Apple announces ``Keyframer'', an AI tool that animates still images just by entering a prompt
On February 8, 2024, Apple's research team announced Keyframer , an AI tool that uses large-scale language models to animate still images.
Keyframer: Empowering Animation Design using Large Language Models
Apple researchers unveil 'Keyframer': An AI tool that animates still images using LLMs | VentureBeat
https://venturebeat.com/ai/apple-researchers-unveil-keyframer-an-ai-tool-that-animates-still-images-using-llms/
Apple is developing an AI tool for animating images using text prompts - The Verge
Keyframer, which uses OpenAI's large-scale language model GPT-4 as a base model, uses images in SVG file format uploaded by users to generate CSS code to realize text prompts input by users. thing
Users can create animations from still images by simply following three steps on Keyframer: ``Upload an image,'' ``Enter a text prompt,'' and ``Click Generate.''
A demo by Apple shows how the background changes when you enter a prompt such as 'make the stars twinkle.'
Users can also freely adjust properties such as the color code used in the animation and the length of the animation. At that time, Keyframer automatically converts the changes made by the user into CSS, so no complicated coding knowledge is required. You can also edit the CSS code directly.
“Keyframer supports further exploration and refinement of your animations through a combination of prompts and direct editing of generated output,” Apple explains.
A professional motion designer who participated in Apple's Keyframer test said, ``I'm worried about my work being replaced by Keyframer.The potential of Keyframer is so great. I plan to use it as a tool.'
However, Apple notes that the Keyframer test was a small study of just 13 people, and that only two pre-selected SVG file formats could be used to test the tool. I pointed out that it wasn't there.
Apple also notes that Keyframer is focused on web-based animation production, including loading sequences, data visualization, and animated transitions, and is currently unable to create complex animations like those seen in movies and games. I've made it clear that I can't.
In addition, Apple has announced its focus on the field of generative AI , and actually released the image editing AI model 'MGIE' in February 2024.
Apple has released an image editing AI model 'MGIE' that edits photos just by giving instructions in language, and a demo has been released so I tried using it - GIGAZINE
Related Posts:
in Software, Posted by log1r_ut