Awesome Open Source
Awesome Open Source


A.I. for GNU Image Manipulation Program


⭐️ ⭐️ ⭐️ ⭐️ are welcome. This branch will no longer be updated and would only work with GIMP 2.10 and python 2.7 on mac and linux. Only GIMP3-ML branch will be updated in future which is targeted for python3 and GIMP3 (with windows and linux support) .

[June 2] GIMP3-ML branch development started.
Old Updates:
[January 9] Added image inpainting. (Existing users should be able to update.)
[November 28] Added interpolate-frames.
[October 31] Use super-resolution as a filter for medium/large images.
[October 17] Added image enlightening.
[September 27] Added Force CPU use button and minor bug fixes.
[August 28] Added deep learning based dehazing and denoising.
[August 25] Simplified installation and updating method.
[August 2] Added deep matting and k-means.
[July 17] MonoDepth and Colorization models have been updated.

Screenshot of Menu

image1

Installation Steps

Install GIMP 2.10 with Python 2.7

MacOS

[1] python command in terminal should point to GCC Apple LLVM Python 2.7.
[2] Install GIMP 2.10.22
[3] Open GIMP,Python-Fu should appear in the Filters menu.

Ubuntu

[1] Install GIMP 2.10 sudo apt install gimp
[2] Install Python 2.7 sudo apt install python2.7 , followed by sudo apt install python python-cairo python-gobject-2
[3] Download Files: gimp-python-debs.zip
[4] Install the above downloaded files with sudo dpkg -i *.deb
[5] Open GIMP,Python-Fu should appear in the Filters menu.

Install GIMP-ML

[1] Clone this repository: git clone https://github.com/kritiksoman/GIMP-ML.git
[2] Open terminal, go to GIMP-ML/gimp-plugins and run :
bash installGimpML.sh
[3] Open GIMP and go to Preferences -> Folders -> Plug-ins, add the folder gimp-plugins and restart GIMP.
[4] Go to Layer->GIMP-ML->update, click on ok with "update weights" set to yes and restart GIMP. (Weights ~ 1.5GB will be downloaded)

Manual install description if above is not working: Link

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}
}

Model Zoo

Name License Dataset
facegen CC BY-NC-SA 4.0 CelebAMask-HQ
deblur BSD 3-clause GoPro
faceparse MIT CelebAMask-HQ
deepcolor MIT ImageNet
monodepth MIT Multiple
super-resolution MIT ImageNet
deepmatting Non-commercial purposes Adobe Deep Image Matting
semantic-segmentation MIT COCO
kmeans BSD -
deep-dehazing MIT Custom
deep-denoising GPL3 BSD68
enlighten BSD Custom
interpolate-frames MIT HD
inpainting CC BY-NC-SA 4.0 DIV2K

Contribution

If anyone is interested in contribution, then please see our GIMP3-ML branch--> Link

License

GIMP-ML is MIT, but each of the individual plugins follow the same license as the original model's.


Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (1,143,903
Python3 (33,410
Machine Learning (31,776
Deep Learning (23,747
Linux (17,065
Macos (9,195
Computer Vision (8,228
Ubuntu (3,415
Machine Learning Algorithms (2,401
Image Manipulation (570
Gimp (136
Photo Editing (84
Deblurring (46
Gimp Plugin (45
Dehazing (42
Enlightenment (27
Coloring Image (2
Related Projects