You can now edit DALL-E images if your AI-generated image needs a tweak here and there.
This week, OpenAI released an editor interface tool, which lets users make edits by describing changes in a text prompts.
As explained in the DALL-E help section which was updated this week with instructions for using the tool, there are two main ways of editing images. The first is by highlighting a part of the image and giving specific instructions for that area, and the second is by making overall changes to the image in the chat sidebar.
How to edit images in DALL-E
To highlight part of the image and make edits to specific parts of the picture on desktop, there’s a new select button depicted as a swooping paintbrush icon. From there, you can add, remove, or enhance the highlighted part in the editor text box by giving prompts like, “add flowers.” You can also use the select tool the ChatGPT mobile app and highlight areas with your finger.
To make general edits, enter a prompt in the chat in the sidebar, like “make it black and white.” This feature also works on the ChatGPT mobile app.
OpenAI’s DALL-E is just one of many AI image generators on the market these days. Microsoft’s Copilot image generator is powered by OpenAI’s latest model, DALL-E 3, but Google has its own tool within its Gemini model (which came under fire recently for rendering Nazis as people of color and other historical inaccuracies, leading the company to pause Gemini while it fixed its historiography problem.) These, plus other tools out there by Midjourney and Stability AI, make the competition fierce for creating images using generative AI.
AI-generated images are increasingly prevalent, as demonstrated by their integration into search results and their utilization in films such as Late Night with the Devil and promotional materials (with apologies to Willy Wonka and the children of Glasgow).
From this standpoint, it’s probably a good move on OpenAI’s part to make AI-generated images more editable.
Meanwhile, OpenAI is focusing on expanding generative AI in multimedia with the announcement of its video generator Sora, and most recently, a voice creator called Voice Engine.
