Vector Graphics Generation & Multi-Modal AI

9 repos

This cluster focuses on generative AI models that produce vector graphics (SVG) and animation formats from multi-modal inputs. The repositories center on training and deploying vision-language models that can synthesize scalable, editable vector outputs rather than raster images, with prominent work on OmniSVG and OmniLottie architectures. Developers exploring this area will find model implementations, training pipelines, and inference code for converting text, images, or other signals into production-ready SVG and animation assets.

Related clusters