Apple has introduced another AI-based tool – now it’s the Keyframer animation generator, based on a large language model. The system animates ready-made vector images on request in natural language format.
The authors of the project noted that today there are many AI image generators that work based on text descriptions – in particular, Dall-E and Midjourney. But animation requires a more complex set of parameters, including scene duration and coordination of object movement, that are not easily captured in a single task description, so alternative means, including command clarification, may be required.
These goals were achieved in the Keyframer system – it creates animated illustrations from static two-dimensional pictures. Commands are processed by the GPT-4 neural network; An SVG (Scalable Vector Graphic) format image is used as the source, and the output is CSS code that animates the picture. The user can refine this code by manually editing it or by specifying an additional text command.
The developers demonstrated Keyframer to professional animation designers and engineers, and their feedback was positive. They, in particular, noted that such a tool can save time: to achieve the result obtained by AI manually, it can take several hours.
Apple has been releasing research projects related to AI technologies in recent months – last week it was the free image editor MGIE. The company does not position itself as a leader in the field of AI, but it is not going to bypass this area: Tim Cook promised to make a major announcement this year.
If you notice an error, select it with the mouse and press CTRL+ENTER.