SVG Autoencoder - Uses a frozen representation encoder with a residual branch to compensate the information loss and a learned convolutional decoder to transfer the SVG latent space to pixel space.
You will need an XFL project (tested with Animate 2022), either in compressed .fla form or as a decompressed directory. To convert all frames of "Scene 1" to SVG, run: $ xfl2svg [path to .fla or dir] ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback