Good ChatGPT image prompts go in a set order: scene, subject, key details, constraints, plus what the image is for. That is the structure OpenAI recommends in its image generation prompting guide, written for its gpt-image-2 model: background or scene first, then the subject, then the details that matter, then the rules, with the intended use (an ad, a UI mockup, an infographic) stated up front.

Below are OpenAI’s prompting rules in plain terms, the official example prompts quoted word for word, and what OpenAI says about using images on each ChatGPT plan.

On this page

How to create and edit images in ChatGPT

According to OpenAI’s help article Images in ChatGPT:

  1. To create an image, describe it in any chat, or select More, then Images, and enter a prompt.
  2. To edit an image, select one ChatGPT made or upload your own, then describe the change.
  3. To change only one area, use the selection tool to highlight it, then describe the edit. OpenAI notes that “highlights are not always precise, and edits may extend beyond the area you selected.”
  4. To change the shape, use the aspect ratio picker or write the ratio in your prompt.

ChatGPT Images can add text, add details and make the background transparent. Image generation “may take a few minutes”, and you can keep using ChatGPT while it works. Everything you create is saved under Images on web and mobile.

OpenAI’s rules for image prompts

From the prompting guide:

  • Structure and goal. Write “background/scene → subject → key details → constraints” and include the intended use. For complex requests, use short labeled sections or line breaks.
  • Any format works. Short prompts, paragraphs, JSON-like structures and tag lists “can all work well as long as the intent and constraints are clear.”
  • Photorealism. Include the word “photorealistic”. Phrases like “real photograph” or “iPhone photo” also help, but OpenAI says detailed camera specs “may be interpreted loosely”.
  • Composition. Name framing, angle and lighting, and placement when layout matters, such as “logo top-right”.
  • People in scenes. Describe scale, body framing, gaze and what their hands are doing, for example “full body visible, feet included”.
  • Change versus preserve. For edits, write “change only X” plus “keep everything else the same”, and repeat the preserve list on each iteration.
  • Text in images. Put the exact words in quotes or ALL CAPS and give font, size, color and placement. Spell tricky brand names letter by letter.
  • Several input images. Refer to each by number and say how they interact, for example “apply Image 2’s style to Image 1”.
  • Iterate. Start with a clean base prompt, then make single changes like “make lighting warmer”.

Infographics and diagrams

OpenAI’s infographic example:

Create a detailed Infographic of the functioning and flow of an automatic coffee machine like a Jura. 
From bean basket, to grinding, to scale, water tank, boiler, etc. 
I'd like to understand technically and visually the flow.

Listing: coffee machine infographic. To localize it afterwards, OpenAI uses:

Translate the text in the infographic to Spanish. Do not change any other aspect of the image.

Listing: translate infographic text into Spanish.

For classroom visuals, OpenAI recommends prompting “like an instructional design brief”: audience, objective, required labels and what to leave out.

Create a simple biology diagram titled "Cellular Respiration at a Glance" for high school students.

Show how glucose turns into energy inside a cell. Include glycolysis, the Krebs cycle, and the electron transport chain.
Use arrows to connect the steps, and label the main molecules: glucose, pyruvate, ATP, NADH, FADH2, CO2, O2, and H2O.
Make it look like a clean classroom handout or slide, with a white background, simple icons, clear labels, and easy-to-read text.

Avoid tiny text, extra decoration, or anything that makes the diagram hard to understand.

Listing: cellular respiration diagram.

Photorealistic photos

OpenAI’s advice: prompt “as if a real photo is being captured in the moment”, ask for real texture, and avoid words that suggest studio polish.

Create a photorealistic candid photograph of an elderly sailor standing on a small fishing boat. 
He has weathered skin with visible wrinkles, pores, and sun texture, and a few faded traditional sailor tattoos on his arms. 
He is calmly adjusting a net while his dog sits nearby on the deck. Shot like a 35mm film photograph, medium close-up at eye level, using a 50mm lens. 
Soft coastal daylight, shallow depth of field, subtle film grain, natural color balance. 
The image should feel honest and unposed, with real skin texture, worn materials, and everyday detail. No glamorization, no heavy retouching.

Listing: candid photorealistic sailor photo.

Logos

OpenAI says strong logos come from “clear brand constraints and simplicity”:

Create an original, non-infringing logo for a company called Field & Flour, a local bakery. 
The logo should feel warm, simple, and timeless. Use clean, vector-like shapes, a strong silhouette, and balanced negative space. 
Favor simplicity over detail so it reads clearly at small and large sizes. Flat design, minimal strokes, no gradients unless essential. 
Plain background. Deliver a single centered logo with generous padding. No watermark.

Listing: bakery logo.

Comics and UI mockups

For comics, OpenAI recommends one clear visual beat per panel:

Create a short vertical comic-style reel with 4 equal-sized panels.
Panel 1: The owner leaves through the front door. The pet is framed in the window behind them, small against the glass, eyes wide, paws pressed high, the house suddenly quiet.
Panel 2: The door clicks shut. Silence breaks. The pet slowly turns toward the empty house, posture shifting, eyes sharp with possibility.
Panel 3: The house transformed. The pet sprawls across the couch like it owns the place, crumbs nearby, sunlight cutting across the room like a spotlight.
Panel 4: The door opens. The pet is seated perfectly by the entrance, alert and composed, as if nothing happened.

Listing: four-panel pet comic strip.

For app screens, OpenAI says to “describe the product as if it already exists”:

Create a realistic mobile app UI mockup for a local farmers market. 
Show today’s market with a simple header, a short list of vendors with small photos and categories, a small “Today’s specials” section, and basic information for location and hours. 
Design it to be practical, and easy to use. White background, subtle natural accent colors, clear typography, and minimal decoration. 
It should look like a real, well-designed, beautiful app for a small local market. 
Place the UI mockup in an iPhone frame.

Listing: farmers market app UI mockup.

Edits that keep the rest of the image

OpenAI’s edit examples are short and strict. Two from the guide:

Turn this drawing into a photorealistic image.
Preserve the exact layout, proportions, and perspective.
Choose realistic materials and lighting consistent with the sketch intent.
Do not add new elements or text.

Make it look like a winter evening with snowfall.

For edits of photos of people, upload only photos you have the right to use. We do not publish prompts that put celebrities or other real, identifiable people into images.

Limits by plan

OpenAI states that ChatGPT Images 2.0 “is available on all tiers”, and that “Images with thinking” is available on Plus, Pro and Business (Images in ChatGPT). On the Free plan, OpenAI’s Free tier FAQ says image creation has usage limits separate from the main chat limit, that these “can have stricter limits than paid plans”, and that ChatGPT will notify you when you reach a limit. If you hit it, you wait until a later time to create more images.

Plan details: ChatGPT Free, ChatGPT Go, ChatGPT Plus and ChatGPT Pro.