ONLINEAGENT_OPS 2026.Q3 HOME ARTICLES CRAFT RECORD BLOG MAP HUBS FAQ SEARCH
HOMETHE CRAFTCHEAT SHEETSCHATGPT IMAGE
CHEAT SHEET · OPENAI · TEXT-TO-IMAGE

ChatGPT Image Prompting Cheat Sheet

OpenAI's own prompt structure — scene, subject, details, constraints — plus the prompt rewrite that changes how you iterate.

READ4 min
WORDS732
SECTIONS5
SOURCES3
TYPECHEAT SHEET
CHECKED16 SEP 26

OpenAI does publish a prompting guide for its image models. An earlier version of this sheet said it did not; this one is built from that guide.

TL;DR — THE SHORT VERSION
  • Current model: ChatGPT Images 2.5, released 8 September 2026. In the API it is “gpt-image-2.5-sunburst and gpt-image-2.5-flare”.
  • OpenAI's structure for complex requests: “organize the prompt as scene, subject, details, and constraints, using labeled sections.”
  • Exclusions go in the prompt. OpenAI: “State exclusions such as unwanted text, logos, or watermarks.”
  • Words in the image go in quotes. OpenAI: “Put required wording in quotes and describe its position and typography.”
  • Through the Responses API your prompt is rewritten first, and the rewrite comes back in revised_prompt.
  • Known limits: precise text placement and layout-sensitive compositions.
VENDOR-DOCUMENTED

Every rule on this sheet is quoted from the vendor's own published documentation, linked where it is used.

The formula

Scene + Subject + Details + Constraints — in labelled sections for complex requests

OpenAI, Image prompting guide, read at source 16 Sep 2026: “For complex requests, organize the prompt as scene, subject, details, and constraints, using labeled sections.”

Template:

Scene: [setting, light, time]
Subject: [who or what, and what the image is for]
Details: [style, composition, aspect ratio, exact text in quotes]
Constraints: [what must not change · what to exclude]

Worked example:

Scene: north-facing pottery studio at dusk, window light only.
Subject: documentary photograph of a ceramicist centring clay on a wheel, for a studio poster.
Details: muted earth palette, shallow depth of field, 3:2. A sign on the wall reads "OPEN STUDIO — SATURDAY" in plain sans-serif, top left.
Constraints: no extra text, no logos, no watermark.

Breakdown — what each part does

01

Scene

Where it happens and how it is lit. Set it first so the rest has somewhere to sit.

02

Subject

OpenAI: “Name the subject and intended use, such as a product photograph, advertisement, or diagram.”

03

Details

OpenAI: “Specify the composition, aspect ratio, and important placement constraints.” Any words in the image go here, in quotes.

04

Constraints

What must not change, and what to leave out. For edits, OpenAI says “say “change only X” and list the details to preserve”.

Does it take a negative prompt?

No separate field. Exclusions go inside the prompt.NO

OpenAI, Image prompting guide, read at source 16 Sep 2026: “State exclusions such as unwanted text, logos, or watermarks.”

Keep exclusions specific and short — "no watermark" rather than a paragraph of worries — and put them in the constraints section so they do not compete with the description.

TAKEAWAY

Label the four parts, put any required words in quotes, and write exclusions inside the prompt. There is no separate box.

What not to do

Do not assume the model used your exact words. On the Responses API, OpenAI says the main model “will automatically revise your prompt for improved performance”.
Do not expect exact text placement. OpenAI: “the model can still struggle with precise text placement and clarity”.
Do not expect tight layouts. OpenAI: the model “may have difficulty placing elements precisely in structured or layout-sensitive compositions”.
Do not paraphrase words you need in the image. Quote them, and say where they go.
THE PROMPT REWRITE

When you use the image generation tool in OpenAI's Responses API, “You can access the revised prompt in the revised_prompt field of the image generation call”. If an image does not match your words, read that field before rewriting yours. An earlier version of this sheet also said the chat interface hides the rewrite; no source for that was found, so the claim was removed.

THE PROMPT REWRITE · RESPONSES API
Why an image can miss words you are sure you wrote.
You send your promptScene, subject, details, constraints.
The main model revises itAutomatically, when you use the image generation tool in the Responses API.
The image comes backWith the rewrite in the revised_prompt field.
If it missed, read that field firstBefore rewriting your own prompt.
Reasoning — summarises this sheet’s box on the prompt rewrite, which quotes OpenAI’s documentation. Page checked 16 Sep 2026.

Free or paid? What the free plan allows, who owns the output, and when you need to pay: free vs paid AI image, video and music tools.

Where this model sits among the others: which models take a negative prompt, and what each vendor publishes as its formula.

Putting readable words inside a picture is covered on text inside images.

The checklist

Before you send it:

1 — Scene, subject, details and constraints labelled?
2 — Required words in quotes, with position and typography?
3 — Exclusions stated in the constraints?
4 — On an edit, said "change only X" and listed what stays?
5 — On the API, checked revised_prompt?
SOURCES

OpenAI, Image prompting guide · OpenAI, Image generation guide · OpenAI, Introducing ChatGPT Images 2.5 (read in a browser; OpenAI blocks automated fetches) All read at source on 16 Sep 2026.

Model versions and vendor documentation both move. Re-read the source before relying on a specific number.

Every other sheet in this set: all model cheat sheets.

ABOUTMETHODVERIFYPRIVACYCONTACTINDEXAI PROMPT GENEER · EVERY ARTICLE CARRIES ITS OWN CHECKED DATE