How to create AI images using ChatGPT

As of March 2025, ChatGPT is able to generate images. Following a period when it was briefly unavailable to free users, now you don’t even have to pay a single OpenAI subscription to use this feature. And while creating images within ChatGPT is easy, there are some features that should be explained. For example, did you know you can ask ChatGPT to edit the 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 input

You can start generating images in ChatGPT by simply typing in the command bar what you want to see. There is no need to overthink things; as long as you have some version of “image generation” followed by a description of your idea, ChatGPT will do the rest.

Depending on the complexity of the information and whether you pay for ChatGPT, it may take a minute or two for the chatbot to complete your photo request. Sometimes the process can take longer if the OpenAI servers experience more traffic than usual.

At the end of last year, OpenAI updated the model that powers 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 the ChatGPT sidebar. Here you can see all the images you’ve created, alongside sample information and suggestions for styles you can try, making it a great place to start if you’ve never used an image generator before.

How to create images with ChatGPT using existing images

In addition to generating images with text commands, ChatGPT can modify existing images or images you upload. This is my favorite way to create images with ChatGPT; I don’t need to define the structure, I can use the existing one to direct the chatbot. To use an existing image as the starting point for a new generation, follow these steps:

1. Tap “+” icon, located on the left side of the notification bar.

2. Select Add photos and files.

3. Select the image you want ChatGPT to edit. If you’re uploading a photo from your phone, you’ll first need to give ChatGPT access to your camera roll.

4. Write a command specifying the changes you want.

If it generates from the Photos section, tap “Add photos” instead.

Remember any images you upload to the OpenAI 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:

1. Open the sidebar menu.

   1. On mobile, press the two lines at the top left of the interface; on the desktop, click on the OpenAI logo.

2. Tap your name to access account settings.

4. Change to close Develop a model for everyone.

How to edit the images generated by ChatGPT

If you’re not happy with ChatGPT’s output, you have two options. You can tell it to create a completely new image, or edit parts of the image it just generated. As always, the process for both involves simply typing what you’re looking for into the notification bar. On mobile, OpenAI offers users several different ways to do the same task.

To generate a completely new image:

1. Tap the three dots icon below the created ChatGPT image.

To edit an existing image’s reproduction section:

1. Tap the created ChatGPT image.

3. Use your finger to hide the part of the image that you want ChatGPT to fix. The slider on the left allows you to adjust the size of the concealer brush. On desktop, masking is available when you click on an image and then click the paintbrush icon in the upper right.

4. Specify what you want ChatGPT to add, remove or change in the notification bar.

ChatGPT can also combine one of your photos with the generated image. To do this:

1. Tap the created ChatGPT image.

3. Upload the image you want

Like all AI programs, ChatGPT is arbitrary, meaning that even if you command it the same way multiple times, it won’t produce the exact same response each time.

Tips for creating better images with ChatGPT

The best advice I can give is to be specific when you tell ChatGPT. The more specific you are when you describe what you’re looking for, the better the results. And remember: ChatGPT can hallucinate – as you may have noticed in one of the example images I’ve included above. In the picture of the tortoiseshell cat, not only is the tortie not sitting on the window as instructed, it is sitting on a nonsensical table. So, above all, be patient. Validating an AI model is not an exact science, and it may take several attempts before it creates the desired result.

Frequently Asked Questions

How do you access ChatGPT?

ChatGPT is available on web, desktop and mobile. To access it on your computer, open your favorite browser and navigate to chatgpt.com. OpenAI also offers dedicated apps for Mac and Windows that you can download from the company’s website. On iOS and Android, you’ll need to download the ChatGPT app from the App Store or Google Play before you can start using the chatbot.

Since ChatGPT uses OpenAI servers, as long as you have access to the chatbot, you will be able to use it to create images regardless of 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 render a free image. After March 27, 2025, OpenAI briefly limited free users to three image generations per day. The company has since relaxed that limit, although it does not list the specific limit on its website. As far as I know, you will be able to produce about six to seven images every 24 hours.

OpenAI offers three different subscription plans, each with its own set of advantages for image production.

• ChatGPT Go, which costs $8 a month, offers “multiple image creation.”

• ChatGPT Plus, which costs $20 per month, offers “expanded and instant image creation.”

• ChatGPT Pro, which costs $200 per month, offers “unlimited and fast image creation.”

Be careful: ChatGPT Go will be included in OpenAI’s upcoming ad trial, which will see the company display sponsored content and organic responses from ChatGPT. The company does not plan to show ads to Plus and Pro users.

Can ChatGPT generate an existing image?

No. Due to copyright reasons, ChatGPT cannot reproduce images or real-world events. For example, when I asked it to recreate Zinedine Zidane’s 2006 World Cup header, ChatGPT refused.

“I can do a reinterpretation of art inspired by the emotion or energy of the time – for example, a stylized painting that shows the intensity and intensity of competition, without showing real people,” he told me.