Since March 2025, ChatGPT has been capable of generating images. Following a period where it briefly wasn’t available to free users, you now don’t even pay for one of OpenAI’s subscriptions to use this feature. And while making images inside of ChatGPT is easy, there are some nuances worth explaining. For example, did you know you can ask ChatGPT to edit photos you’ve taken? It’s more powerful than you might think. Here’s everything you need to know about generating AI images with ChatGPT.
How to create images with ChatGPT using text prompts
To begin making an image in ChatGPT, you can start by typing in the prompt bar. (Igor Bonifacic for Engadget)
You can start generating images in ChatGPT simply by typing in the prompt bar what you want to see. There’s no need to overthink things; as long as you have some version of “generate an image” followed by a description of your idea, ChatGPT will do the rest.
Depending on the complexity of the prompt and whether you pay for ChatGPT, it may take a minute or two for the chatbot to complete your image request. Sometimes the process can take longer if OpenAI’s servers are experiencing greater traffic than usual.
At the end of last year, OpenAI updated the model powering image generation to make it faster, as well as better at rendering text and following instructions. At the same time, it added a dedicated “Images” section to ChatGPT’s sidebar. Here you can see all the images you’ve made, alongside sample prompts and suggestions for styles to try out, making it a great place to start if you’ve never used an image generator before.
How to create images with ChatGPT using existing photos
You can also upload images to ChatGPT. (Igor Bonifacic for Engadget)
In addition to generating images from text prompts, ChatGPT can modify existing photos or images you upload. This is my preferred way of making images with ChatGPT; I don’t need to describe the composition, I can use an existing one to guide the chatbot. To use an existing image as a starting point for a new generation, follow these steps:
Tap the “+” icon, located to the left of the prompt bar.
Select Add photos & files.
Select the image you want ChatGPT to edit. If uploading an image from your phone, you’ll first need to grant ChatGPT access to your camera roll.
Write a prompt describing the changes you want.
If generating from the Images section, tap “Add photos” instead.
Keep in mind any photos you upload to OpenAI’s servers may be used by the company to train future models. You can opt out of allowing your data to be used for training by following these steps:
Open the sidebar menu.
On mobile, tap the two lines on the top left of the interface; on desktop, click instead on the OpenAI logo.
Tap your name to access account settings.
Toggle off Improve the model for everyone.
How to edit the images ChatGPT generates
ChatGPT gives you a few different ways to edit images. (Igor Bonifacic for Engadget)
If you’re unhappy with ChatGPT’s output, you have two options. You can either prompt it to create an entirely new image, or edit parts of the picture it just generated. As always, the process for both involves simply typing what you want in the prompt bar. On mobile, OpenAI gives users a few different ways of accomplishing the same task.
To generate an entirely new image:
Tap the three dots icon below the image ChatGPT created.
To edit part of an existing image generation:
Tap the image ChatGPT created.
Use your finger to mask the section of the image you want ChatGPT to tweak. The slider on the left allows you to adjust the size of the masking brush. On desktop, masking is also available if you click on an image and then click on the paintbrush icon on the top right.
Describe what you want ChatGPT to add, remove or replace through the prompt bar.
ChatGPT can also blend one of your photos with an image it has generated. To do this:
Tap an image ChatGPT created.
Upload the photo you wish
Like all AI systems, ChatGPT is non-deterministic, meaning even if you prompt it in the same way multiple times, it won’t generate the exact same response each time.
Tips to create better images with ChatGPT
The best advice I can offer is to be specific when prompting ChatGPT. The more detail you can provide when describing what you want from it, the better the results. And remember: ChatGPT can hallucinate — as you may have noticed from one of the example pictures I included above. In the image of the tortoiseshell cat, not only is the tortie not sitting on the window sill as instructed, it’s sitting on a table that doesn’t make much sense. So, most of all, be patient. Prompting an AI model is not exact science, and it can take a few tries before it creates the result you want.
FAQs
How do you access ChatGPT?
ChatGPT is available on the web, desktop and mobile. To access it on your computer, open your preferred browser and navigate to chatgpt.com. OpenAI also offers dedicated Mac and Windows apps you can download from the company’s website. On iOS and Android, you’ll need to download the ChatGPT app from either the App Store or Google Play before you can start using the chatbot.
Since ChatGPT runs on OpenAI’s servers, as long as you can access the chatbot, you’ll be able to use it to create images no matter the age of your phone or computer.
Can ChatGPT generate images for free?
Yes, ChatGPT can generate images for free, as long as you create an OpenAI account. However, there is a daily rate cap and GPT-5 will take longer to make a free image. Following March 27, 2025, OpenAI briefly limited free users to three image generations per day. The company has since relaxed that restriction, though it doesn’t list a specific limit on its website. In my experience, you’ll be able to generate about six to seven images every 24 hours.
OpenAI offers three different subscription plans, each with their own set of image generation perks.
ChatGPT Go, which costs $8 per month, offers “more image creation.”
ChatGPT Plus, which costs $20 per month, offers “expanded and faster image creation.”
ChatGPT Pro, which costs $200 per month, offers “unlimited and faster image creation.”
Note: ChatGPT Go will be included in OpenAI’s forthcoming ads pilot, which will see the company display sponsored content alongside organic responses from ChatGPT. The company does not plan to display ads to Plus and Pro users.
Can ChatGPT generate an existing photo?
No. For copyright reasons, ChatGPT can’t replicate photos or exact real world events. For example, when I asked it to recreate the photo of Zinedine Zidane’s iconic 2006 World Cup headbutt, ChatGPT refused.
“I can make an artistic reinterpretation inspired by the emotion or energy of that moment — for example, a stylized painting showing the tension and intensity of competition, without depicting real individuals,” it told me.
