Apple’s New AI Tool Lets You Edit Images Using Text Instructions

Apple’s rumored to be making some big strides in the world of AI with the upcoming iPhone, iPad, and Mac software updates later this year.

Now, the company has already shared a new open source image editing tool that uses the power of AI to edit images based on text-based instructions.

The Verge reports that the tool, called MGIE, can perform complex instructions when modifying even specific portions of an image.

MGIE, which stands for MLLM-Guided Image Editing, can be applied to simple and more complex image editing tasks like modifying specific objects in a photo to make them a different shape or come off brighter. The model blends two different uses of multimodal language models. First, it learns how to interpret user prompts. Then it “imagines” what the edit would look like (asking for a bluer sky in a photo becomes bumping up the brightness on the sky portion of an image, for example).

It remains to be seen whether this will form the basis of a new feature that will become part of the iOS 18 and other software updates this fall, but it’s interesting that the company is working on such a feature at all.

While we don’t imagine Apple having people type image editing instructions into an iPhone, it’s possible that these instructions could originate from something like a Siri request with users literally telling their device what to do with a photo. The launch of the Apple Vision Pro seems like the perfect place for such a feature to be used, for example.

You may also like to check out:

You can follow us on Twitter, or Instagram, and even like our Facebook page to keep yourself updated on all the latest from Microsoft, Google, Apple, and the Web.