Apple’s AI image editing model has arrived although it’s far from a finished product. MGIE, short for multimodal large language model-driven image editing, is currently available on GitHub, and there is a PDF project document with instructions.
The template uses text instructions to change and edit images. It can perform simple image editing tasks such as increasing contrast or brightness and changing white balance. But it can also try to interpret more complex suggestions, such as making pizza healthier by adding vegetable toppings.
The template can also crop and resize, automatically fill image edges, change the subject’s hair, eyes and clothing, and remove objects.
MGIE is just the first step in Apple’s generative AI journey. It’s not likely to appear on any of Apple’s current devices, but it’s likely a sign of things to come.
Start a new Thread