alexandre01 / deepsvg

[NeurIPS 2020] Official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Includes a PyTorch library for deep learning with SVG data.

Home Page:https://www.lingosub.com

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

how to save“ icon.animate()” into *.gif ? and Can you add Font data in Demo test?

Johnson-yue opened this issue · comments

Hi, thanks for your sharing, I am testing your repo

I want to know how to save result of icon.animate() to *.gif ?

Hi! Thanks for your interest.

Just provide a value for the file_pathargument. For example:

icon.animate(file_path="animation.gif")

so quickly!!!, thank you

And Would you add some more ipynb for Font-generation like 4.4 sections in paper?

haha 😉

Yes I'll add the pretrained model for font-generation very soon. However, we do not plan to release the font-dataset since it is very large and we do not own the rights on the fonts. We recommend following SVG-VAE's instructions below to download it by yourself:
https://github.com/magenta/magenta/tree/master/magenta/models/svg_vae

ok, I know , you can test by no rights fonts like, Source Han Sans font, or I can provide some other open-source Font file, if you want ?

Oh yes, sounds like a good solution to show some examples of interpolations between real glyphs in the notebook. Thanks for suggesting!

If you want to some font ,you can email to me。

when you add pretrained model for font-generation or same examples for font , I will close this issue 。
have a nice day~

Added the pretrained models, mini dataset and a Jupyter notebook for font generation and interpolation 💪

https://github.com/alexandre01/deepsvg/blob/master/notebooks/fonts.ipynb

Thank you , I will try it soon