OpenAI will now let users edit AI-generated DALL-E images within ChatGPT

Open AI It has added some new features. Artificial intelligence (AI) image generator DALL-E, specifically for its ChatGPT interface. The two new features, announced Wednesday, will allow users to edit photos created by DALL-E within ChatGPT and let users see style tips to inspire their creations. Both of these features are intended to improve the tool’s accessibility and make it more user-friendly for casual users. Notably on Tuesday, the AI ​​firm also created ChatGPT Accessible For everyone, even those who don’t have an OpenAI account.

The announcement was made via OpenAI’s official account via a. Post on X (formerly known as Twitter). Inline edit feature within ChatGPT as well as web client Android And iOS Apps Now, users with a paid subscription to OpenAI can go to ChatGPT and after entering a prompt to create an image, if they’re not happy with the result, they can open the image, which now displays an edit icon. will

This edit icon is placed just before the download icon. Once clicked, users can select circles to indicate the area they want to edit. After selecting the region, users will have to provide another prompt stating what they want to change. After the changes are entered, the AI ​​will regenerate the image. Recently, Microsoft’s copilot Designer also added a similar inline editing tool.

to use DALL-E Its native platform can be difficult for those who do not come from a graphic designing background as the tool is quite complex and requires detailed prompting with style weights to achieve the desired result. When OpenAI integrated the AI ​​Image Generator with it. Chat GPT After the launch of DALL-E 3 in September 2023, it solved this problem. Now, with the editing tool, users will find it easy to fix the images they have created.

In addition, OpenAI will also display style prompts right above the text field in ChatGPT to act as inspiration for users. Styles such as woodcut, close-up, low angle, artificial lighting, and more appear, and hovering the arrow over it reveals an example of the style. Users can click on a style of their choice and follow it with a simple prompt to create an image in that style.