gray gradient. Eyes angled slightly downward. Inner brows slightly raised. Lips gently curved down.
Social Media Post - Hongdae Street Style Portrait — output

Social Media Post - Hongdae Street Style Portrait

NawalGPT Image 2
Young woman with {argument name="hair style" default="extra long straight brown hair with a center part"}, wearing a {argument name="outfit" default="light grey fitted tank dress and a denim jacket tied around her waist"}. She has a black shoulder bag and a silver necklace. She is standing at a {argument name="location" default="city alley middle in Seoul's Hongdae street"} with her arms relaxed. Summer background, bright daylight, effortless street style, photorealistic.
Infographic / Edu Visual - Dutch Golden Age Food Photography — output

Infographic / Edu Visual - Dutch Golden Age Food Photography

PromptLabGPT Image 2
Render {argument name="dish" default="DISH"} as a Dutch Golden Age or Italian Renaissance oil painting, hyperrealistic with dramatic chiaroscuro lighting. Place the hero dish front and center on dark velvet or stone, ingredients arranged in a baroque composition all around it. One strong light source from upper-left reveals every texture: glistening proteins, translucent sauces, jewel-bright vegetables, rustic bread, scattered fresh herbs. Label each ingredient with a small ornate gold cartouche in copperplate script: "{argument name="ingredient" default="[INGREDIENT]"} [poetic Latin or French descriptor]". Add the dish name in gilded ornate typography at the top: "{argument name="dish name" default="[DISH NAME]"}". Subtitle: "[TAGLINE]". Mood: Caravaggio meets Rembrandt meets the most craveable food photo ever shot. Deep rich shadows, jewel-tone colors, extraordinary museum-quality, utterly craveable.
Profile / Avatar - Editorial Vertical Portrait with Black Mist — output

Profile / Avatar - Misty Korean Editorial Portrait

PromptLabGPT Image 2
Vertical 9:16 editorial portrait — single subject. Soft black mist effect, gentle haze, mild highlight glow, desaturated palette. Simple interior, clean backdrop with subtle texture. Subject: {argument name="subject" default="young Korean woman, bare-faced, natural skin"}. Clothing: {argument name="clothing" default="snug ribbed knit or camisole under an open overshirt"}, high-waisted bottoms; drape is soft and body-skimming, not explicit. Hair: loosely tousled, natural body. Pose: {argument name="pose" default="seated on the floor, one knee drawn up, the other leg extended, body slightly reclined"}, uneven shoulder line, head gently tilted. Framing: off-center, breathing room in the negative space. Expression: serene, gaze slightly withdrawn, lips relaxed. Light: soft lateral source, gradual shadow. Atmosphere: low-key, intimate, quiet allure from natural posture — unposed and effortless. Render: fine grain, gentle softness, true-to-life.
按模型、风格或主题浏览

寻找下一个方向

ASTORIE CANVAS

让灵感,继续生长。

在同一个创作空间,连接提示词、参考素材和生成结果。

打开创作画布 ↗