Image generation in GPT-4o is now available to all users as the default image generator in ChatGPT. Users who prefer to continue with DALL·E can still access it through the DALL·E GPT.

You can generate images with ChatGPT by simply asking the model to create an image with the details you want, or by selecting the Create image option in the composer.

Once you enter your prompt, ChatGPT Images will generate the image as you’ve described it. Depending on the complexity of your instructions, ChatGPT may take up to two minutes to generate an image.

ChatGPT Images is capable of following precise instructions to add text, add details within the image, or make the background of an image transparent.

You can also use ChatGPT Images to make updates or edit existing images. To begin, upload an existing image and describe the changes you want ChatGPT to render.

To edit an image in ChatGPT, simply click on the image and find the Select tool on the top-right corner of the window.

The Select tool enables you to select an area of the image and edit it with ChatGPT by describing your changes. Learn more about editing your images with ChatGPT Images.

ChatGPT Free, Plus, Team, and Pro users can still generate images with DALL·E using the DALL·E GPT.

All images created using DALL·E will show 'Created with DALL·E' below the image.

If you encounter images generated by ChatGPT that may violate OpenAI's usage policies, please refer to our content reporting guidelines for detailed instructions on how to submit a report.

Currently, all GPTs with create GPTs using our legacy image creation model, DALL·E.