Breathe new life into your old photos with colorization - Ainize

I was surprised how AI (Artificial Intelligence) technology can replace human intelligence and change our future when I watched the Google Deepmind Challenge Match in 2018. Since then, AI has been a cutting edge trend and I have watched this field with interests.

Now I work for this company which built open source as a service platform called Ainize especially for AI. Naturally, I encountered many fun open source projects related to AI and would like to share one of them called DeOldify.

DeOldify created by Jason Antic is an open-source AI tool enabling us to colorize and restore black and white images based on the GAN (Generative Adversarial Network) deep learning model. This one has been trained to add high-quality colorization to grayscale images. DeOldify is also selected as one of the top 10 most popular Machine Learning Github repositories.

I also had a chance to see photo albums of my grandparents and most of the pictures were black and white and they seemed oddly distant from reality even though they have emotional power at some point. I wondered how it would be to colorize those pictures. Maybe they would feel quite different by just colorizing pictures.

It would be very fun to fill with vivid colors for any kind of old pictures such as historic images, old animations, any photo you want to bring back to your life. As an example of what I can do with DeOldify, I tried Olivia Hussey.

You can also get started coloring your images and I’d like to share a short tutorial for this. You can click this link (https://deoldify-api.kmswlee.endpoint.ainize.ai/) and simply put an image URL and run it. Ainize team has deployed DeOldify and served it as API on this website using technologies such as Docker. Our Youtube video explains well about this project showing many examples of “Deoldified images”

If you are also interested in deploying other cool open-source projects using Ainize for free without any backend infrastructure, you can visit this link.(https://ainize.ai/) You can easily deploy it with Github URL once there’s a dockerized file on the repo. If not, simply follow our direction on http://docs.ainize.ai for the deployment.

Thanks to Jason, I am also glad that I could share this awesome project with everyone.
Hopefully this website gives you a fun experience. Enjoy Ainizing!

DeOldify GitHub : https://github.com/jantic/DeOldify
Try on Ainize: https://bit.ly/2Vc79RL
Sign up for Ainize Project : https://link.ainize.ai/2Xnbe76
Youtube: https://www.youtube.com/watch?v=Gei0nxVqbOo&feature=youtu.be
Facebook : https://bit.ly/2XIL7Yn
Twitter : https://link.ainize.ai/3alYwZ2