Apple Unveils AI Tool That Makes Detailed Edits To Videos With Text Commands: Here's How It Works

In a recent development, Apple Inc. AAPL has introduced a new AI image editing tool that enables users to make alterations to photos using text prompts.

What Happened: The new tool, named MGIE (MLLM-Guided Image Editing), allows users to describe the changes they want to make to a photo in everyday language, reported The Verge on Tuesday. The tool, developed in collaboration with the University of California, Santa Barbara, can perform a range of tasks, from simple edits like cropping and resizing to more complex ones, such as altering the shape or brightness of specific objects in an image.

MGIE uses multimodal language models to interpret user prompts and then ‘imagines’ what the edit would look like. Once the user inputs the desired changes, the model automatically applies them to the image. Apple has made the MGIE model available for download on GitHub and released a web demo on Hugging Face Spaces.

See Also: Happy 20, Facebook: If You Invested $1,000 In Mark Zuckerberg’s Social Network When It Went Public 12 Years Ago, Here’s How Much You’d Have

Why It Matters: This new tool from Apple is a significant addition to the AI image generation space. Other tech giants have also been making strides in this area. In December 2023, Meta Platforms Inc. launched a similar tool called Imagine with Meta, which generates high-resolution images based on text prompts. Microsoft Corporation and OpenAI also have similar text-to-image generation options available.

However, Apple’s entry into this space is notable, as the company has not been a significant player in the generative AI field. This new tool aligns with Apple CEO Tim Cook‘s statement that the company plans to add more AI features to its devices this year. In December, Apple researchers also released an open-source machine learning framework called MLX to make it easier to train AI models on Apple Silicon chips.

This development also comes at a time when the use of AI in image generation and editing is under scrutiny. A study by the Stanford Internet Observatory revealed that AI image generators are being trained on explicit images of minors, raising concerns about the ethical use of AI in image creation.

Meanwhile, Microsoft CEO Satya Nadella has spoken out against using AI to create non-consensual explicit images, emphasizing the need for tech companies to establish safeguards around AI technology.

Read Next: Arm Holdings Expected To Report Strong Earnings On Back Of Android Demand, While Apple Supplier Faces Risks Amid China Slowdown

Image via Shutterstock