OpenAI has updated the editor for DALL-E, the artificial intelligence image generator that is part of the ChatGPT premium tiers. The update, based on the DALL-E 3 model, makes it easier for users to adjust their generated images. Shortly after DALL-E 3’s September debut, OpenAI integrated it into ChatGPT, enabling paid subscribers to generate images from text or image prompts. The new DALL-E editor interface lets users edit images “by selecting an area of the image to edit and describing your changes in chat” without using the selection tool. Desired changes can also be prompted “in the conversation panel,” according to OpenAI.

“You’ll now find image editing tools when using DALL-E within ChatGPT, both on the web and on mobile,” writes The Verge, adding that the third generation of the image-generator “now offers preset style suggestions to help inspire image creation — not unlike Android’s AI-generated wallpaper prompts.”

“The editor interface enables you to add, remove, and update parts of your image,” OpenAI writes in a blog post, explaining “the interface provides a range of options to highlight parts of your generated image that you want to update.” When using ChatGPT-3, the DALL-E editor is accessed through the same chatbot interface used for the ChatGPT features.

“A newly added ‘Select’ button at the top of the interface enables users to highlight the specific image section they wish to edit,” explains SiliconANGLE, noting that “from there, they can enter natural language instructions describing the changes they wish to make.”

The example provided is drawing a circle around one tree to have the DALL-E editor remove it from a forest photo. “It’s also possible to change the design of the objects in an image or add new ones,” SiliconANGLE reports.

“Undo” and “redo” buttons have also been added, along with “clear selection” to start over entirely. “Customers can also adjust the aspect ratio of the image that the tool generates, as well as access drawing style suggestions,” per SiliconANGLE.

“DALL-E encourages a kind of over-the-top prompt engineering, where people submit paragraphs of text, something between a vignette and a short story,” writes CNET, which reviews the app, comparing it favorably to Adobe Firefly and Google ImageFX.

This year, DALL-E 3 began adding “visible watermarks and metadata to denote an AI-generated image,” reports The Verge, crediting “a good start, for sure, but both can be easily removed by bad actors.”