minivision-ai/photo2cartoon
A deep learning project that uses GANs to translate real photos into cartoon-style portraits while preserving identity information.
Not currently ranked — collecting fresh signals.
star history
This project implements a photo-to-cartoon translation system using deep learning and GAN architectures. Based on the U-GAT-IT approach with AdaLIN normalization and attention mechanisms, it performs unpaired image translation without requiring paired training data. The model learns the mapping between real photos and cartoon-style images from unaligned datasets, targeting a realistic cartoon style that balances simplicity with clear identity preservation.
Frequently asked
- What is minivision-ai/photo2cartoon?
- A deep learning project that uses GANs to translate real photos into cartoon-style portraits while preserving identity information.
- Is photo2cartoon open source?
- Yes — minivision-ai/photo2cartoon is open source, released under the MIT license.
- What language is photo2cartoon written in?
- minivision-ai/photo2cartoon is primarily written in Python.
- How popular is photo2cartoon?
- minivision-ai/photo2cartoon has 4k stars on GitHub.
- Where can I find photo2cartoon?
- minivision-ai/photo2cartoon is on GitHub at https://github.com/minivision-ai/photo2cartoon.