Apple researchers release MGIE AI image editing tool

Earlier in the month, Apple CEO Tim Cook teased several AI related announcements for later this year during an earnings call. (Image: Reuters)

Researchers from Apple have released a new AI model that lets you make photo edits, simply by describing what you want through text.

Called MLLM-Guided Image Editing (MGIE), the model can do Photoshop-like edits, modifying specific objects in a photo and more. In the released research paper, the team uses an example with an image of a pepperoni pizza, which can be edited using simple text inputs like "make it more healthy", which replaces the toppings to add vegetables.

Also read | World Street | China tightens the noose on securities, Apple's lawsuit win, DuPont's mega buyback plans and more

Similarly, it can remove subjects from a photo or enhance the brightness and contrast of an image.

“Instead of brief but ambiguous guidance, MGIE derives explicit visual-aware intention and leads to reasonable image editing. We conduct extensive studies from various editing aspects and demonstrate that our MGIE effectively improves performance while maintaining competitive efficiency. We also believe the MLLM-guided framework can contribute to future vision-and-language research,” the research paper reads.

The AI model is available for anyone to try through GitHub, and is an open-source project meaning anyone in the community can contribute to it.

Earlier this month, Apple CEO Tim Cook teased several AI-related announcements for later this year during an earnings call, telling investors he was, "excited to share the details of our ongoing work in that space later this year."