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

Profile / Avatar - Cute Cat Selfie — output

Profile / Avatar - Cute Cat Selfie

Al-ShamusGPT Image 2
a {argument name="cat type" default="cute orange and white cat"}, he looks like hes thinking. taking a selfie inside a {argument name="room lighting" default="dramatically lit room dark room"}. the cat has {argument name="facial features" default="big eyes, a chubby face"}, and a happy expression. the image is a wide-angle shot with sharp focus and high resolution, resulting in a high-definition photograph.
Profile / Avatar - Hyper-Realistic Stoic Portrait — output

Profile / Avatar - Hyper-Realistic Stoic Portrait

KGPT Image 2
A hyper-realistic, cinematic medium close-up portrait of the uploaded person. The subject is positioned with their torso angled slightly forward, but their head is turned to the side, looking off-camera to the left with a deeply contemplative, serious, and stoic expression. One hand is raised, resting gently against the chin and lower lip in a classic "thinking" gesture, fingers softly curled. On the wrist is a {argument name="accessory" default="prominent, luxurious metallic chronograph watch"} with complex dial details. The subject is wearing a {argument name="outfit" default="sleek, dark black long-sleeved shirt or suit jacket"} that blends into the shadows, with metallic cuff accents catching the light. Background: A minimalist, moody, {argument name="background" default="textured charcoal-grey gradient backdrop"}, featuring a soft, faint vertical strip of light on the far left edge. Camera Angle & Photography: Eye-level angle, amazing high-end commercial portrait photography. Lighting, Editing & Effects: Dramatic chiaroscuro side-lighting illuminating the right side of the subject's face while casting deep, rich shadows on the left. The image features a shallow depth of field with sharp focus on the visible eye and the luxury watch. There is a distinct, heavy foreground blur (a hazy, soft white/grey light leak effect) obscuring the very bottom and bottom-left corner of the frame to create atmospheric depth. High-contrast editing, moody cinematic color grading, and a highly polished, premium aesthetic. ar 4:5
Profile / Avatar - Aesthetic Creator Workspace — output

Profile / Avatar - Aesthetic Creator Workspace

Noor 🌸GPT Image 2
Aesthetic AI workspace scene inside an X (Twitter) profile interface, dark theme UI in the background showing a profile named "Noor 🌸" with a verified badge. In the foreground, a stylized semi-realistic digital girl with {argument name="hair style" default="short messy golden-yellow hair"} and soft glowing skin, wearing a {argument name="outfit" default="sleeveless mustard-yellow top"}, sitting at a desk and working on a laptop with the X logo.

Desk setup includes: a black smartphone with X logo, a minimal glass pen holder with pencil, a yellow pen, sticky notes, stacked notebooks, small yellow cube decor, and a {argument name="decor" default="vase with yellow flowers"}. Lighting is soft, cinematic, warm tones with high contrast against the dark UI.

Composition: centered subject, slightly angled view, sharp focus on the girl, blurred background interface. Hyper-detailed, smooth rendering, 3D + illustration hybrid style, trending on ArtStation, ultra clean, professional, cozy creator workspace vibe.
Profile / Avatar - Double Exposure Motion Blur Portrait — output

Profile / Avatar - Double Exposure Motion Blur Portrait

𝗦𝗮𝗻𝗶𝗮GPT Image 2
portrait of a young woman with {argument name="hair color" default="short curly black"} hair and {argument name="skin tone" default="fair"} skin, wearing transparent safety goggles and a {argument name="clothing" default="blue ribbed turtleneck sweater"}, seated in front of a solid azure blue background, double-exposure motion blur effect to the left side of the face, subtle soft reflections on the glasses, cold ambient lighting, high sharpness on facial features with dreamlike blur trail overlaying second face, fashion editorial studio setup, icy color palette, futuristic retro mood.
E-commerce Main Image - Luxury Jewelry Advertisement — output

E-commerce Main Image - Luxury Jewelry Advertisement

Dheepan RatnamGPT Image 2
Create a jewelry advertisement for {argument name="jewelry piece" default="[JEWELRY PIECE]"}, macro sparkle, velvet surface, warm gold light, romantic shadow play, minimal headline, luxury boutique feel, ultra-detailed gem reflections, premium editorial composition.
Social Media Post - Bob Barker Skyscraper Portrait — output

Social Media Post - Bob Barker Skyscraper Portrait

BMXGPT Image 2
{argument name="person" default="Bob Barker"} standing on the top of a {argument name="location" default="skyrise building"} holding a skateboard. He is wearing his {argument name="outfit" default="classic suit from The Price is Right"}.
E-commerce Main Image - Minimalist Tech Accessory Advertisement — output

E-commerce Main Image - Minimalist Tech Accessory Advertisement

Dheepan RatnamGPT Image 2
Generate a tech accessory ad for {argument name="accessory" default="[ACCESSORY]"}, floating product render, magnetic alignment, smooth gradients, sharp spec cards, clean sans-serif typography, Apple-level minimalism, premium digital product launch aesthetic.
Profile / Avatar - Surreal Resin-Split Portrait — output

Profile / Avatar - Surreal Resin-Split Portrait

Zar⭕onGPT Image 2
Ultra-photorealistic 8K RAW, 35mm, f/8, deep focus, no blur, no DOF, no noise, no grain, no haze, no dust, no volumetric light, no soft light, no glow. IMAX stage, 2:3 aspect ratio. Male with my exact face, 181cm 73kg, {argument name="hair style" default="messy dark hair"}, short stubble. Face split: left side — clean skin with {argument name="markings" default="thin amber technical markings (numbers \"6.66\", spiral symbols, hand-drawn)"}; right side — {argument name="skin effect" default="matte black skin covered in thick black resin (glossy, wet-looking, partially dried with stretched glossy strings between skin and fingers)"}. One eye natural dark brown, other faint amber glow (subtle, like light through honey, no beam). Tattoos: small eye on left neck, two horizontal lines on right jaw, tiny cross behind right ear. One mechanical prosthetic hand (black steel with sticky resin residue) raised to chin, fingers pulling a glossy resin string away from right cheek. Clothing: matte black worn jacket, high collar, no hood. Lighting: hard warm amber key from upper left, cool grey fill from lower right, sharp shadows. Color: desaturated grey-black, only amber as accent in resin reflections. Background: solid charcoal grey wall. Clean dry air, no particles. All surfaces sharp.
Comic / Storyboard - 3D Gaming Character Sheet Prompt — output

Comic / Storyboard - 3D Gaming Character Sheet Prompt

Shira WigglesGPT Image 2
A highly detailed 3D gaming character sheet, 
- on the left side a {argument name="character description" default="beautiful female french student"} , head front view + side view, accessory samples, character front view and back view, 
- on the right side details about her: name, age, job, city, size, weight, character description, hobbies, strengths, weaknesses, backstory,
Product Marketing - Futuristic Bionic Hiking Boot Prompt — output

Product Marketing - Futuristic Bionic Hiking Boot Prompt

Ericool 🇲🇾GPT Image 2
Extreme futuristic {argument name="inspiration" default="hedgehog-inspired"} bionic {argument name="item" default="hiking boot"}, fusion of rugged outdoor gear and armored creature design, spiked protective shell structure, layered carbon fiber plates, adaptive grip sole with claw-like traction, subtle glowing energy core, {argument name="color scheme" default="black and bronze luxury finish"}, built for extreme terrain, dramatic low angle, cinematic lighting, high-end outdoor gear advertisement, ultra detailed, 8k
Social Media Post - 3D Animated Scene with Reference Matching — output

Social Media Post - 3D Animated Scene with Reference Matching

NOORGPT Image 2
A high-quality 3D animated scene featuring a {argument name="subject" default="young woman"} (based on the provided reference image, accurate face and identity, realistic skin texture) wearing the exact same outfit/costume as in the reference image, with all clothing details, colors, and textures preserved. She is sitting casually on a {argument name="furniture" default="soft pastel couch"} in a {argument name="room type" default="cozy, aesthetic room"}. Her posture is relaxed and expressive, with a playful, slightly amused facial expression. Next to her is the baby character “Goo Goo Gaga”, recreated exactly the same as in the provided reference image — identical appearance, outfit, proportions, facial expression, and style (no changes at all). Goo Goo Gaga is standing on the couch, playfully interacting with her (pulling her cheek or holding onto her arm), creating a cute and slightly chaotic moment. Environment: warm, cozy pastel-toned room filled with soft cushions, plush toys, and minimal aesthetic decor (colors: soft pink, peach, cream, mint). Lighting: soft cinematic lighting with warm glow, gentle shadows, depth of field, dreamy atmosphere. Style: high-end 3D cartoon (Pixar/Disney style), ultra-smooth rendering, subsurface scattering skin, fluffy fabric textures, highly detailed, clean composition. Mood: cute, playful, wholesome, expressive, slightly chaotic, viral social media aesthetic. Important: use the provided reference images for both characters — keep the woman’s face and outfit accurate, and keep Goo Goo Gaga exactly unchanged from its reference.“8K render, Unreal Engine, Octane render quality”
Profile / Avatar - High-Fidelity Fashion Photography Prompt — output

Profile / Avatar - High-Fidelity Fashion Photography Prompt

Danna R.GPT Image 2
(9:16) Raw high-fidelity photo, eye-level, medium shot, {argument name="camera" default="iPhone 17 Pro sim"}, 35mm, f/4, sharp subject, natural depth, authentic grain. Framing: Subject ~60%, ~2m, centered, mirrored wall + plants, terrazzo floor. Identity Lock: Preserve ALL facial features; natural skin clarity, soft glow, refined highlights, salon hair, bio-fidelity (pores, vellus hair, hydration). Expression: {argument name="expression" default="Confident, direct gaze"}, neutral lips, slight head tilt (~10° left). Hair: Straight center part, slightly lifted, warm highlights. Makeup: Mauve lip, light base, defined lashes. Accessories: Gold charm necklace, black glossy nails. Outfit: {argument name="outfit" default="Black bodysuit + burgundy sequined mini skirt"}, tight fit, high shine, S-curve. Pose: Torso ~20° right, hips forward, leaning on pot, left hand in hair. Mood: Elegant, warm (black, burgundy, terracotta), ~3200K, moderate-high contrast. Environment: Upscale lounge, mirrored wall, terracotta pots, terrazzo floor, warm light.
Product Marketing - Premium Sportswear Campaign Poster Prompt — output

Product Marketing - Premium Sportswear Campaign Poster Prompt

Chase Dimond | Email Marketing Nerd 📧GPT Image 2
Create a premium, highly realistic 1:1 campaign poster for {argument name="brand" default="DIMOND"}, a modern performance sneaker brand. Show one {argument name="item" default="hero sneaker"} as the main focus in a dark studio with a glossy reflective floor, dramatic cinematic lighting, subtle motion energy, and a sleek athletic feel. Add bold, minimal typography with the brand name {argument name="brand" default="DIMOND"} and a short campaign headline. Make it feel like a real high-end sportswear ad, clean composition, sharp detail, realistic materials, modern and polished, cool dark tones with subtle metallic accents, no clutter, no collage.
Profile / Avatar - HD Photo Restoration Prompt — output

Profile / Avatar - HD Photo Restoration Prompt

Jahan ZaibGPT Image 2
Restore this {argument name="subject" default="old photo"} into {argument name="output style" default="professional portrait of DLSR"} - quality colour and detail, using an advanced upscaling algorithm comparable to the results from {argument name="camera model" default="canon EOS R6 II"}. Ensure the restored the image looks natural, retains exact facial features, has great clarity.
Comic / Storyboard - Character Asset Design Card — output

Comic / Storyboard - Character Asset Design Card

骑司ChaseGPT Image 2
Create a character design sheet based on the uploaded image. Design: Character profile poster. Include: 1. Large main portrait 2. Various facial expressions (happy, angry, sleepy, surprised, etc.) 3. Action poses (running, playing) (based on personality) 4. Small object icons 5. Color scheme section 6. Profile section, including name and personality.
E-commerce Main Image - Chinese Traditional Luxury Product Design — output

E-commerce Main Image - Chinese Traditional Luxury Product Design

Xiao YangGPT Image 2
Silk shawl with 'Court Ladies Wearing Floral Headdresses' pattern from the Tang Dynasty, featuring {argument name="pattern design" default="Zhou Fang's court ladies surrounding pattern"}, crabapple floral gold weaving, glossy satin texture, palace luxury style.

Song Dynasty Ru-ware sky-blue glazed tea set, delicate ice-crackle glaze, 'blue as the sky after rain' color, minimalist Song Dynasty style setting, museum-grade still life studio photography.
Product Marketing - McDonald's Advertisement Prompt — output

Product Marketing - McDonald's Advertisement Prompt

SPEEDYAIGPT Image 2
Create a clean, high-quality {argument name="brand" default="McDonald’s"} advertisement. Use a bold red brand color with yellow brand accents. Show {argument name="product" default="a Big Mac, fries, and a drink"} in a realistic, appetizing style. Include the golden arches in the background. Add bold white headline text: “{argument name="headline" default="Better together."}” Include smaller text: “Big Mac + Fries — The classic combo.” Add price and minimal product details at the bottom. Keep the layout simple, balanced, and premium with strong brand consistency.
Infographic / Edu Visual - Dance Choreography Instruction Sheet Prompt — output

Infographic / Edu Visual - Dance Choreography Instruction Sheet Prompt

JohnnGPT Image 2
Dance Sequence Instruction Sheet [VISUAL STYLE] A composition featuring a highly detailed 3D-rendered female dancer. Designed like a professional choreography guide with a technical, diagram-inspired layout. Clean white background, soft studio lighting, and strong contrast to highlight body movement and posture. [GRID LAYOUT] Structured 4×4 panel grid (16 frames total), evenly spaced with thin black divider lines. Each panel is identical in size and clearly numbered from 1 to 16 to show a continuous dance progression. [CHARACTER] Use image1 as the base character. The same female dancer appears consistently across all panels with accurate likeness and proportions. [WARDROBE] The dancer wears a stylish, performance-ready outfit: a well-fitted top paired with a short, flowy skirt. The look should feel modern and visually appealing while still practical for dance movement. Fabric should subtly respond to motion (slight flow and folds), even in grayscale. [PANEL STRUCTURE – EACH FRAME] Top-left: Step number + short dance move title (e.g., “Step 5 – Spin Transition”) Center: Full-body pose capturing a precise moment in the choreography Bottom-left: 3–4 lines of concise instruction describing the move Overlay: Motion arrows and directional guides illustrating how the dancer transitions [MOTION INDICATORS] Incorporate curved arrows for fluid motion, straight arrows for directional steps, and circular indicators for spins or turns. Emphasize rhythm, weight shifts, and body isolation. [RENDER QUALITY] High-detail sculpted 3D style with smooth grayscale shading, subtle shadows, and clean linework. Maintain a polished, concept-art level finish with clarity in every pose. [RESTRICTIONS] No color, no background scenery, no extra characters, no visual clutter, only the dancer and instructional elements.
Product Marketing - Streetwear Campaign Poster Prompt — output

Product Marketing - Streetwear Campaign Poster Prompt

DaniloGPT Image 2
Create a premium, highly realistic 1:1 campaign poster for {argument name="brand" default="NOIR"}, a modern streetwear brand. Show one {argument name="product" default="hero oversized hoodie"} as the main focus against a gritty urban backdrop with wet concrete floors, dramatic low lighting, subtle smoke in the air and a raw street energy. Add bold minimal typography with the brand name NOIR and a short campaign headline like "{argument name="headline" default="Wear the Dark"}." Make it feel like a real high-end streetwear editorial, sharp detail, realistic fabric textures, modern and edgy, deep black tones with subtle grey accents, no clutter, no collage.
Infographic / Edu Visual - Minimalist Educational Infographic Template — output

Infographic / Edu Visual - Minimalist Educational Infographic Template

知识分享官GPT Image 2
A clean educational infographic poster explaining "{argument name="topic" default="Topic"}".

[Overall Style]
Modern minimalist UI style, background in soft light colors (e.g., cream #FAF7F2 / light gray-blue), restrained and comfortable color palette suitable for long reading sessions.

[Core Requirements (Key)]
Naturally organize content modules based on the information structure of the "topic". Do not force a fixed number or order of modules; prioritize clear logical information over formal symmetry.

[Layout (Adaptive)]
- Use grid layout (auto-select 2 columns / 3 columns / irregular distribution)
- Card count adjusts based on content (usually 5–9)
- High information density modules can be enlarged (higher visual weight)
- Simple modules can be shrunk or merged

[Card Design]
- White cards (#FFFFFF)
- Rounded corners + subtle shadows (soft layering)
- Maintain uniform spacing and alignment

[Each Information Module Includes]
- Simple illustrations (unified style)
- Clear headings (strong hierarchy)
- 1–3 core explanatory sentences (avoid wordiness)
- Examples / comparisons / summaries provided where necessary

[Content Organization Principles (Emphasis)]
Auto-select appropriate structure based on theme, e.g.:
- Concept type → definition + principle + characteristics + example
- Contrast type → A vs B (comparative structure)
- Process type → steps / flowcharts
- System type → components + relationships
- Skill type → methods + tips + common mistakes

[Visual Hierarchy]
- Title > Module Title > Main Text > Supporting Information
- Important info can be highlighted with color or icons

[Color Suggestions]
- Primary color: Choose based on theme (Tech=Blue, Learning=Green, Warning=Orange)
- Secondary colors: 1–2 types suffice
- Avoid high saturation and flashiness

[Style Requirements]
- Generous negative space, strong sense of "breathability"
- Unified icons (linear or flat)
- High readability as priority
- Clear educational orientation

[Extra Optimization (Optional)]
- Can include: comparison blocks / process arrows / structure diagrams
- Can have a "Core Summary" module as a visual finale.
Social Media Post - Location-Specific Japanese Photo Album — output

Social Media Post - Location-Specific Japanese Photo Album

小森映像GPT Image 2
Create a Japanese photography collection showing a woman at coordinates {argument name="coordinates" default="34.66565030001616, 135.43231849672236"}, with visuals matching the current local atmosphere and weather. Integrate the specified character into the scene to make it look as if they are sightseeing at that location.
Social Media Post - Anime Character Noodle Delivery — output

Social Media Post - Anime Character Noodle Delivery

水木易GPT Image 2
Generate {argument name="character" default="Annie Leonhart from 'Attack on Titan'"}. Use the {argument name="style" default="original 'Attack on Titan' anime style"}. Annie is wearing her classic outfit from the series, facing the camera, slightly bowing her head with a shy expression, eyes looking down, not daring to look at the viewer. She is {argument name="action" default="holding a bowl of steaming noodles with both hands and handing them to the viewer"}. The noodles and rising steam are clearly visible in the bowl. Close-up composition, clear character, simple background.
YouTube Thumbnail - Anachronistic Beauty Tutorial — output

YouTube Thumbnail - Anachronistic Beauty Tutorial

Mr.pineconeGPT Image 2
{argument name="character" default="Pan Jinlian"} posting a beauty tutorial on {argument name="platform" default="Bilibili"} titled "{argument name="topic" default="How to Conceal Blemishes Using Ancient Methods"}," with bullet comments saying "Sister-in-law's technique is amazing!"
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 ↗