Turn a complex topic into a clean whiteboard lesson with diagrams, arrows, color-coded sections, and no presenter in the frame.
Create a professor-style whiteboard explainer that teaches [CORE CONCEPT] visually. Divide the board into [NUMBER] clear sections and use concise labels, diagrams, arrows, boxes, and color coding to show how the ideas connect. Use a clean hand-drawn marker style with a logical left-to-right reading order. Do not show a person. Lesson content: [PASTE THE EXACT CONTENT TO EXPLAIN].
Create a black-and-white ticket-style information graphic with editorial hierarchy, geometric zones, precise spacing, and bilingual typography.
Design a premium black-and-white ticket-style infographic about [TOPIC]. Use a strict editorial grid, 3–4 distinct type sizes, and a headline at least three times larger than the supporting copy. Divide the composition into balanced geometric zones with generous spacing, thin rules, ticket notches, a barcode, serial numbers, and restrained utility symbols. Keep every text block legible and preserve strong contrast. Orientation: [PORTRAIT OR LANDSCAPE]. Exact copy: [PASTE FINAL HEADLINE AND SUPPORTING TEXT].
Stage a believable macOS browser screenshot where ChatGPT draws an ASCII dog while terminal windows and desktop clutter remain visible behind it.
a screenshot of chatgpt, in a browser, in macosx. the user types "draw me a dog" chatgpt draws an ascii dog the front window is chatgpt, but the desktop is quite messy with lots of random windows open (e.g. a terminal). they're all in the background
Build a museum-like editorial collage that combines diagrams, manuscripts, interfaces, natural specimens, art history, and multilingual visual culture.
I am creating a magazine page with the theme of "visual polyglot". The title in the center of the image should be "Create Everything at Once". Create a piece of art celebrating visual creations, not limited to beautiful photographs but also across the full breadth of human visual culture and natural visual elements. There should be curated collage representing the diverse distribution: scientific diagrams, the periodic table, the solar system, medieval manuscript pages, botanical illustrations, anatomical drawings, old maps, climate charts, engineering schematics, transit signage, multilingual text, comic panels, UI screenshots, a camera photo, a butterfly specimen, pie charts, architectural blueprints, and façade drawings. The text frames the model as fluent across languages, notation systems, interfaces, cultural forms, and visual conventions—able to move from utility to beauty, from document understanding to artistic generation. Also feature artistic elements like pixel art, styles, history, sculpture, nature, photography, paintings, and all art forms. These are just examples, I need you to actively think about other elements / styles that may fit in a good design that's not limited to these concepts. The overall effect is that of a premium research announcement or museum-style manifesto: elegant, ambitious, and designed to argue that image intelligence should be trained on the whole visual world, not just polished aesthetics. Use an unstructured, creative and artistic layout, such as but not limited to fan out, avoid grid-like layouts. Portrait 4:5 aspect ratio. Don't add any content text beside the "Create Everything at Once" title. Text as part of the art is okay. Avoid a beige tint of the overall style, since we want vibrant elements to be vibrant.
Generate a phone photo of a pencil-written essay on lined paper, including human variation, uneven baselines, paper texture, and a small coffee stain.
a photorealistic, taken by phone photo of a handwritten essay in pencil, bold but elegant handwriting, but messy and somewhat uneven, on an 8.5x11 piece of lined paper, about the history of baseball in toronto. make sure there is variance in the writing in a very human way. give it a slight coffee stain on the top right corner
Direct a dramatic Japanese shonen manga page about a magical quill, with purposeful panel pacing, Japanese lettering, and the look of printed paper.
Make a sample page of a colorized Japanese shonen adventure manga. The page should vividly depict our main character found a magical quill. The name of the quill is called the Quill of GPT Image. Make it dramatic. The magical quill has strong power sealed inside it.
Additional instructions: Aspect ratio: Portrait 1440x2560. The pen should have an OpenAI logo on it. The language throughout the manga should be Japanese. Think carefully first to make this a good story with good split of manga panels. The page should appear as a photo of a physical page, not a digital page.
Transform an uploaded portrait into a diagram-first personal color analysis that compares flattering clothing colors with minimal explanatory text.
Using this portrait, create a diagram-first personal color analysis. Show which clothing colors suit the subject through visual comparison. Keep text minimal and avoid paragraphs.
Compose a monochrome Zen garden entirely from ASCII characters, balancing rocks, raked sand, bonsai trees, mountains, and a small moon.
A monochromatic ASCII art desktop background, featuring a Zen garden made entirely of ASCII characters. The landscape should include: A central rock formation using @, #, and * characters; Carefully raked sand patterns using -, =, and ~ characters; Small ASCII bonsai trees using |, /, \, and Y characters; A distant mountain range made with ^ and /\ characters; A simple ASCII moon or sun in the corner; Everything should be done in pure ASCII text art style, completely monochromatic, suitable as a desktop wallpaper. The overall composition should feel peaceful, balanced and show technical artistry in ASCII representation.
Test multilingual rendering with one central Chinese character surrounded by Japanese, Arabic, Devanagari, Korean, Thai, and Hebrew translations.
Create a visually striking image that demonstrates multilingual text rendering capabilities. The image should feature: a central, large Chinese character (choose "美" meaning "beauty") rendered in an elegant calligraphic style. Surrounding this central character, arrange smaller text in multiple scripts: Japanese hiragana and katakana (spell out "うつくしい" - "beautiful"), Arabic script (write "جميل" - "beautiful"), Devanagari (write "सुंदर" - "beautiful"), Korean Hangul (write "아름다운" - "beautiful"), Thai script (write "สวยงาม" - "beautiful"), Hebrew (write "יָפֶה" - "beautiful"). Each script should be clearly legible and rendered in its traditional style, with appropriate spacing and proportions. Use a clean, modern layout with subtle color accoding to writing system: warm tones for CJK, cool blues for Middle Eastern scripts, earth tones for South Asian scripts. The background should be a soft, neutral color that makes all text pop. Include thin decorative lines connecting the various scripts to create a visual flow. Ensure the typography is crisp and the text is perfectly centered and balanced.
Create a photorealistic magazine cover with a dominant WOLF masthead, issue metadata, barcode, supporting cover line, and a central wolf portrait.
A photorealistic magazine cover. The magazine is called "WOLF" in huge bold text. Include a barcode, issue number "Issue 1: The Alpha", and a small text area that says "The science behind the howl". The main image on the cover is a wolf.
Render a quiet black-and-white Japanese street scene with two speakers, a thinking cat, storefront signage, captions, and carefully placed dialogue.
A black and white manga panel of a quiet scene from a Japanese town. The caption says "静かな朝" (Shizuka na asa / Quiet morning). Two young women chat on the sidewalk outside a corner store. One says "今日もいい天気ね" (Kyou mo ii tenki ne / Nice weather today again), and the other responds "うん、散歩日和だね" (Un, sanpo biyori da ne / Yeah, perfect for a walk). A cat sits nearby, thinking "また人間たちが話している" (Mata ningen-tachi ga hanashite iru / The humans are talking again). The store sign reads 角の本屋 (Kado no hon'ya / Corner Bookstore) and a small poster says 新刊入荷中 (Shinkan nyuuka chuu / New arrivals in stock). The scene is detailed in classic manga style with careful linework and N-screen tones.
Frame a candid Marrakech souk photograph around an artisan arranging spices, with weathered hands, late-afternoon shadows, textiles, and market depth.
A candid travel photography shot in the streets of Marrakech, Morocco. A local artisan is photographed mid-action while arranging colorful spices in a traditional souk. The shot is taken from a slightly elevated angle, showing the intricate patterns of the spice mounds and the artisan's weathered hands. The image should have the authentic feel of documentary street photography, with natural lighting casting long afternoon shadows. Include subtle details like worn cobblestones, the edge of a colorful textile, and out-of-focus passersby to add depth and authenticity.
Create a raw nightlife portrait with direct flash, slightly overexposed skin, motion, neon bar details, visible grain, and an unguarded expression.
Night flash photography portrait, like Nan Goldin shot in a 90s dive bar. A young woman in a leather jacket, mid-laugh, cigarette in hand. Hard flash, red lips, smudged eyeliner, slightly overexposed skin. A half-drunk beer on the table, neon signs in the background. Raw and honest.
Blend a high-fashion floral garment, formal garden, and cosmic sky into a surreal editorial image with warm sunlight and cool moonlight.
A high fashion editorial photograph. The model is wearing an avant-garde outfit made entirely of fresh flowers and leaves. The setting is a surreal landscape that blends a formal garden with a cosmic space environment. Stars and nebulas are visible in the sky above perfectly manicured hedges. The model's pose is dramatic and otherworldly. The lighting is a mix of golden hour sunlight and cool moonlight, creating an ethereal effect. The image should have the quality and artistic vision of a top fashion magazine spread.
Build a wide golden-hour floating-market panorama with a foreground food vendor, layered boats, canal activity, temple spires, mist, and documentary detail.
A sweeping cinematic panorama of a traditional Thai floating market at golden hour, where wooden boats laden with tropical fruits and flowers create winding pathways on the canal. In the foreground, a weathered vendor in a wide-brimmed straw hat ladles steaming boat noodles into a bowl, surrounded by herbs and spices. The middle ground shows a colorful mosaic of market activity, while the background reveals ancient temple spires rising through morning mist. The entire scene should feel authentic and alive, captured in the style of documentary travel photography with shallow depth of field, natural color grading, and subtle film grain.
Illustrate a bear family preparing a lantern-lit burrow for winter with collected berries, pinecones, expressive characters, and soft watercolor texture.
A charming children's storybook illustration of a small bear family preparing for winter. The cozy scene shows a parent bear and two young cubs in a warm, lantern-lit burrow, surrounded by collected pinecones and berries. Rendered in the warm, detailed style of classic picture books with soft watercolors and expressive characters.
Use an uploaded portrait to create a friendly Fukuwarai-inspired caricature with recognizable features, clean linework, watercolor washes, and gentle exaggeration.
A Japanese-style caricature illustration of a person, exaggerating their most distinctive features in the traditional Fukuwarai style. The illustration should be warm and humorous, capturing their personality through exaggerated but friendly features. Use clean line art with gentle watercolor washes and a warm, inviting color palette.
Extract five dominant colors from an uploaded portrait and arrange them as a clean palette card with hex values, percentages, and complementary combinations.
Analyze the colors in this portrait photo and create a professional color palette card. Extract the 5 dominant colors, show each as a color swatch with its hex code and percentage presence, and suggest 3 complementary color combinations that would work well with this palette. Present it as a clean design asset.
Visualize Cantor’s diagonal argument with a hypothetical list of decimals, a highlighted diagonal, changed digits, and the newly constructed number.
Create a clear, mathematically accurate visualization of Cantor's diagonal argument proving that real numbers are uncountable. Show a hypothetical complete list of real numbers between 0 and 1, with a diagonal highlighted in red. Then show how to construct a new number by changing each digit along the diagonal, demonstrating it can't appear anywhere in the list.
Name the world, focal subject, action, and the details that distinguish it.
02
Composition
Set framing, camera angle, hierarchy, and where negative space should remain.
03
Materials & light
Describe surfaces, texture, named lighting, and the mood that light should create.
04
Text & constraints
Quote exact words, assign their position, and state what must not change or appear.
Before you generate
Questions, answered.
What makes a good GPT Image 2 prompt?
A useful prompt names the subject, setting, composition, materials, lighting, required text, and constraints. Treat it like a concise creative brief rather than a bag of style keywords.
Can I copy and edit these prompts?
Yes. Copy a prompt, replace the variables that matter to your project, or open the template in the generator and refine it before spending credits.
Do image-to-image prompts need a reference photo?
Yes. Templates marked Image edit need at least one uploaded reference. Use images you own or have permission to process.
Is the first GPT Image 2 generation free?
New accounts receive enough starter credits for at least one 1024px text-to-image generation. Higher resolutions and image edits can require a paid plan or more credits.
GPT Image 2 is a trademark of OpenAI. This independent service is not affiliated with, endorsed by, or sponsored by OpenAI. Source labels identify where a prompt direction originated; they do not imply endorsement or guaranteed reproduction.