Apple has released a new artificial intelligence (AI) model that can organize photos based on text descriptions. The project, called MLLM Guided Image Editing (MGIE), was developed in collaboration with the University of California, Santa Barbara, United States.
Tool As with AI image creators, you can crop, resize, orientation, add or remove filters, and more by following user-provided prompts.
During the editing process, The user must describe in text the changes he wants to apply. In documentation provided by Apple, the user describes changes such as “make this recipe healthier,” have the AI add vegetables to the pizza, and “add contrast to simulate more light.”
Apple notes that MGIE requires the user to identify a “clear visual awareness purpose,” resulting in a reasonable accommodation.
What can MGIE do?
According to Apple, some of MGIE’s capabilities include:
- Instruction-based editing;
- Changes and adjustments in Photoshop style;
- General optimization of a photo;
- Changes found in an image.
Broadly speaking, Apple’s AI can make a multitude of changes to a file, including fine-tuning contrast, brightness, and color temperature, as well as adding and removing objects.
Available on GitHub
MGIE is available for consultation and testing on GitHub, so developers can experiment at their leisure. The company also launched a web demo on another online repository, Hugging Face Spaces.
This is one of Apple’s first public AI demonstrations, reinforcing that the company is actually interested in developing the technology.
Such an editing tool could also be useful in Apple apps, and could even be part of the upcoming iOS 18, which is expected to be one of the biggest updates to the system.
Source: Tec Mundo
I am a passionate and hardworking journalist with an eye for detail. I specialize in the field of news reporting, and have been writing for Gadget Onus, a renowned online news site, since 2019. As the author of their Hot News section, I’m proud to be at the forefront of today’s headlines and current affairs.
