Was always fascinated by SVG art. How good are LLMs in generating SVGs?
Getting better!
https://simonwillison.net/2024/Oct/25/pelicans-on-a-bicycle/
Perhaps a generous definition of "better"... but some of those genuinely made me laugh!
Regular LLMs are quite bad at it (see simonwillison's blog post). However this paper [0] describes an apparently sound approach using Neural Radiance Fields (NeRFs), however their github repo [1] has been "code coming soon!" for months now, so you can't really use it.
It's been released as of an hour ago!!! https://github.com/SagiPolaczek/NeuralSVG/pull/6
Oh boy oh boy oh boy
I've gotten decent outputs with Claude with iteration (sending both text feedback and screenshot for context) and then tweaked the output in Inkscape.
In at least my limited experience, they're kind of bad. They can retrieve shapes that already exist, sometimes inaccurately, but they are less reliable at creating novel ones