DALL-E now lets you edit images with ease: How to use feature on ChatGPT web and mobile

“The DALL·E editor interface enables you to edit images by selecting an area of the image to edit and describing your changes in chat. You can also provide a prompt with your desired edit in the conversation panel, without using the selection tool,” the company said on its website.

You can now edit DALL·E images in ChatGPT across web, iOS, and Android. pic.twitter.com/AJvHh5ftKB

— OpenAI (@OpenAI) April 3, 2024

Using the new feature is fairly simple. Once an image is generated, users simply need to click on it and edit options. A user can later click on the select tool and choose the specific area that needs to be edited. The selection tool is located on the top-left of the editor. Users can also change the size of the selection tool to highlight the area that they want to change.

OpenAI recommends selecting a larger space around the area that you need to edit to obtain better results. Besides, users will also be able to undo and redo selections with the Undo and Redo buttons above the image or select Clear Selection to start from scratch again. Users can save their creations by selecting the Save Button on the top-right corner of the editor.

Editing with DALL-E on ChatGPT Mobile

Just like the web, users can now edit their creations on the DALL-E editor interface on ChatGPT Mobile. Clicking on the generated image will reveal four buttons at the bottom – Edit, Select, Save and Share. To edit, users need to click on the generated image to go to the interface, click on edit, pick a select tool to specify the area, and offer a prompt with the desired edit.

The select tool provides easy access to the selection tool allowing users to highlight parts of the image to edit. The select tool also reveals a slider to the left of the screen that allows users to change the size of the selection tool along with undo and redo buttons at the bottom of the screen.

Once the selection is done, click on next on the top right of the screen. Later in the conversation panel users can complete the edit by describing the changes that they want to make to the highlighted areas of the image.

We tried the tool, however, did not get the desired results. Regardless, the new edit options are a great way to amplify your creativity as it lets you not only refine, but add new elements to an image.

The latest upgrade is in line with OpenAI’s measures to address issues related to trust when it comes to AI image generation. Recently, the AI startup introduced watermarks and metadata. This is seen as a good way to act against bad actors.