jacobjohansen / gimp-ml

Set of Machine Learning Python plugins for GIMP

GIMP-ML

Preprint: Link
Set of Machine Learning Python plugins for GIMP.

The plugins have been tested with GIMP 2.10 on the following machines:
[1] macOS Catalina 10.15.3
[2] ubuntu 18.04 LTS

Screenshot of Menu

Installation Steps

[1] Install GIMP.
[2] Clone this repository: git clone https://github.com/kritiksoman/GIMP-ML.git
[3] Open GIMP and go to Preferences -> Folders -> Plug-ins, add the folder gimp-plugins and close GIMP.
[4] Download weights.zip (1.22 GB) and save it in gimp-plugins folder.
[5] Open terminal and run :
bash installGimpML-mac.sh
bash moveWeights.sh
[6] Open GIMP.

Demo videos on YouTube

Paper References

[1] Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (https://arxiv.org/abs/1609.04802)
[2] DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better (https://arxiv.org/abs/1908.03826)
[3] Digging into Self-Supervised Monocular Depth Prediction (https://arxiv.org/abs/1806.01260)
[4] BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation (https://arxiv.org/abs/1808.00897)
[5] MaskGAN: Towards Diverse and Interactive Facial Image Manipulation (https://arxiv.org/abs/1907.11922)
[6] Perceptual Losses for Real-Time Style Transfer and Super-Resolution (https://cs.stanford.edu/people/jcjohns/eccv16/)
[7] Rethinking Atrous Convolution for Semantic Image Segmentation (https://arxiv.org/abs/1706.05587)

Code References

The following have been ported :
[1] https://github.com/switchablenorms/CelebAMask-HQ
[2] https://github.com/TAMU-VITA/DeblurGANv2
[3] https://github.com/zllrunning/face-parsing.PyTorch
[4] https://github.com/nianticlabs/monodepth2
[5] https://github.com/richzhang/colorization
[6] https://github.com/twtygqyy/pytorch-SRResNet

Citation

Please cite using the following bibtex entry:

@article{soman2020GIMPML,
  title={GIMP-ML: Python Plugins for using Computer Vision Models in GIMP},
  author={Soman, Kritik},
  journal={arXiv preprint arXiv:2004.13060},
  year={2020}
}