As reported by Ukrinform, The Verge reports this.

The MGIE model, which Apple researchers worked on with the University of California at Santa Barbara, can crop, resize, rotate and add filters to images using text commands.

MGIE, which stands for MLLM Guided Image Editing, can be applied to both simple and more complex image editing tasks, such as changing certain objects in a photo into different shapes or to make them brighter.

This AI model combines two different multimodal language models.

First, it learns to interpret the user’s prompts. It then “imagines” what the edit will look like (for example, when wanting to make the sky bluer in the photo, the model adjusts the brightness of the sky in the photo).

When editing a photo with MGIE, users only need to type what they want to change in the image itself.

Apple is not yet a “major player” in the generative AI space, unlike Microsoft, Meta or Google, he said, but CEO Tim Cook said the company is looking to add more AI-powered features to its devices this year.

As Ukrinform reports, the American company Google has presented ImageFX, a new tool based on artificial intelligence (AI) for converting text into images.