Apple has created an artificial intelligence model for photo editing using text suggestions

by alex

The Technology section is published with the support of Favbet Tech

Apple создала модель искусственного интеллекта для редактирования фотографий с помощью текстовых подсказок

Apple researchers have developed a new artificial intelligence model that allows users to describe in simple language what they want to change in the photo. At the same time, you can adjust images without even touching photo editing software.

The MGIE (MLLM-Guided Image Editing) model, which Apple worked on with the University of California, Santa Barbara, allows you to crop, resize, flip and add filters to images using text prompts. This model can also be used for more advanced image editing tasks, such as changing certain objects in a photo to give them a different shape or make them brighter.

MGIE combines two different types of use of multimodal language models. First, it learns to interpret the user's cues. It then “imagines” what the edit would look like (for example, asking for a bluer sky in a photo causes the sky portion of the image to be brightened).

Apple создала модель искусственного интеллекта для редактирования фотографий с помощью текстовых подсказок

When editing a photo using MGIE, users simply need to type what they want to change in the image. For example, when editing an image of a pepperoni pizza, you can type the prompt “make it healthier” and the model will add vegetable toppings. The photo of tigers in the Sahara looks dark, but after the models were told to “add more contrast to simulate more light,” the image became brighter.

“Instead of brief but ambiguous directions, MGIE reveals clear visual intent and results in intelligent image editing,” — says the researchers' article.

Apple has made MGIE available for download via GitHub and has also released a web demo of Hugging Face Spaces. The company did not specify its future plans for this model.

READ
AvtoVAZ announced when Lada Niva will receive airbags

2D character concept artist course. During the course you will learn skills in robotics with light, color, anatomy and plasticity. View information about the course

Apple создала модель искусственного интеллекта для редактирования фотографий с помощью текстовых подсказок

Apple создала модель искусственного интеллекта для редактирования фотографий с помощью текстовых подсказок

Favbet Tech is IT a company with 100% Ukrainian DNA, which creates perfect services for iGaming and Betting using advanced technologies and provides access to them. Favbet Tech develops innovative software through a complex multi-component platform that can withstand enormous loads and create a unique experience for players. The IT company is part of the FAVBET group of companies.

You may also like

Leave a Comment