Prompt Library
Every GPT Image 2.5 prompt here is printed in full beside the picture it actually produced, with the model, quality and size it ran at. Short on purpose — not nine thousand you have to sift through.
23 prompts · each one with the image it made
Nothing to upload
The prompt is the only input. Copy one, change a noun, run it in text to image.
Think · Standard · 1K · 2:3Get a portrait that does not look retouched
Names skin texture and worn materials explicitly, then bans retouching outright.
Nothing to bring6 cr
Think · Standard · 1K · 2:3Turn a process you half-understand into a diagram
Names a real object and asks for the flow. The model supplies the internals.
Nothing to bring6 cr
Think · Standard · 1K · 2:3Put an exact tagline in an ad and have it spelled right
Quotes the copy, pins the repeat count to one, and bans stray text and logos.
Nothing to bring6 cr
Think · Standard · 1K · 2:3Get four logo options on a genuinely transparent background
Asks for alpha in the prompt and the parameter, and bans the painted checkerboard.
Nothing to bring24 cr
Think · Standard · 1K · 2:3Set a scene on a specific date in a specific place
A named place and an exact date do the work a paragraph of period description would.
Nothing to bring6 cr
Think · Standard · 1K · 2:3Turn a story into a four-panel comic
One numbered line per panel, each describing a single visible beat.
Nothing to bring6 cr
Think · Standard · 1K · 2:3Mock up an app screen that looks shipped, not designed
Describes a product that already exists, listing real screen regions rather than a visual mood.
Nothing to bring6 cr
Think · HD · 1K · 3:2Make a classroom diagram with the labels you specify
Names the audience, the objective and every required label, then runs at HD for the small text.
Nothing to bring24 cr
Think · HD · 1K · 16:9Build a pitch-deck slide with your real numbers on it
Supplies the real figures, labels and footnotes so the model lays out data instead of inventing it.
Nothing to bring24 cr
Think · Standard · 1K · 2:3Design a character you can reuse on every page
Builds a plain-background character reference so later scenes have something to stay consistent with.
Nothing to bring6 cr
Think · Standard · 1K · 2:3Design a card with the greeting spelled exactly right
Writes the scene as an emotional premise and fences the card text with a verbatim-only instruction.
Nothing to bring6 cr
Think · Standard · 1K · 2:3Mock up a product in retail packaging
Describes materials, packaging and print clarity, with the packaging copy fixed verbatim.
Nothing to bring6 cr
Start from a picture you have
Each of these shows the before and the after, because an edit shown only as its output tells you nothing about what the edit did. Run one in image to image.
- Think · HD · 1K · 2:3

Input 
Result Translate the text in an image without moving the layout
Fourteen words. Half of them exist to stop the model redrawing the design.
Bring an image28 cr - Think · Standard · 1K · 2:3

Input 
Result Borrow one image's style and draw something else with it
Assigns the reference a single role — style — then describes the new subject separately.
Bring an image10 cr - Think · Standard · 1K · 2:3

Input 
Result Change what someone is wearing without changing their face
Nine preservation clauses and nine prohibitions, because each one closes a known drift.
Bring an image10 cr - Think · Standard · 1K · 2:3

Input 
Result Put something from one photo into another
Numbers both inputs, names the element and its destination, then forbids everything else.
Bring an image10 cr - Think · Standard · 1K · 2:3

Input 
Result Cut a product out onto real transparency
Isolates the product on real alpha, and names the painted checkerboard as forbidden.
Bring an image10 cr - Think · Standard · 1K · 2:3

Input 
Result Remove one thing and leave everything else alone
Names the object and its location precisely, then closes the door on everything else.
Bring an image10 cr - Think · Standard · 1K · 2:3

Input 
Result Put a person into a completely different scene
Rebuilds the whole scene around a preserved face, and refuses cinematic grading three times.
Bring an image10 cr - Think · Standard · 1K · 2:3

Input 
Result Put your product on a billboard, then change the weather
A two-turn workflow: build the scene, then change one condition in five words.
Bring an image10 cr - Think · Standard · 1K · 3:2

Input 
Result Swap one piece of furniture in a real room photo
A capitalised ONLY plus a list of photographic properties that must survive the swap.
Bring an image10 cr - Think · Standard · 1K · 2:3

Input 
Result Draw the next page without the character changing
A new scene with the character constraints restated verbatim from the reference prompt.
Bring an image10 cr
Start from a drawing
The sketch owns the geometry and the prompt owns the materials. Run it in sketch to image.
How to use one of these
Taking a whole prompt and changing the subject works, and it is what most people do first. Taking one clause works better, and it transfers to subjects nothing like the original.
Pick the job, not the picture
Every card is named after a task, not a genre. Find the one whose job matches yours — the subject in the example does not matter, and swapping it is the easy part.
Steal the constraint clauses
The lines worth copying verbatim are the ones that forbid something: "no extra text", "do not change anything else", "no checkerboard". Those are what most people write worst and they transfer to any subject.
Match the settings, or know why you did not
Every card carries the model, quality and size the example ran at. A diagram at Draft is a diagram whose labels have gone soft — the settings are part of the prompt.
None of these is your idea? The prompt generator writes one from your own words — and hands you the settings to run it at.
Free to copy, free to run once
Every prompt is printed at full length, exactly as it was run — nothing truncated, nothing paraphrased, no watermark over the result. Copying costs nothing and needs no account. Only an image we actually render spends a credit.
Free here, no account
- Reading and copying every prompt, in full
- The settings each one was published at
- Your first image — Standard, 1K, no card
Costs credits
- HD and above, 2K and 4K
- Sunburst, the quality model
- Batches, and the 3:1 and 1:3 wide frames
Copy as many as you like, today, without telling us who you are.
Where these came from
The three largest prompt collections on the web hold about nine thousand entries between them, and almost all of it is GPT Image 2 material published under GPT Image 2.5 headings — because none of them records which model made which picture. We record it, so here is the tally, counted from the library itself every time this page renders.
- Published by OpenAI in the 2.5 prompting guide
- 23/23
- Published by somebody else, credited on the page
- 0/23
- Generated here
- 0/23
- Made on a named GPT Image 2.5 model
- 23/23
- Editing prompts shown with their input image
- 11/23
All 23 carry a source link and the model that produced them. Where a published example used a size we do not currently offer, the template says so rather than quietly resolving to a different frame.
Prompt library questions
Where these prompts came from, what the settings mean, and what running one costs
Are these GPT Image 2.5 prompts free to copy?
Why are there only a couple of dozen?
Were these images actually made with GPT Image 2.5?
Why does every prompt list a quality and a size?
Flare or Sunburst — does it matter which?
Why do the editing prompts show two pictures?
Why does the rest of my image change when I only asked for one edit?
What does running one of these cost?
Take one and run it.
Copying needs no account and nothing here is gated, truncated or watermarked. Your first image is on us — Standard, 1K, no card.
Written and maintained by Andy SwiftPublished Last updated

