Get the latest tech news

NeuralSVG: An Implicit Representation for Text-to-Vector Generation


graphics are essential in design, providing artists with a versatile medium for creating resolution-independent and highly editable visual content. Recent advancements in vision-language and diffusion models have fueled interest in text-to-vector graphics generation.

We show results generated by our method when keeping a varying number of learned shapes in the final rendering. Even with a small number of shapes, our approach effectively captures the coarse structure of the scene. NeuralSVG generates sketches with varying numbers of strokes using a single network, without any modifications to the framework.

Get the Android app

Or read this on Hacker News

Read more on:

Photo of Text

Text

Photo of generation

generation

Photo of vector

vector

Related news:

News photo

Donut Lab's next-generation in-wheel motors

News photo

Racket-embed-images-in-source-text

News photo

Show HN: Experiments in AI-generation of crosswords