Checkpoints for iColoriT models are available in the links below.
put pretrained models into ./saved_models/
| hint | Link | |
|---|---|---|
| Ours | ✓ | Google Drive |
| iColoriT | ✓ | Google Drive |
| No hint | ✗ | Google Drive |
Our code is implemented in Python 3.8, torch>=1.8.2, and PyQt5
git clone https://github.com/SaebyeolShin/Colorization_UI.git
pip install -r requirements.txt
Once you have satisfied all the requirements, you can run the base iColoriT model by executing
python3 colorize_ui.py
- Left click on Drawing Pad to select the hint location.
- Left click on the ab Color Gamut to select a color.
- Right click on a hint location to undo the click.
- Press Restart to undo all hints.
- Press Save to save the colorized image.
- Press Load to load another image.
Our GUI is an updated version of the iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer. Thanks for sharing the codes!