Decomate: Leveraging Generative Models for Co-Creative SVG Animation

TL;DR

Decomate is a system that uses multimodal large language models to help designers animate SVG graphics intuitively through natural language, enabling easy restructuring and motion specification for creative workflows.

Contribution

It introduces a novel approach combining multimodal AI and natural language to simplify SVG animation, making it accessible without technical expertise.

Findings

Enables semantic restructuring of SVGs for animation.

Supports natural language-based motion specification.

Facilitates iterative refinement through user interaction.

Abstract

Designers often encounter friction when animating static SVG graphics, especially when the visual structure does not match the desired level of motion detail. Existing tools typically depend on predefined groupings or require technical expertise, which limits designers' ability to experiment and iterate independently. We present Decomate, a system that enables intuitive SVG animation through natural language. Decomate leverages a multimodal large language model to restructure raw SVGs into semantically meaningful, animation-ready components. Designers can then specify motions for each component via text prompts, after which the system generates corresponding HTML/CSS/JS animations. By supporting iterative refinement through natural language interaction, Decomate integrates generative AI into creative workflows, allowing animation outcomes to be directly shaped by user intent.