Apple Inc. (NASDAQ: AAPL) has added another generative AI tool to its growing portfolio. Named Keyframer, it allows users to animate static images using simple text prompts.
What Happened: Apple's recent innovation, outlined in a research paper named "Keyframer: Empowering Animation Design Using Large Language Models," leverages large language models (LLMs) to animate static images based on user's text prompts.
Using natural language prompts, Keyframer enables users to generate animated illustrations from static 2D images. Users upload an SVG image and input a prompt, and Keyframer generates a CSS animation code to animate the image.
Users can then fine-tune the animation by editing the code or inputting additional text prompts.
Keyframer's research was guided by interviews with professional animation designers and engineers. It allows users to iteratively refine their designs through sequential prompting, eliminating the need to plan their entire design upfront.
This development is the latest in a string of AI breakthroughs by Apple. Recently, Apple researchers unveiled an AI model that performs pixel-level edits on images.
In late December, Apple also made progress in deploying LLMs on iPhones and other Apple devices with limited memory.
Analysts predict that Apple will introduce some form of generative AI feature on the iPhone and iPad later in the year when iOS 18 is released. This could potentially be the "biggest" update in the iPhone's history.
Why It Matters: Back in October last year, Alphabet Inc.'s (NASDAQ: GOOG) (NASDAQ: GOOGL) Google showed off its AI-powered image generation tool.
Later next month, Meta Platforms Inc. (NASDAQ: META) had also introduced a similar tool.
Apple's recent AI developments, including the introduction of an AI image editing tool earlier this month and the acquisition of the iWork.ai domain just days ago, suggest that Apple is aggressively expanding its AI capabilities to compete in this space.