ChatGPT

ChatGPT Images

Creating and editing pictures in ChatGPT from a description, from illustrations and diagrams to product shots, with targeted edits by area.

Describe, generate, edit by area You describe the image, ChatGPT generates it, you select an area, and only that area changes. Describe subject, style, format Generate first version Select an area the sky, the logo Targeted edit rest stays Check the edges after an area edit.

ChatGPT Images turns a description into a picture. Ask in any chat or open Images in the sidebar. You can set the aspect ratio, put text on the image, ask for a transparent background, or start from a template.

Editing is the strong part: select an area and describe the change, or describe a change to the whole picture. On Plus, Pro, and Business, images can use thinking for complex scenes. One rule at work: no realistic images of real people without consent, and no logos that aren't yours to use.

Often confused with: Image search. Search finds existing pictures on the web; Images makes a new one from your description.

See it in a lesson: Images, Sites and slides

Further reading

← All terms

Rollo AI AcademyWant your whole team speaking this language?Knowing the words is a start. Rollo Academy gets teams genuinely working with AI, through hands-on, in-company training built around your own work.Discover Rollo Academy →