Apple has introduced the MGIE artificial intelligence model for image processing. To do this, users need to describe the desired changes in simple language, writes The Verge.

The name of the model stands for MLLM-Guided Image Editing. The company worked on this project together with the University of California, Santa Barbara.

MGIE lets you crop, resize, flip, and add filters to images with text prompts. You can also use the model to add specific objects to an image, reshape them, or make them brighter.

During operation, the model first learns to interpret the user’s prompts and then “imagines” what the editing will look like. Apple has demonstrated how effective MGIE is with several examples.

For example, in one case, the model was asked to make the pizza in the image healthier. Following this prompt, MGIE added a vegetable topping to the pepperoni.

Apple MGIE

It was recently reported that Google is launching a new tool for image creation based on artificial intelligence. It is called ImageFX and is based on the Imagen 2 model.