Apple’s new AI will be able to edit photos using text commands – Kommersant
[ad_1]
American corporation Apple presented new multimodal AI model MGIE for image editing. Users will be able to describe in their own words what they want as a result, and the AI will make appropriate changes to the list.
MGIE will be able to add, remove or change various objects, add contrast or simulate more light. The new AI is not without a sense of humor: if you ask to make the pizza “a little healthier,” it will add vegetable toppings. The distribution with MGIE can be downloaded from GitHub and tried on the Hugging Face Spaces platform.
Previously Apple released Ferret multimodal language model that works with both texts and images. The release of the neural network was not accompanied by announcements from the company, and the AI itself is able to analyze the image and determine what objects are on it, and then outline them with frames.
[ad_2]
Source link