diffvg

This is a fork of the original diffvg repository. The following file has been modified:

• pydiffvg/save_svg.py

We modified the file to support saving SVGs with radial gradients and backgrounds. See SGLIVE.

Name of the package is not changed. Please take caution when using this fork, or install it in a virtual environment.

The original README.md is below.

Differentiable Rasterizer for Vector Graphics https://people.csail.mit.edu/tzumao/diffvg

diffvg is a differentiable rasterizer for 2D vector graphics. See the webpage for more info.

Install

git submodule update --init --recursive
conda install -y pytorch torchvision -c pytorch
conda install -y numpy
conda install -y scikit-image
conda install -y -c anaconda cmake
conda install -y -c conda-forge ffmpeg
pip install svgwrite
pip install svgpathtools
pip install cssutils
pip install numba
pip install torch-tools
pip install visdom
python setup.py install

Install using poetry

prerequisite

install python 3.7, poetry and ffmpeg

# install poetry (mac, linux)
curl -sSL https://raw.githubusercontent.com/python-poetry/poetry/master/get-poetry.py | python -

# install ffmpeg

(macos)
brew install ffmpeg

(linux)
sudo apt install ffmpeg

or use conda
conda install -y -c conda-forge ffmpeg

Install python packages

# install all python dependencies
poetry install

# install pydiffvg
poetry run python setup.py install

Now to run the apps, just add poetry run before each of the commands below, e.g.

poetry run python single_circle.py

Building in debug mode

python setup.py build --debug install

Run

cd apps

Optimizing a single circle to a target.

python single_circle.py

Finite difference comparison.

finite_difference_comp.py [-h] [--size_scale SIZE_SCALE]
                               [--clamping_factor CLAMPING_FACTOR]
                               [--use_prefiltering USE_PREFILTERING]
                               svg_file

e.g.,

python finite_difference_comp.py imgs/tiger.svg

Interactive editor

python svg_brush.py

Painterly rendering

painterly_rendering.py [-h] [--num_paths NUM_PATHS]
                       [--max_width MAX_WIDTH] [--use_lpips_loss]
                       [--num_iter NUM_ITER] [--use_blob]
                       target

e.g.,

python painterly_rendering.py imgs/fallingwater.jpg --num_paths 2048 --max_width 4.0 --use_lpips_loss

Image vectorization

python refine_svg.py [-h] [--use_lpips_loss] [--num_iter NUM_ITER] svg target

e.g.,

python refine_svg.py imgs/flower.svg imgs/flower.jpg

Seam carving

python seam_carving.py [-h] [--svg SVG] [--optim_steps OPTIM_STEPS]

e.g.,

python seam_carving.py imgs/hokusai.svg

Vector variational autoencoder & vector GAN:

For the GAN models, see apps/generative_models/train_gan.py. Generate samples from a pretrained using apps/generative_models/eval_gan.py.

For the VAE models, see apps/generative_models/mnist_vae.py.

If you use diffvg in your academic work, please cite

@article{Li:2020:DVG,
    title = {Differentiable Vector Graphics Rasterization for Editing and Learning},
    author = {Li, Tzu-Mao and Luk\'{a}\v{c}, Michal and Gharbi Micha\"{e}l and Jonathan Ragan-Kelley},
    journal = {ACM Trans. Graph. (Proc. SIGGRAPH Asia)},
    volume = {39},
    number = {6},
    pages = {193:1--193:15},
    year = {2020}
}