AI is about intelligence demonstrated by machines, as opposed to natural intelligence displayed by living things.
OpenAI is among the pioneers in the AI field. Having introduced the highly-hyped ChatGPT, OpenAI also has what it calls the DALL·E.
The AI is meant to be the 'GPT' for images.
Its successor, DALL·E 2 is way more powerful, and the successor of that, the DALL·E 3 is even more powerful.
Since the product was introduced, users could only give it a prompt, and let the AI does the rest.
This time, OpenAI is introducing a feature, so users have more control.
You can now edit DALL·E images in ChatGPT across web, iOS, and Android. pic.twitter.com/AJvHh5ftKB
— OpenAI (@OpenAI) April 3, 2024
Users can access the DALL·E editor interface by clicking on an image generated by DALL·E.
In an editor-like interface, as explained in a dedicated help section, allows two main ways of editing.
The first method is allowing users highlight a specific area they want to change and then describe the alteration they would like to see through a text prompt.
To do this, users can use the 'select' option depicted as a swooping paintbrush icon. Once highlighted, a prompt box appears in the bottom right-hand side of the image which users can use to type in the change they want to see.
From there, users can add, remove, or enhance the highlighted part in the editor text box by giving prompts like, "add flowers."
Users can also use the select tool the ChatGPT mobile app and highlight areas with their finger.
The second method is by making overall changes to the image in the chat sidebar.
To make general edits, users can enter a prompt in the chat in the sidebar, like "make it black and white."
It's worth noting that OpenAI implementation relies heavily on ChatGPT to understand users' request.
This feature also works on the ChatGPT mobile app.
You can also get inspiration on styles when creating images in the DALL·E GPT. pic.twitter.com/mRrkwJKHyq
— OpenAI (@OpenAI) April 3, 2024
And for those who are overwhelmed by a blank canvas, and/or cannot think of where to start, OpenAI introduced a way to help these users.
OpenAI's DALL·E 3 is just one of many AI image generators on the market.
From Microsoft's Copilot image generator that is also posted by OpenAI's DALL·E 3, to Google's Gemini AI models, Adobe Firefly, to other powerful tools, like Midjourney and Stability AI.
The competition is fierce.
From this standpoint, it's a good move on OpenAI's part to make AI-generated images editable.
At this time, OpenAI is also focusing on expanding generative AI in multimedia with the announcement of its video generator Sora.