DeepSVG for text-conditioned vector generation.

[nd7141]

I wonder if it's possible to adapt DeepSVG to replace the VAE block in stable diffusion to generate vector graphics?

I see a couple of problems.

1. The latent embedding size in DeepSVG (256) does not match latent embedding size of SD (64).
2. diffusers library expects bin file instead of pth. There is a script to convert it to diffusers but it seems to use AutoencoderKL, which I'm not sure the right architecture.

I wonder if you know an easy way to adopt DeepSVG for diffusers library?

[PranavSudersan]

That's a great idea. Although I wonder if training a text based LM over the SVG source code dataset would be a better way to go about this, I don't know. Edit: I managed to find a project called VectorFusion which generates SVG from text description using the diffusion model. The authors have a paper on arXiv but they have not published their code unfortunately. The main author has an old github repository which does something similar, but I haven't tried it yet.