Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

Apple Releases MGIE AI Image Editing Tool Capable of Making Detailed Edits Using Text Prompts

Share

Apple researchers have released an artificial intelligence (AI)-powered image editing tool called MGIE, which is capable of editing images using simple text prompts. MGIE, which stands for MLLM-Guided Image Editing, is capable of Photoshop-style edits, global optimisation, and local edits. The AI tool was released just a few days after Apple announced in its quarterly earnings call that it has been spending a “tremendous amount of time and effort” in generative AI. The image editing model shows an improvement on currently existing AI editing tools.

Researchers from Apple and from the University of California, Santa Barbara collaborated on the efforts to develop the tool. VentureBeat reports that the paper was presented at the International Conference on Learning Representations (ICLR) 2024. A preprint version of the research paper has also been hosted on arXiv.

The AI tool is capable of doing Photoshop-style edits which include cropping, resizing, rotating, adding filters, and more. It can also add global optimisation where it can alter the brightness, contrast, sharpness, colour balance, and even add generative elements to the image. Additionally, it can perform local edits where it adds, removes, or alters one particular object or element in the image.

To make an edit, users can simply write a plain text prompt such as “make the sky brighter” or “make the house bigger”, which is then interpreted as an image command and is used to increase the brightness by a certain percentage or increasing the size of the house by certain metric. Users can also provide more complicated and granular edits such as “adjust between the dark and light areas to bring out the details of the leaves and the tree trunk.” The more detailed a prompt is, the closer to the desired result it will get.

While AI-based photo editing tools such as Photoshop’s Generative Fill and under testing FireFly, Canva’s Magic Design, and Luminar Neo already exist, they all require the user to interact with the software to either map out the edit location or to make granular changes. Apple’s MGIE, on the other hand, can do the editing entirely on its own. It uses “instruction-based image editing” or “text-guided image editing”, which is made possible by taking a unique approach to artificial intelligence frameworks.

Instead of relying on the Generative Adversarial Network (GAN) framework, the AI model uses the diffusion model which is a more advanced architecture when it comes to realistic photo generation and instruction adherence. Next, the researchers shifted to using a multimodal large language model to ensure that it was capable of translating natural language into images and showing the desired effect. Further, human evaluators were also used during the process to rank the edits, and the feedback was used to further improve the model.

The tech giant has made the MGIE AI image editing tool available to download as an open-source project through GitHub. At the moment, it is not known whether Apple plans to use this technology for its devices or not. However, Apple CEO Tim Cook has said that the company will announce generative AI features that it has been working on, later this year, while Apple is reportedly working on new AI-powered features for the iOS 18 update that is expected to arrive later this year.


Affiliate links may be automatically generated – see our ethics statement for details.