Ask HN: Stable Diffusion for Vector Art? 1 points by tikwidd 4y ago ↗ HN What would it take to get image synthesis and img2img for generating SVG graphics?
[–] dougabug 4y ago ↗ Diffusion models can be trained to learn distributions over more or less arbitrary spaces of signals.
[–] minimaxir 4y ago ↗ It's probably easier/faster to just have AI generate vector art then use a tool to automatically vectorize it.
[–] sonovice 4y ago ↗ Have a look at https://clipasso.github.io/clipasso/ [–] tikwidd 4y ago ↗ Very interesting, thanks!
4 comments
[ 0.16 ms ] story [ 337 ms ] thread