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

9,894 条提示词

Social Media Post - Oakland Streetwear Editorial — output
Profile / Avatar - Professional Branded Business Portrait — output
Profile / Avatar - Korean Girl Nighttime City Skyline Selfie — output
Social Media Post - Candid Street Portrait — output
Product Marketing - Luxury Fashion Editorial Magazine Poster — output

Product Marketing - Luxury Fashion Editorial Magazine Poster

Aniya IntelligenceGPT Image 2
Create a premium, hyper-realistic luxury fashion editorial magazine poster inspired by the uploaded reference image, using my uploaded female face as the ONLY identity reference for the main female subject.

Preserve my exact facial identity and natural appearance — facial structure, skin tone, eyes, eyebrows, nose, lips, cheekbones, jawline, facial proportions, natural skin texture, hairstyle, and overall likeness. Keep me instantly recognizable. Do not beautify, reshape, feminize, age, de-age, or alter my facial features.

Composition:
Create an elegant minimalist studio fashion scene in a sophisticated charcoal gray, silver, and soft ivory color palette. The woman is positioned slightly right of center in a dramatic editorial pose, leaning gracefully backward against an oversized sculptural upholstered chair covered in richly textured dark-gray fabric.

She wears a fitted charcoal-gray corset-style top, high-waisted wide-leg gray denim trousers, and sleek black pointed-toe stiletto heels, with a small structured black handbag hanging naturally from one hand. Her pose should feel confident, relaxed, powerful, and fashion-forward. Add subtle jewelry and polished but natural styling.

Use a clean light-gray studio background, glossy reflective floor, soft diffused cinematic lighting, realistic shadows, subtle reflections, and premium high-fashion photography. Keep the image sophisticated, restrained, and editorial rather than overly glamorous.

Typography & Layout

Replace the original branding and wording with completely original text:

Top:
{argument name="magazine heading" default="LUMIÈRE"}

Main headline:
QUIET
CONFIDENCE

Use an elegant high-contrast luxury serif typeface with thin refined strokes.

Small tagline:
presence speaks louder.

Bottom-left:
BE YOU.
THE WORLD WILL ADJUST.

Bottom-right:
EST. 2026
MODERN FEMININITY

Add minimal thin divider lines and one or two tiny sparkle/star accents. Typography should be perfectly aligned, sharp, readable, and integrated naturally into the composition.

Overall aesthetic: quiet luxury, contemporary fashion magazine, sophisticated monochrome editorial, effortless confidence, premium campaign photography, realistic fabric texture, realistic skin, cinematic studio lighting, high-end print quality.
使用此提示词 ↗
Infographic / Edu Visual - Step-by-Step Pancake Process Collage — output

Infographic / Edu Visual - Step-by-Step Pancake Process Collage

Dua FatimaGPT Image 2
Create an ultra-realistic food photography collage in a {argument name="layout" default="2×2 grid"}, showing the complete process of making {argument name="food item" default="fluffy American pancakes"}, matching the reference composition.\n\nTop-left: A {argument name="setting" default="wooden kitchen table"} with a large white ceramic bowl filled with smooth pancake batter, surrounded by neatly arranged ingredients: a small bowl containing one raw egg, a cup of white flour, a small dish with butter, a glass jar of milk, a small bowl of baking powder, a cracked eggshell, and a metal whisk. Warm natural kitchen lighting, realistic textures, clean overhead composition.\n\nTop-right: Close-up of a black non-stick frying pan on a stovetop. A hand wearing a beige oven glove holds a ladle and pours thick pale pancake batter into the center of the hot pan. Visible steam and tiny butter droplets around the pan. Warm wooden kitchen background, realistic cooking action.\n\nBottom-left: Two thick fluffy pancakes cooking in the same black skillet. One pancake is golden brown and partially cooked, while the other is being flipped with a spatula. Subtle steam rising from the pan, realistic bubbles and crispy edges, warm natural lighting.\n\nBottom-right: Final serving of several thick, fluffy, golden-brown American pancakes stacked beautifully on a plate, showing soft airy layers and perfectly browned surfaces. Appetizing close-up food photography, warm tones, realistic texture and subtle highlights.\n\nStyle: photorealistic, premium food photography, natural warm kitchen lighting, realistic ingredients, shallow depth of field where appropriate, detailed textures, authentic cooking atmosphere, clean 2×2 split composition, consistent cookware and ingredients across all panels, high detail, 8K, no text, no labels, no watermark.
使用此提示词 ↗
Game Asset - Cosmic Galaxy Dual Portrait Template — output

Game Asset - Cosmic Galaxy Dual Portrait Template

shah_zadiiGPT Image 2
Create two separate ultra-detailed cinematic fantasy portraits from one prompt, both using the exact same deep blue cosmic galaxy theme and visual style.

IMAGE 1 — WOMAN:
Create a beautiful clearly adult woman with long flowing black hair, luminous smooth skin, glamorous blue-and-silver celestial eye makeup, glossy lips, and sparkling star-like details across her face. Add elegant crescent moon and star jewelry, subtle crystal accents, and glowing cosmic particles around her. Her expression is confident, mysterious, and attractive. Surround her with deep blue nebula clouds, glowing stars, large planets, moons, cosmic dust, and electric-blue light. The galaxy energy should naturally blend around her face, hair, shoulder, and clothing.

IMAGE 2 — MAN:
Create a handsome clearly adult man in the exact same blue cosmic theme. He has thick slightly messy black hair, a neat dark beard, strong facial features, intense glowing blue eyes, and a confident mysterious expression. Add subtle galaxy-like glowing patterns and tiny stars across one side of his face. His hand is near his chin in a stylish fashion pose with an elegant dark metallic ring. Surround him with the same deep blue nebula clouds, glowing planets, moons, stars, cosmic dust, and electric-blue energy.

IMPORTANT:
Generate the woman and man as two separate images, not together in one frame. Keep the same lighting, same blue galaxy color palette, same premium fantasy fashion style, same level of detail, and matching visual identity so both images look like a coordinated pair.

Ultra-realistic, premium cinematic lighting, high contrast, glossy luxury fantasy look, sharp focus, detailed skin and hair, magical blue glow, no text, no watermark.

Vertical portrait composition, 9:16 for both images.
使用此提示词 ↗
Comic / Storyboard - Gourmet Product Commercial Storyboard Template — output

Comic / Storyboard - Gourmet Product Commercial Storyboard Template

ÀBDŪLLÂHGPT Image 2
TITLE:
Premium {argument name="brand name" default="Nutella"} Product Commercial Storyboard

FORMAT:
• Single-page premium storyboard
• 3:4 Portrait ratio
• Luxury food product advertising
• 8 cinematic product-focused scenes
• Product remains the main hero
• High-end advertising agency presentation

HEADER:
• Elegant serif typography
• Information cards:

- Duration: 20 Seconds
- Style: Cinematic Gourmet Food Commercial
- Product: {argument name="product name" default="Nutella Hazelnut Spread"}
- Audio: Soft Spread + Food ASMR
  • Why This Style Works section
  • Warm brown, cream and golden aesthetic
  • Minimal hazelnut decorative accents

STORYBOARD:

1. Premium Nutella jar standing on polished dark wood
2. Jar lid opening in extreme macro
3. Creamy Nutella slowly spreading from the jar
4. Chocolate spread forming a glossy ribbon in mid-air
5. Nutella cascading over fluffy pancakes
6. Extreme macro showing rich chocolate texture and tiny reflections
7. Pancake stack surrounded by the hero jar and hazelnuts
8. Final luxury product packshot with dramatic Nutella spread

EVERY PANEL:
• Scene number
• Duration badge
• Camera direction
• Visual
• Action
• Product detail

CAMERA:
Extreme macro, slow-motion spread photography, overhead food shot, controlled push-in, shallow depth of field, cinematic hero framing.

STYLE:
Ultra-realistic food advertising, realistic spread viscosity, glossy chocolate texture, warm studio lighting, premium glass packaging, sophisticated gourmet presentation, 8K.
使用此提示词 ↗
Social Media Post - Sunlit Window Antique Room Portrait — output

Social Media Post - Sunlit Window Antique Room Portrait

Prompt アトリエ|AI画像プロンプトGPT Image 2
Subject:
White profile looking up at a floral window

Main Subject:
A vertical profile photograph of an adult woman sitting at a dark wooden table in the center-right of a bright room with flowers and old furniture, looking up towards the window.

Person/Expression:
Body and face directed to the left of the screen, with eyes turned up towards the window on the upper left in a pensive expression. Slender oval face, natural eyebrows, wide brown eyes, a clean nose bridge, and pale lips. Long wavy dark brown hair with thin bangs and thin locks along the cheeks.

Clothing/Pose:
A camisole with thin shoulder straps combining white rib knit and lace, and an off-white skirt. Sitting sideways on a chair, leaning her left elbow on the table with her fingertips near her lips, and her right forearm placed on the table.

Background/Light:
A window behind lace curtains on the left side of the screen, white and pink vases on the table and background, and an old mirror and warm-colored lamp on the right side. Harsh, warm daylight streams through the left window, creating bright highlights and contoured shadows on her face and shoulders.

Composition/Camera:
A 3:4 vertical composition, with the camera placed at the same height as the seated person, capturing from the upper right from the top of the head to above the waist. The person is placed prominently on the center-right, with the window and flowers on the left. Focus on the profile and fingertips, with the background flowers and mirror lightly blurred.

Texture/Style:
Photorealistic live-action photograph. Delicately capturing the wavy hair, white lace and ribbing, wooden table, petals, and the warm shadows of window light.

Negative:
No looking at the camera; do not omit the flowers and the left window.
使用此提示词 ↗
Social Media Post - Woman by Flower-Covered Table at Night — output

Social Media Post - Woman by Flower-Covered Table at Night

Prompt アトリエ|AI画像プロンプトGPT Image 2
Subject:
{argument name="subject" default="Profile in flower light"}

Main Body:
{argument name="main scene" default="A vertical photograph of an adult woman sitting at a flower-covered table in the center-right of a nighttime interior, resting her cheek on her palm and looking out the window."}

Person/Expression:
Quiet profile expression with eyes looking to the right and mouth closed. Rounded oval face, thin natural eyebrows, wide brown eyes, small nose, and pale pink lips. Light brown hair in a casual high updo with thin bangs and wisps along the cheeks.

Clothing/Pose:
{argument name="clothing" default="An off-white dress with small red-pink floral patterns and thin ribbon ties at the shoulders."} Sitting in a chair, resting the right elbow on the table and supporting the right cheek with the palm. Left arm near the tabletop.

Background/Lighting:
White daisies, light purple flowers, and pink roses in the foreground and sides. A small candle on the left, a faceted warm glass lamp on the right, with curtains and thin fairy lights in the background. Warm light from both sides softly envelops the face, with smooth shadows.

Composition/Camera:
3:4 vertical composition, chest-up photo from seated eye level. The subject is large in the center-right, with the supporting hand and flowers in the lower foreground, leaving space for the light on the left. Focus on the face, with soft bokeh on the foreground flowers and background lights.

Texture/Style:
Photorealistic live-action photograph. Soft and detailed rendering of small floral fabric, petals, wisps of hair, and the warm glow of candles and glass lamps.

Negative:
Do not look at the camera; do not omit flowers or warm lighting.
使用此提示词 ↗
Comic / Storyboard - Photo to Storybook Illustration Split — output

Comic / Storyboard - Photo to Storybook Illustration Split

ÀBDŪLLÂHGPT Image 2
Create a single vertical 3:4 PHOTO + HAND-DRAWN ILLUSTRATION artwork based ONLY on the uploaded photograph.

Use the uploaded photograph as the ONLY visual reference. Analyze the photograph independently and reproduce the exact subject, pose, expression, clothing, hairstyle, accessories, objects, proportions, and overall moment in the illustration. Do not introduce elements from any previous image or reference.

TOP — ORIGINAL PHOTOGRAPH

Use approximately the upper 50% of the canvas for the original photograph.

Preserve the photograph faithfully and naturally:
- Keep the original subject exactly recognizable.
- Preserve the face, expression, hairstyle, clothing, accessories, pose, body proportions, and visible objects.
- Preserve the original environment and composition.
- Do not retouch, beautify, replace, or redesign the subject.
- Keep the photograph realistic with its original lighting, colors, textures, and details.

BOTTOM — HAND-DRAWN ILLUSTRATION

Use approximately the lower 50% for a charming handmade illustration of the SAME photograph.

Transform the photographic moment into a delicate children's storybook-style hand-drawn artwork.

Illustration style:
- Soft watercolor and colored-pencil texture
- Gentle pencil/ink outlines
- Slightly imperfect handmade strokes
- Warm, tactile off-white textured paper
- Soft natural shading
- Subtle watercolor washes
- Cute, expressive, wholesome appearance
- Delicate handcrafted imperfections
- No glossy digital-rendered appearance
- No photorealism
- No 3D CGI
- No anime or cartoon franchise style

Most importantly, accurately preserve the subject from the photograph:
- Same pose and body position
- Same facial expression
- Same hairstyle
- Same clothing and clothing patterns
- Same shoes/accessories
- Same proportions
- Same distinctive visual details
- Same overall action or mood

Simplify the background substantially. Do not recreate every background detail. Keep only a very subtle suggestion of the original environment, allowing the illustrated subject to remain the main focus.

Place the illustrated subject slightly smaller than the photograph's subject, surrounded by generous negative space.

MINIMAL DECORATIVE DETAILS

Add a few tiny hand-drawn decorative marks around the illustration, such as:
- small hearts
- simple motion lines
- tiny doodles
- subtle stars or flowers

Keep these decorations sparse and tasteful.

Add a small handwritten caption near the illustration, such as:

"little happy girl ♡"

The caption should look naturally handwritten with a casual brown/gray pencil or ink texture.

If the uploaded subject is not a girl, automatically adapt the wording appropriately or omit the caption entirely.

OVERALL AESTHETIC

The final artwork should feel like a precious memory transformed into a page from a handmade children's picture book.

Composition:
- Vertical 3:4
- Clean separation between photograph and illustration
- Soft warm editorial presentation
- Large amount of negative space around the illustration
- Minimal, elegant, sentimental
- Premium handmade stationery / illustrated scrapbook aesthetic

CRITICAL RULE:
The uploaded photograph is the sole source of truth. Do not invent, substitute, merge, or carry over any person, clothing, object, background element, color, pose, or detail from another image.

The bottom illustration must clearly look like a hand-drawn version of the EXACT moment shown in the top photograph.

REFERENCE PRIORITY:
1. Exact subject and pose
2. Facial expression and hairstyle
3. Clothing and accessories
4. Overall composition
5. Illustration style
6. Minimal decorative elements

Never sacrifice subject accuracy for artistic stylization.
使用此提示词 ↗
Product Marketing - Fashion Editorial Magazine Cover — output

Product Marketing - Fashion Editorial Magazine Cover

Dr Bloodline | AIGPT Image 2
Ultra-realistic fashion editorial magazine cover showing {argument name="subject" default="[Reference Person]"} seated confidently on a low wooden pallet bench inside a contemporary creative studio. Outfit is fully monochrome: black denim jacket, wide-leg black trousers, black t-shirt, and black low-top canvas sneakers with white rubber soles and white laces. Sitting in a relaxed wide stance, leaning slightly forward, one elbow resting on the knee, one finger resting at the temple, gaze locked directly into the lens. Mood: calm, self-assured, visionary.

Studio backdrop: a matte black wall lined with vertical wooden art panels painted in vivid geometric shapes, giving the space an elevated creative-agency feel. Warm cinematic lighting falls softly across the face and jacket, while rich shadows preserve dramatic editorial contrast. A natural textured woven rug sits beneath, adding warmth to the luxury studio setting.

Cover layout uses a single typographic element only: oversized bold beige text at the very top spelling "{argument name="magazine title" default="BLOODLINE"}" in a wide condensed sans-serif, dominating the upper portion of the frame. Zero additional text anywhere, no subheadings, no captions, no handles, no dates, no watermarks, no logos. "{argument name="magazine title" default="BLOODLINE"}" is the sole word visible in the entire image.

Color story: jet black, warm cream-beige, muted burnt orange, earthy brown, dusty teal, cinematic shadow tones. Centered, symmetrical crop with the visual weight of a GQ editorial, a high-end streetwear campaign, and a cinematic creator brand shoot.

Captured on a {argument name="lens" default="50mm prime lens"}, shallow depth of field, hyper-detailed skin and fabric texture, soft drop shadows, photorealistic lighting, clean type design, high-resolution editorial composition, 8K output, premium cinematic color grade.
使用此提示词 ↗
Profile / Avatar - Urban Luxury Male Portrait — output
Social Media Post - Motorcycle Lifestyle Golden Hour — output

Social Media Post - Motorcycle Lifestyle Golden Hour

Abkr SadiqGPT Image 2
Use the uploaded photo as the facial identity reference.

Create an ultra-realistic cinematic lifestyle portrait of an adult man seated outdoors beside a premium sport motorcycle at a rustic countryside café during {argument name="lighting" default="golden hour"}.

Give the man a normal, neat short haircut with naturally trimmed sides and a clean hairline. Avoid exaggerated fades, undercuts, spikes, or overly styled hair. Keep the hairstyle simple, mature, and realistic.

Dress him in a {argument name="clothing" default="fitted black motorcycle riding suit consisting of a premium black leather riding jacket with subtle white, blue, and neon-yellow accent panels"}, a plain black high-neck inner shirt, black fitted riding trousers, protective black riding gloves, and tall black motorcycle boots with understated sporty details.

Pose him seated casually on a wooden café chair beside a rustic wooden table. His posture should appear calm, confident, and relaxed, with one hand resting naturally near his lap and the other positioned comfortably around the chair or thigh. Add stylish dark rectangular sunglasses.

Place a {argument name="motorcycle" default="large high-performance blue, white, red, and black sport motorcycle"} prominently beside him, angled slightly toward the camera. Include realistic aerodynamic fairings, windshield, mirrors, headlights, exposed suspension components, large front brake discs, racing-style wheels, carbon-fiber details, and premium mechanical textures.

On the wooden café table, place a white ceramic cup of coffee on a saucer, a neatly folded newspaper, riding gloves or small motorcycle accessories, and subtle everyday café details.

Set the scene on a stone-paved terrace surrounded by traditional dry-stone walls. In the background, show expansive green countryside with rolling hills, grazing fields, scattered mature trees, farmhouses, stone fences, and distant hills illuminated by warm late-afternoon sunlight.

Use beautiful golden-hour lighting coming from the side, producing warm highlights on the rider, reflective leather jacket, motorcycle bodywork, and countryside. Maintain realistic shadows, crisp foreground details, soft atmospheric depth in the distance, and natural cinematic color grading.

Composition: vertical portrait orientation, full-to-three-quarter body framing, rider positioned on the right side, motorcycle dominating the left side, countryside landscape clearly visible in the background.

Style: ultra-realistic professional photography, premium motorcycle lifestyle editorial, cinematic golden-hour lighting, highly detailed leather and metal textures, realistic skin, natural proportions, sharp focus, subtle depth of field, sophisticated masculine atmosphere, photorealistic 8K quality.
使用此提示词 ↗
Profile / Avatar - Giant Moon Night Silhouette — output
Product Marketing - Ronaldo Rooftop Fashion Shoot — output
Profile / Avatar - Summer Garden Lifestyle Portrait — output
Comic / Storyboard - Cinematic Character Profile Bible Sheet — output
Infographic / Edu Visual - Mount Fuji Watercolor Transformation — output

Infographic / Edu Visual - Mount Fuji Watercolor Transformation

Laraib Fatima‎GPT Image 2
Create a vertical before-and-after comparison image showing an ordinary landscape transformed into a minimalist watercolor-and-ink illustration. Canvas: portrait 4:5 aspect ratio. Layout: split horizontally into two equal panels with no border; the top panel is a realistic landscape photo and the bottom panel is the stylized illustration on warm off-white watercolor paper. Top panel: a clear daytime scene with {argument name="mountain name" default="Mount Fuji"} centered in the distance, blue sky with subtle wispy clouds, snow-capped peak, low mountain range, a row of white arched bridges crossing the midground, dry tan riverbank grasses, calm deep-blue river in the foreground with reflections, crisp natural colors and photographic detail. Bottom panel: preserve the exact same composition but simplify it into a delicate minimalist watercolor and thin ink sketch; small centered island-like landscape motif with a blue mountain silhouette and white snowy peak, white arched bridges, tan ochre riverbank, soft blue water reflections below, lots of empty paper around it, light washes, gentle bleeding edges, sparse fine-line details, elegant Japanese travel-sketch feeling. Include exactly one tiny handwritten signature-like mark centered beneath the illustration, very subtle and not readable. Use {argument name="sky color" default="clear vivid blue"}, {argument name="watercolor paper tone" default="warm ivory"}, and {argument name="illustration style" default="delicate minimalist watercolor and ink"}. Avoid extra text, people, vehicles, frames, heavy outlines, or clutter.
使用此提示词 ↗
Profile / Avatar - Golden Hour Coastal Portrait — output
Product Marketing - Albuquerque GTA-Style Crime Collage — output

Product Marketing - Albuquerque GTA-Style Crime Collage

드럼통청약당첨GPT Image 2
Goal: Create a square illustrated parody video game cover/poster in the style of a Grand Theft Auto V key art collage, themed around {argument name="series theme" default="Breaking Bad and Better Call Saul in Albuquerque"}. Make it look like polished digital box art with dramatic realism, comic-book painting, bold black panel borders, and a central oversized game logo.

Canvas: 1:1 square poster, high resolution, full bleed, saturated desert colors, crisp inked edges, cinematic lighting, no photo collage. Use a black background grid with tilted rectangular panels surrounding the center.

Layout: Use exactly 8 illustrated scene panels around one central title logo. The panels are separated by thick black diagonal borders. The central logo overlaps the panels and reads {argument name="main title text" default="grand theft auto"} in large stacked white block letters with black outline, plus a green Roman numeral V emblem with a white ribbon reading {argument name="ribbon location text" default="ALBUQUERQUE"}.

Panel count and contents: 1) Top-left large panel: stern bald middle-aged man with glasses, goatee, black porkpie hat, and dark jacket, with a beige RV in the desert behind him; include handwritten text “ALL BAD THINGS MUST PAY”. 2) Top-center panel: young man with stubble wearing a black-and-red beanie and hoodie, looking worried against a pink sunset city background; include handwritten text “YEAH BITCH!”. 3) Top-right narrow panel: helicopter flying over desert mountains and a water tower labeled “ALBUQUERQUE”. 4) Middle-left panel: slick lawyer in a suit pointing finger-guns toward the viewer, yellow legal-ad background; include red script “Better Call Saul!” and small text “ATTORNEY AT LAW”. 5) Middle-right panel: composed man in glasses and a dark suit in front of a fast-food sign reading “LOS POLLOS HERMANOS”; include small tagline “A HIGHER STANDARD”. 6) Bottom-left panel: bald older tough man in a black jacket looking over his shoulder near industrial tracks; include handwritten text “NO HALF MEASURES”. 7) Bottom-center panel: rear view of a black classic car driving toward the Albuquerque skyline and desert mountains, license plate reading “HEISENBRG”, roadside sign reading “ALBUQUERQUE NEW MEXICO”. 8) Bottom-right panel: plastic bag of blue crystal meth beside stacks of cash; include handwritten text “COOK SELL SURVIVE” and a small yellow square Rockstar-style rating/logo icon with a black “R” and white star.

Visual style: Highly detailed painterly realism mixed with GTA loading-screen illustration, strong outlines, warm desert yellows, turquoise blues, pink skies, noir shadows, expressive faces, dramatic cropped portraits, clean readable typography.

Constraints: Do not use actual actor names. Keep all visible text spelled exactly as specified. Maintain the exact 8-panel collage plus central logo. Avoid extra panels, watermarks, UI elements, or modern app overlays.
使用此提示词 ↗
Infographic / Edu Visual - Editable PPT Workflow Infographic — output

Infographic / Edu Visual - Editable PPT Workflow Infographic

SuSu_酥酥👅GPT Image 2
Goal: Create a dark futuristic Chinese workflow infographic slide showing how to turn written content plus images into an advanced editable PPT, with a premium tech presentation aesthetic.

Canvas: Wide 16:9 horizontal slide, deep navy/black background with subtle circuit-line texture, thin glowing border, cyan and gold neon accents, soft bloom highlights, clean corporate SaaS style.

Main headline: Centered at the top, use {argument name="headline text" default="文稿 + 配图 → 高级可编辑PPT"}. Highlight “文稿” in gold, “配图” in cyan, and the rest in white. Add a small cyan lens flare under the headline.

Top workflow layout: Place exactly 3 large rounded rectangular cards across the upper half, connected by a glowing horizontal process line and arrows that run left to right.
1. Card 1: Yellow numbered circle “1”, title “ChatGPT”, subtitle “理清文字结构”, large gold chat-bubble icon with three dots.
2. Card 2: Cyan numbered circle “2”, title “Image2”, subtitle “生成整页视觉稿”, small mock visual preview containing exactly 3 inner panels: a landscape image, a mini bar-chart/text panel, and a second landscape image.
3. Card 3: Yellow numbered circle “3”, title “GPT-6”, subtitle “拆层成可编辑PPT”, layered floating blue sheets over a gold base icon.

Central demonstration: In the lower middle-left, create one large tilted PPT slide mockup with rounded corners and glow. Slide title text: {argument name="demo slide title" default="未来城市:智能与可持续的融合"}. Slide subtitle: {argument name="demo slide subtitle" default="技术创新 · 绿色发展 · 生态共生"}. Inside the slide, show a cinematic mountain lake landscape at sunset, plus a small inset city skyline image on the right.

Metric row inside the slide: Show exactly 3 metric items along the bottom of the slide: “35% 能源效率提升” with a clipboard icon in cyan, “60% 碳排放降低” with a shield/check icon in gold, and “2026 全面落地目标” with a globe icon in gold.

Layer conversion effect: To the right of the central slide, show the slide splitting into multiple translucent editable layers, about 7 visible stacked panels, with flowing cyan and gold data particles moving from the slide into the layers.

Editable output list: On the right side, create exactly 4 stacked rounded cards connected by thin lines to the separated layers:
1. “标题文本” with smaller text “副标题文本”, icon: large letter T.
2. “流程图节点” with smaller text “可编辑 · 可调整”, icon: flowchart nodes.
3. “图片占位符” with smaller text “替换 · 缩放 · 裁剪”, icon: image placeholder.
4. “布局与样式” with smaller text “母版 · 主题 · 动画”, icon: layout grid.

Bottom slogan: Centered near the bottom, in gold Chinese characters with dot separators, use {argument name="bottom slogan" default="好看 · 能改 · 复用"}.

Visual style: High-resolution presentation infographic, crisp vector-like UI, luminous cyan and warm gold strokes, glassmorphism cards, subtle depth and perspective, modern Chinese typography, clean spacing, no people, no logos, no watermark. Keep all listed text legible and preserve the exact counts: 3 top workflow cards, 3 metric items, 4 editable-output cards, and 7 visible separated layer panels.
使用此提示词 ↗
Infographic / Edu Visual - Graphite Portrait Progression Sheet — output

Infographic / Edu Visual - Graphite Portrait Progression Sheet

Hania AiGPT Image 2
Goal: Create a vertical 3-by-3 tutorial-style progression sheet showing the same young woman’s portrait being developed from a faint construction drawing into a polished realistic graphite pencil sketch on clean white drawing paper.

Canvas: Portrait-oriented white paper background, 4:5 aspect ratio, divided into exactly 9 equal rectangular panels arranged in a 3 columns x 3 rows grid. The grid divisions are very subtle, created by slight tonal differences in the paper rather than visible borders.

Subject: The same front-facing young woman appears centered in every panel from the shoulders up. She has {argument name="hair color" default="dark brown hair rendered in graphite"}, thick softly arched eyebrows, almond-shaped light eyes, a straight delicate nose, full lips with a faint closed-mouth smile, an oval face, and a calm elegant expression. Her hairstyle is a voluminous loose updo with wispy curled strands falling beside both cheeks. She wears dangling earrings and an off-shoulder dark dress or neckline that forms a soft V shape across the bottom of the portrait.

Panel count and progression: Include exactly 9 portrait panels. Panel 1, top left: extremely faint initial construction sketch with an oval head, centerline, horizontal facial guide lines, rough neck, shoulders, and hair mass. Panel 2, top center: light clean line art with facial features, hair outline, earrings, shoulders, and neckline established. Panel 3, top right: early shaded portrait with more developed eyes, lips, hair texture, earrings, and dark neckline beginning. Panel 4, middle left: stronger graphite rendering, fuller hair shading, clearer facial planes, eyes, lips, shoulders, and dress. Panel 5, middle center: refined realistic portrait with balanced midtone shading, detailed hair strands, defined earrings, and darker neckline. Panel 6, middle right: nearly finished portrait with high contrast hair, smooth skin shading, detailed eyes, and darker clothing. Panel 7, bottom left: finished graphite portrait with polished face and hair, strong neckline shadow, and soft shoulder shading. Panel 8, bottom center: finished portrait variant with slightly smoother lighting and crisp facial detail. Panel 9, bottom right: final polished portrait, high realism, clean graphite values, detailed hair, earrings, expressive eyes, soft skin transitions, and dark off-shoulder garment.

Visual style: Extremely realistic traditional graphite pencil drawing, monochrome black-and-white, visible pencil grain, delicate crosshatching and smudged blending, soft eraser highlights, clean white drawing paper texture. The top-left panel should be very pale and sketchy, and each subsequent panel should gradually increase in contrast, detail, and realism until the final bottom-right portrait looks complete.

Constraints: Keep the woman’s identity, proportions, pose, expression, hairstyle, jewelry, and clothing consistent across all 9 panels. No text labels, no watermark, no colored ink, no digital UI elements, no extra objects, and no background scenery.
使用此提示词 ↗
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 ↗