Remember Prisma – the awesome app that uses artificial intelligence to turn your photos and videos into pieces of art? Well, Google is working on a new style transfer technology that will make even Prisma’s filters look lame.
In a recent blog post, Google revealed it’s developing a photo-manipulation system that not only lets you turn your selfies into art, but also allows you to create your own unique filters by combining different styles together – and all of that in real-time.
Here’s how the big G explains its new method:
[M]ultiple styles are combined in real-time and the resulting style is applied using a single style transfer network. The user is provided with a set of 13 different painting styles and adjusts their relative strengths in the final style via sliders.
As showcased in the video, the app basically makes it possible to adjust the different styles in real-time until you reach the result you desire.
What’s noteworthy is that Google claims its method is not only easy to implement, but also much more efficient and less memory-intensive than previous methods.
At present, it seems the filter technology is still in development stages. However, Google claims it will release more details in the near future, and further promises to make the system’s TensorFlow source code available to users so they can run and test it themselves.
Google and Prisma aren’t the only ones working on style transfer technologies though. Facebook announced it’s crafting its own art filters for live video, but it’s not yet clear when the new feature will roll out.