With myriad innovations being invented and flourishing in the tech space, it seems we will be seeing even more mind-blowing creations, as Apple is currently working on a technology that lets you edit photos with language text prompts and possibly, voice instructions.
In cooperation with researchers from the University of California, UC Santa Barbara researchers, the tech company has released the software in an open-source beta that is AI-powered and freely available online.
The new tech is called “MGIE”, an acronym for MLLM-Guided Image Editing. MLLM stands for Multimodal Large Language Model.
In a paper released by UC Santa Barbara and Apple researchers, they state, “Instruction-based image editing improves the controllability and flexibility of image manipulation via natural commands without elaborate descriptions or regional masks. However, human instructions are sometimes too brief for current methods to capture and follow. Multimodal large language models (MLLMs) show promising capabilities in cross-modal understanding and visual-aware response generation via LMs.”
“MGIE can perform common Photoshop-style edits, such as cropping, resizing, rotating, flipping, and adding filters. The model can also apply more advanced edits, such as changing the background, adding or removing objects, and blending images.”
Apple has also hinted that Siri, its existing voice assistant AI, is going to get updates soon, to make it smarter and more efficient.
