Apple releases MGIE AI image editing tool capable of performing detailed editing using text prompts

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 editing, global optimization, and local editing. The AI ​​tool was released just days after Apple announced in its quarterly earnings call that it was spending “huge amounts of time and effort” in generative AI. The image editing model shows improvements over currently existing AI editing tools.

Researchers from Apple and the University of California, Santa Barbara collaborated in efforts to develop the device. venturebeat reports This paper was presented at the International Conference on Learning Representations (ICLR) 2024. A preprint version of the research paper Also hosted on arXiv.

The AI ​​tool is capable of performing Photoshop-style editing including cropping, resizing, rotating, adding filters, and more. It can also add global customization where it can change the brightness, contrast, sharpness, color balance and even add generative elements to the image. Additionally, it can perform local editing where it adds, removes or changes a particular object or element in the image.

To make edits, users can simply type a plain text prompt such as “make the sky brighter” or “make the house bigger”, which is then interpreted as an image command and will increase or decrease the brightness by a certain percentage. Used to increase. House size according to certain metrics. Users can also provide more complex and nuanced edits such as “Adjust between dark and light areas to bring out details of leaves and tree trunks.” The more detailed the signal, the closer it will be to the desired result.

While AI-based photo editing tools like Photoshop’s Generative Fill and the under-tested Firefly, Canva’s Magic Design and Luminar Neo already exist, they all require the user to map out the editing space or make subtle changes along with the software. There is a need to interact. Apple’s MGIE, on the other hand, can do the editing completely on its own. It uses “instruction-based image editing” or “text-guided image editing”, 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 propagation model which is a more advanced architecture when it comes to realistic photo generation and instruction following. Subsequently, researchers started using multimodal large language models to ensure that it is able to translate natural language into images and show the desired effect. In addition, human evaluators were also used during the process to rank the edits, and the feedback was used to further improve the model.

Tech giant makes MGIE AI image editing tool available download As an open-source project via 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 it is working on later this year, while Apple is reportedly working on new AI-powered features for the iOS 18 update. Which is expected to come by the end of this year. Year.


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

(TagstoTranslate)Apple MGI AI image tool releases text prompt for detailed editing Apple(T)Artificial Intelligence(T)AI

Leave a comment