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

10,050 条提示词

YouTube Thumbnail - Tech Tutorial Thumbnail with UI Mockup — output

YouTube Thumbnail - Tech Tutorial Thumbnail with UI Mockup

corbinGPT Image 2
A clean modern YouTube thumbnail on a bright white background, split visually between bold text on the left and a cropped presenter on the right. On the left, place a massive stacked headline in heavy black sans-serif uppercase reading {argument name="headline text" default="CLAUDE DESIGN"}, aligned top-left across two lines. Below it, add a large rounded rectangular orange banner with a subtle drop shadow containing bold white uppercase text with an orange outline that reads {argument name="subheadline text" default="IN 6 MINS"}. Near the headline, include 2 orange starburst spark shapes, one small beside the text and one much larger in the far right background. In the lower-left quadrant, show a floating app interface mockup for a design tool dashboard with a soft off-white panel, thin borders, rounded corners, and a faint shadow. The interface should have a left sidebar with 4 menu items labeled exactly: "Recent", "Your designs", "Examples", and "Design systems". The main panel header should say "Recent" and contain 3 project cards arranged in a grid, labeled exactly: "Thumio Design System", "Thumio Startup", and "Design System". On the right half, show a cropped photorealistic young adult man from chest up wearing a white turtleneck sweater, with messy light brown hair and light facial hair, positioned close to camera. His face is intentionally obscured by a solid tan rectangle placeholder covering most of the face area. He points with one hand toward the interface panel on the left, finger extended. Use a warm orange and white brand palette, high contrast, minimal clutter, polished creator-economy thumbnail styling, subtle shadows, and a composition designed for tech tutorial content.
Comic / Storyboard - Lunar Bathhouse Comedy Manga Page — output

Comic / Storyboard - Lunar Bathhouse Comedy Manga Page

猫おじGPT Image 2
A colorful single-page Japanese comic manga set in a whimsical lunar public bathhouse on the moon, drawn in a polished retro-futuristic anime style with warm lighting, thick clean panel borders, expressive sound effects, and highly detailed environmental storytelling. The scene is a moon onsen called "月面銭湯 つきのゆ" with a large illuminated entrance sign, blue noren curtain with the white character "ゆ", exposed pipes, gauges, rounded architecture, and a giant circular window showing the moon surface and Earth in space. Include exactly 8 comic panels arranged in a dynamic page layout. Panel 1: exterior establishing shot of the bathhouse on the moon, with the sign "月面銭湯 つきのゆ", a smaller sign reading "重力 1/6", a red milk vending machine labeled "牛乳", a tanuki statue, lunar terrain outside, and a vertical banner promoting the bath. Panel 2: a young female mechanic bathhouse worker with {argument name="character design" default="brown ponytail tied with a red polka-dot bandana, green work jumpsuit, tool belt, energetic expression"} adjusts a machine or boiler control, seen from behind or side, with speech balloons about preparing today's bath and boiler condition. Panel 3: a cute alien customer with {argument name="alien appearance" default="round mint-green body, purple spots, sleepy eyes, pink cheeks, small mouth, white towel with a purple star on its head"} relaxes in steaming bathwater, half submerged, with a rubber duck floating nearby and a wooden sign reading "ぬるめ じっくり リラックス". Panel 4: a small cleaning robot with {argument name="robot design" default="silver body, blue accents, black digital face with glowing blue eyes, red antenna light, thin mechanical arms and legs"} happily scrubs the floor with broom and bucket beside a hanging sign that says "清掃中". Panel 5: the same robot suddenly slips or splashes dramatically into the bath, with a huge water burst, many bubbles, the large sound effect "ぽわぁ〜ん!!", and the worker reacting in surprise from the side. Panel 6: the worker sits by the bath smiling, holding a bottle labeled "月面牛乳". Panel 7: the alien in the bath gives a thumbs-up while holding a bottle labeled "月面フルーツオーレ", looking blissfully satisfied, with the rubber duck still present. Panel 8: the cheerful robot poses beside the bath with cleaning tools and a bucket, near a bath curtain marked "ゆ" and a pink wash basin labeled "つきのゆ", saying the bath is the best. Maintain a cozy, comedic tone, retro Showa-style sento details mixed with space technology, glossy tiled bath surfaces, steam, bubbles, and cute character acting throughout. The comic should feel like a charming slice-of-life gag manga about working at a lunar bathhouse.
Social Media Post - Split-Screen Time Travel Scene — output

Social Media Post - Split-Screen Time Travel Scene

宝玉GPT Image 2
A horizontal split-screen cinematic shot of {argument name="scene" default="Times Square, New York"}, seamlessly blending two different eras: {argument name="first era" default="1920s"} on the left and {argument name="second era" default="present day"} on the right (default: about 100 years ago vs. present day). On the left side: show era-appropriate architecture, interior or environment design, materials, vehicles, and props that clearly belong to that historical period. People wear authentic clothing from the era, including hairstyles, accessories, and typical items in their hands. The overall mood feels nostalgic and historically accurate. On the right side: show the same scene in the modern era, with updated architecture or renovated structures, contemporary materials (glass, steel, LED screens, modern furniture), modern vehicles or equipment, and current technology. People wear contemporary fashion that matches today’s style in this setting. In the center: the two eras merge and overlap organically, without a hard dividing line. Elements from both eras visually interact: people from different times look at each other, walk through each other’s space, or seem surprised by the other era’s technology and objects. Architecture and environment smoothly morph from old to new. Make sure the scene is not just a simple left/right comparison but a dynamic time-travel interaction. Photorealistic, 8k resolution, cinematic lighting, wide angle, highly detailed textures, rich sense of time-travel storytelling. Aspect Ratio: 4:3
E-commerce Main Image - 3D Product Box Dieline Visualization — output

E-commerce Main Image - 3D Product Box Dieline Visualization

SalmaGPT Image 2
Assemble the dieline into a flawless 3D box with accurate panels, clean folds, undistorted type, and artwork preserved exactly. shoot it upright at a refined ¾ angle in a {argument name="setting" default="minimal premium studio setting"} with a soft neutral background, diffused light, subtle shadows, no props, true colours, {argument name="texture" default="matte paperboard texture"}, and realistic editorial detail
E-commerce Main Image - Gourmet Burger Commercial Photography — output

E-commerce Main Image - Gourmet Burger Commercial Photography

𝐌GPT Image 2
A premium fast-food commercial product photograph of a gourmet cheeseburger centered against a warm golden-yellow seamless studio background. The burger features a glossy sesame seed bun, fresh lettuce, tomato slices, onion rings, melted cheese, a juicy grilled beef patty, and rich sauce. Soft studio lighting, subtle shadows, mouthwatering texture, sharp focus, ultra realistic food advertisement photography, clean composition, 8K. Create a hyper-realistic exploded vertical infographic composition of a gourmet cheeseburger. At the top, a glossy sesame seed bun top with crisp texture. Below it, fresh green lettuce leaves, tomato slices, onion rings, melted cheese, a juicy grilled beef patty, a sauce layer, and a soft bun base. All ingredients are evenly spaced and perfectly aligned vertically. Warm yellow seamless studio background, soft commercial food lighting, subtle realistic shadows under each floating element, ultra-sharp focus, DSLR macro food photography, premium fast-food ad aesthetic, 8K. Add clean infographic text labels with thin pointer lines pointing to each element using these exact labels: “Bun Top” “Lettuce” “Tomato” “Onion” “Cheese” “Patty” “Sauce” “Bun Base”
YouTube Thumbnail - Streaming Scene Screenshot — output

YouTube Thumbnail - Streaming Scene Screenshot

neural nets.GPT Image 2
twitch screenshot of {argument name="person" default="tung tung sahur"} playing {argument name="activity" default="chess irl match"} on a stream with demis hannabis
Profile / Avatar - Forced Perspective Idol Portrait — output

Profile / Avatar - Forced Perspective Idol Portrait

BubbleBrainGPT Image 2
9:16 vertical — creative forced perspective portrait, {argument name="style" default="Korean idol style"}, single subject. analog 35mm film aesthetic, soft natural grain, slightly faded colors, gentle overexposure, pastel tones, low contrast, soft highlight bloom, airy and dreamy atmosphere. minimal indoor setting near a window, clean light-toned background, simple everyday environment. young {argument name="subject" default="Korean female idol"}, very attractive, natural minimal makeup, dewy realistic skin texture, subtle imperfections. outfit: {argument name="outfit" default="oversized white shirt loosely draped + short bottoms"}, soft fabric, relaxed fit, modest but subtly body-shaping, no revealing elements. hair: long dark hair, slightly messy, natural volume. composition (key): forced perspective illusion — the subject appears unusually small relative to nearby objects (such as being inside a cup, standing on a table edge, or interacting with a hand in the foreground), but still realistic; scale ambiguity created by camera distance and alignment. camera: slightly low or eye-level angle, intentional perspective distortion, foreground object close to lens, subject placed farther away to create size illusion. pose: natural relaxed posture, slight body curve, casual stance or light sitting pose. expression: soft calm gaze, slight smile or slightly parted lips, natural and unposed. lighting: diffused natural window light, soft shadows, gentle light wrapping around subject. mood: playful, slightly surreal but grounded in reality, intimate everyday moment with a visual twist. quality: ultra-realistic, fine film grain, slight softness, imperfect framing, natural imperfections.
Profile / Avatar - Kawaii coffee dog vector illustration — output

Profile / Avatar - Kawaii coffee dog vector illustration

宝玉GPT Image 2
a cute kawaii cartoon {argument name="animal" default="dog"} holding a steaming {argument name="object" default="coffee mug"}, same white background with soft light green ground, centered composition, flat 2D vector illustration, soft outlines, pastel colors, adorable mood, text above: "{argument name="text" default="No Coffee No Coddee"}" --ar 3:2
Social Media Post - Cinematic AI mood board prompt — output

Social Media Post - Cinematic AI mood board prompt

Kris KashtanovaGPT Image 2
Make a {argument name="format" default="mood board"} about {argument name="subject" default="AI"}, {argument name="style" default="cinematic style"}, use nostalgic stuff like Polaroids 
Portrait mode
Profile / Avatar - Cinematic Studio Portrait — output

Profile / Avatar - Cinematic Studio Portrait

MizGPT Image 2
{
  "prompt": "Studio portrait of a young adult woman with long wavy red hair and fair freckled skin, wearing a black sequined strapless mini dress and thigh-high black boots. She is seated on the floor in a relaxed yet confident pose, facing forward with a soft, neutral expression. A black ribbon choker drapes loosely around her neck. The scene is lit with warm, golden studio lighting that creates a circular spotlight effect behind her, casting soft shadows and adding depth. Minimalist background, editorial fashion photography style, high detail, cinematic warmth, smooth gradients.",
  "negative_prompt": "lowres, blurry, bad anatomy, extra limbs, deformed hands, distorted face, harsh shadows, overexposed, underexposed, watermark, text, logo, jpeg artifacts, cartoon, CGI, 3D render",
  "style": "editorial fashion photography, photorealistic",
  "camera": {
    "angle": "eye-level",
    "framing": "three-quarter body portrait",
    "lens": "85mm",
    "aperture": "f/2.0"
  },
  "lighting": {
    "type": "studio lighting",
    "setup": "warm spotlight with soft falloff",
    "mood": "cinematic and intimate"
  },
  "setting": {
    "location": "studio",
    "background": "warm gradient backdrop with circular light vignette"
  },
  "color_palette": [
    "black",
    "warm gold",
    "amber",
    "soft beige"
  ],
  "size": "768x1152"
}
Profile / Avatar - Oriental Fantasy Female Portrait Prompt — output

Profile / Avatar - Oriental Fantasy Female Portrait Prompt

李岳GPT Image 2
Oriental fantasy style {argument name="gender" default="female"}, half-body portrait, looking back in profile, ethereal and elegant temperament, soft divine beauty, delicate features, slightly downcast eyes, cool white delicate skin, light orange-pink makeup, accented with gold highlights.

Long hair flowing, with colored flowers and light particles (red, blue, orange, purple) integrated into the strands; the hair has a sense of flow and airiness.

Wearing a translucent silk gown and shawl, the material is light and transparent, fabric fluttering in the wind, with gilded textures and shining particles on the surface.

Overall lighting is warm gold backlighting, strong rim light, obvious volumetric light, floating light particles, soft glow, and a dreamy atmosphere.

The background is clean with a light color gradient, featuring shimmer and particle effects; the overall vibe is ethereal, dreamlike, and sacred.

Style: High-end CG illustration, ultra-fine, cinematic lighting, soft light rendering, 8K details, ArtStation trending style.
Comic / Storyboard - Transformers Space Scenes Prompt — output

Comic / Storyboard - Transformers Space Scenes Prompt

松果先森GPT Image 2
Image 1: All {argument name="faction A" default="Autobots"} assembled at the lunar base, with Earth hanging in the starry sky behind them and the Cybertron flag flying.

Image 2: All {argument name="faction B" default="Decepticons"} arrayed on the deck of an alien warship, with Megatron sitting on a throne overlooking the entire army.
Infographic / Edu Visual - Food Lifecycle Infographic Prompt — output

Infographic / Edu Visual - Food Lifecycle Infographic Prompt

知识猫图解GPT Image 2
An educational infographic themed "Life of {argument name="food name" default="Garlic"}."

The image must feature "a single complete food item" (such as a potato / a bunch of bananas / a head of garlic), using horizontal slicing to show the changes of the same food at different time stages, rather than a collage of multiple different items.

The main food body maintains structural continuity and consistent shape, presenting different levels of maturity in different slice areas (like time being sliced open).

The image is in vertical 3:4 ratio, with the main subject centered and horizontally expanded, evenly divided into 4-6 segments:

From left to right: Immature → Mature → Overripe → Spoiled

Each segment reflects real changes:

Color changes (green → yellow → black, etc.)
Texture changes (plump → softened → shriveled → decayed)
Feature changes (sprouting, weeping, mold, etc.)

Each stage is accompanied by text descriptions:

Stage name
Appearance characteristics
Internal changes (sugar/starch/moisture changes)
Consumption suggestions (recommended/suitable for cooking/inedible)

Design style:

Minimalist light background (beige)
Highly realistic photography style
Clear dividing lines (sense of time slicing)
Chinese educational layout, Little Red Book style
Appropriate use of icons like ⚠️✔️

Title at the top: "Life of {argument name="food name" default="Garlic"}"

Key requirement: It must be presented as "slices of the same food item changing over time," not a collage of independent individuals.
E-commerce Main Image - Dark Ancient Chinese Style Packaging — output

E-commerce Main Image - Dark Ancient Chinese Style Packaging

松果先森GPT Image 2
{argument name="character" default="Pan Jinlian"}-inspired {argument name="product" default="arsenic"} packaging box design, ancient dark style, {argument name="theme" default="Water Margin"} peripheral cultural and creative product.
YouTube Thumbnail - Social Media Meme Cover — output

YouTube Thumbnail - Social Media Meme Cover

币安小说—— ● ——(IP版)GPT Image 2
Draw a {argument name="platform" default="Douyin"} short video cover. Large title text fills the left half of the screen: "{argument name="title" default="I'm in the Emotion Factory AI creating meme images; laughing so hard colleagues called the police"}". On the right side, the host with an {argument name="expression" default="exaggerated close-up photo laughing to tears"}. In the bottom left, the number of likes is {argument name="likes" default="3.28 million"}. In the bottom right, the hashtags are "# AI Shenanigans # Dying of Laughter."
Profile / Avatar - High-End Cinematic Fashion Portrait — output

Profile / Avatar - High-End Cinematic Fashion Portrait

知仰竹GPT Image 2
{argument name="aspect ratio" default="9:16"} vertical composition, solo female artistic portrait, young East Asian girl, refined features, soft facial lines, natural transparent skin, retaining real texture, quiet and high-end aura, with a touch of detachment and narrative feel. Studio style fused with natural light, soft side lighting, delicate highlights on the face, gentle shadows, overall transparent and non-glaring light, with a slight black mist filter effect, subtle haziness, slight glow, strong sense of airiness. Minimalist and clean background, cream gray, off-white, light khaki, or misty warm gray walls, leaving large areas of negative space, overall clean and breathable composition. Model sitting on the ground or a low platform, one leg naturally bent, one leg relaxed and extended, body slightly leaning forward or tilted, asymmetrical shoulders, head gently tilted, natural and relaxed posture, not over-posed. Expression is calm and restrained, soft gaze, slightly detached, with a touch of thoughtfulness, lips naturally parted or slightly closed, lazy, quiet, and delicate state. Hairstyle is naturally fluffy long hair, slightly messy loose strands, soft hair, with a sense of air and layering, as if just styled but retaining a natural casualness. Makeup is high-end light makeup, Korean-style clear base, soft matte skin glow, natural highlights on the bridge of the nose and cheeks, clean eyebrow shape, elegant but spirited eye makeup, long eyelashes, lip color in low-saturation rose bean paste or milk tea nude pink. Outfit in {argument name="clothing style" default="minimalist high-end style"}: cream-white tight ribbed knit tank top, paired with a loose white shirt or soft knit cardigan, bottom is high-waisted skirt or minimalist shorts, fabric is soft and fits the body without overexposure, presenting natural body lines and artistic feel. The image emphasizes delicate texture, soft tones, a combination of light French and Korean magazine vibes, real photographic feel, cinematic skin tone, rich details, clear layers, restrained composition, high-end aesthetics, fashion editorial portrait, soft cinematic portrait, delicate texture, ultra-high detail, realistic, elegant, exquisite, high-end fashion photography, subtle sexiness, simple composition.
Infographic / Edu Visual - Hand-drawn Infographic Card Prompt — output

Infographic / Edu Visual - Hand-drawn Infographic Card Prompt

阿兰AIGPT Image 2
Create a hand-drawn style infographic card with a 9:16 vertical ratio. The card has a clear theme, the background is beige or off-white with paper texture, and the overall design reflects a simple and friendly hand-drawn aesthetic. At the top of the card, a large red and black contrasting brush cursive font highlights the title to attract the visual focus. The text content is all in Chinese cursive, and the overall layout is divided into 2 to 4 clear sections, each expressing core points with short and refined Chinese phrases. The font maintains the smooth rhythm of cursive script, which is both clear and readable and full of artistic atmosphere. Simple and interesting hand-drawn illustrations or icons, such as characters or symbolic signs, are dotted on the card to enhance visual appeal and trigger readers' thinking and resonance. Pay attention to visual balance in the overall layout, reserve enough blank space to ensure the image is concise and clear, easy to read and understand. The theme is: "{argument name="theme" default="Building an IP is long-term compound interest; stick to setting up your stall every day and keep doing it, there will definitely be results because 99% can't persist."} "
Infographic / Edu Visual - Professional Automotive Technical Infographic Prompt — output

Infographic / Edu Visual - Professional Automotive Technical Infographic Prompt

Nice哥GPT Image 2
Chinese infographic with clear layout, striking large titles, and organized parameter tables, maintaining readability for each module while allowing slight decoration. A 9:16 vertical high-end automotive technical breakdown infographic themed "{argument name="theme" default="Mazda Skyactiv Full Technical Analysis"}", with a black-gray dark background, strong tech feel, and professional car magazine cover-level visuals. In the center is a high-detail 3D perspective breakdown of a {argument name="car model" default="Mazda CX-5"} in Soul Red, showing engines, chassis, suspension, brakes, transmission, and interior in layers. Above is a bold title "{argument name="main title" default="Mazda Skyactiv: Most Detailed Breakdown"}" with brand elements. The layout features various Chinese description modules and parameter cards covering performance, power systems, and safety. The vehicle rendering is photographic-grade with extreme detail in mechanical parts. The style resembles automotive engineering posters or professional promotional infographics, high information density, 8K ultra-sharp, sharp and professional with cinematic lighting.
Profile / Avatar - Marcus Rashford Inter Milan Wallpaper — output

Profile / Avatar - Marcus Rashford Inter Milan Wallpaper

Arnold MadiGPT Image 2
Make an image, a {argument name="player" default="Marcus Rashford"} design for {argument name="team" default="inter milan"}, advanced design level, 9:16, mobile wallpaper, write "{argument name="text" default="Welcome MR14"}"
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 ↗