519 GPT Image Prompts

DALL-E is OpenAI's original text-to-image line, now largely superseded by OpenAI's newer GPT Image models. It popularized mainstream text-to-image, and its lineage now lives on as the GPT Image models tightly integrated with ChatGPT.

Browse the prompts

Popular
Hyper-realistic 8K portrait photograph, shot on DSLR with 50mm lens, natural depth of field and razor-sharp focus. Full-body mugshot-style composition mimicking vintage police booking photo aesthetic.

{{subject-description}} leaning against wall with one knee bent, sharp jawline, intense eyes, confident slightly smug smirk. Neat groomed hair. Wearing tailored suit jacket open with no shirt underneath, slightly loosened dark tie matching jacket. Holding single shiny dark patent leather high-heeled shoe in right hand.

Mugshot identification board visible showing {{character-name}} and date 17/5/62.

Background: naturally blurred bokeh, slightly gritty studio wall texture with vertical height chart markings from 2'0" to 6'6". Desaturated, slightly sepia-toned archival photograph aesthetic. Strong overhead or frontal lighting creating dramatic shadows emphasizing height chart lines. Clean,

Hyper-Realistic Mugshot Portrait Generator

Generates vintage police booking photo-style portraits in 8K hyper-realistic quality, shot with DSLR aesthetic and height chart backgrounds. Runs on Midjourney, Flux, and Nano Banana.

864
{{subject}} with illustrated googly eyes and stick-figure arms, shown in an exaggerated comedic action, playful cartoon illustration with bold outlines, vibrant colors, expressive character design, high energy pose, whimsical humor --ar 16:9 --v 6 --style raw --no realistic details, photorealism

Googly Eyes Cartoon Character Generator

Generates playful cartoon illustrations that add googly eyes and stick hands to any subject performing exaggerated comedic actions. Runs on Midjourney, Flux, and other AI image generators.

275
{{building-type}} in {{setting}}, architectural style of {{reference-style}} --ar 16:9

Architectural Design Concept Image Generator

Generates architectural visualization images in specified styles for Midjourney, Flux, and other AI image generators. Produces building renders by combining structure type, environment, and architectural reference style.

148
Photorealistic architectural rendering of a contemporary sustainable high-rise tower featuring offset horizontal floor slabs with strategic overhangs for passive climate response. Design includes deep planted balconies extending from each level, integrated solar shading fins, and ventilation voids for passive cooling. {{climate-strategy}} The tower exhibits clean modernist lines with visible environmental systems integration, floor-to-ceiling glazing with low-e coating, rainwater harvesting channels, and photovoltaic panel integration on south-facing surfaces. Golden hour lighting, professional architectural photography style, ultra-sharp focus, 8K resolution --ar 4:5

Climate Responsive Green Tower Rendering

Generates photorealistic architectural renders of sustainable high-rise towers with offset floor slabs, planted balconies, solar shading fins, and passive cooling voids. Runs on Midjourney, Flux, and other AI image generators.

145
Exploded axonometric architectural diagram of a contemporary {{building-type}}, separated into eight vertical layers with wall panels fanned outward, true axonometric projection with no perspective, all elements aligned to a single vertical axis, consistent exploded spacing, clean technical linework, no photoreal rendering or textures. Layers from bottom to top: foundation and site platform with pier footings or shallow pads and raised platform plinth and entry steps, structural skeleton with primary columns and ring beams and bracing frames and cantilever supports, interior core and stair volume with service core and minimal built-ins for scale, ground floor plate with structural deck and edge beams and terrace connection, facade envelope panels with large sliding glass panels and solid insulated wall panels exploded outward symmetrically left and right with optional sun-shading screens

Exploded Axonometric Architecture Diagram Generator

Generates exploded axonometric architectural diagrams that separate building layers - foundation, structure, envelope, floors, and roof - into clean vertical assemblies with CAD-quality linework. Runs on Midjourney, Flux, and other AI image generators.

92
Ultra-realistic architectural render of a diagonal terraced green skyscraper. Cascading garden platforms wrap the tower in a dramatic spiral, each deep terrace slab filled with visible soil depth and structural honesty. Exposed mega-frame columns and beams support the heavy planted platforms, showing the engineering required for mature vegetation. Water management channels and drainage systems are visible as integrated architectural elements. {{vegetation-palette}} creating lush vertical landscapes with varied textures and seasonal color. Sharp architectural photography aesthetic with precise material definition, accurate shadow casting, and photorealistic vegetation rendering. Daylight with partly cloudy sky emphasizing depth and structural drama. {{camera-angle}} --ar 16:9 --v 6 --style raw --no people, cars, distortion

Terraced Green Tower Architectural Render Prompt

Generates ultra-realistic diagonal terraced skyscraper renders with cascading garden platforms, exposed structural systems, and integrated water management for Midjourney, Flux, and similar image models.

91

What are GPT image prompts?

GPT image prompts are engineered instructions that already work, written and tested for GPT Image. These are not one-line questions. Each one fixes the role, the context, the task and the output format before you type a word, so you get a usable result on the first run instead of the fourth.

They cover the work that actually fills a week: research, briefs, copy, content, analysis, reporting, planning and outreach. Open a card to see the full prompt and the output it returns.

Popular on this page right now: "Hyper-Realistic Mugshot Portrait Generator", "Googly Eyes Cartoon Character Generator", "Cinematic Portrait Photography Generator".

519 on this page. Free to read, free to copy.

Why these prompts beat writing your own

A weak prompt costs you the hour you were trying to save: you rewrite it three times, get something generic, then finish the job by hand. An engineered prompt front-loads that thinking once.

That means first drafts you can send, analysis you can act on, and the repetitive work handed off, so the time goes into judgement instead of typing.

Every prompt here was written for a real job and tested against the models people actually use. Nothing scraped from a thread.

How to use these prompts in GPT Image

Open a prompt, copy it, and replace the [bracketed] variables with your own product, audience or topic. The structure around them stays as is. That structure is the part doing the work.

Paste it into GPT Image and run. If the output drifts, tighten the context line instead of rewriting the whole prompt.

No account needed to copy one. No setup, no extension, nothing to install.

Do these prompts only work with GPT Image?

They are tuned for GPT Image, but the skeleton of role, context, task and format carries over to any capable model. Swap model-specific settings like tone or length when you move.

Are these AI prompts free to use?

A big part of the library is free: open a prompt, copy it, use it. Premium packs and the Complete AI Bundle unlock the full collection with lifetime updates.

How do I adapt these prompts to my use case?

Start with the [variables]: niche, audience, constraints. If the result still misses, add one example of the output you want. A single good example beats three extra instructions.

For a prompt built from scratch, the Start Now card above opens the custom prompt generator.

Related resources

Get smarter on AI every week

One email a week with the best new prompts, tools, and model updates. Unsubscribe anytime.

Join 100,000+ subscribers. One email a week, real prompts, tools, and model updates. Unsubscribe anytime.

How to use GPT Image

For new work, use OpenAI's current GPT Image models rather than the retired DALL-E API. In ChatGPT, describe the image conversationally and iterate. Through the Images API, choose the model, size, and quality tier, and migrate any old DALL-E calls to GPT Image.

Best for

Conversational image generation inside ChatGPT. Quick concept art and illustration from natural-language prompts. Inpainting and editing in its later versions.

Pricing

The DALL-E API is retired. Its successor GPT Image API runs from under a cent to about $0.25 per image by quality and size, and ChatGPT image generation is included in the $20/mo Plus plan with limits.