![google is testing its own neural filter app photo google google is testing its own neural filter app photo google](https://i.tribune.com.pk/media/images/1213023-Googlefilter-1477643470/1213023-Googlefilter-1477643470.jpg)
However, Google is planning to go one step ahead with the technology giant working on a feature that lets you create your own unique filters by combining different styles together – and all of that in real-time. If Google does succeed in doing so, these features may trump Prisma’s popular filters and open a new genre of photo editing.
After images, Prisma now lets users turn videos into artworks
Describing how the app would basically make it possible to adjust the different styles until you reach the combination you desire, the tech giant claimed that its method is not only easy to implement, but also uses less memory - a major complaint people have for Prisma.
![](http://c.tribune.com.pk/2016/10/image06.png)
"This work is considered a breakthrough in the field of deep learning research because it provided the first proof of concept for neural network-based style transfer. Unfortunately this method for stylising an individual image is computationally demanding. For instance, in the first demos available on the web, one would upload a photo to a server, and then still have plenty of time to go grab a cup of coffee before a result was available," said Google in a blog post.
It remains to be seen how Google minimises the processing time given the fact that Prisma has been criticised for its long processing time.
Although the app is in development stages, Google said it will release more details in the near future.
Apple ramps up MacBook infused with touch controls
Google and Prisma aren’t the only ones working on style transfer technologies though. Earlier, Facebook announced it is developing its own art filters for live video, but has not provided any details of when to expect the features.
COMMENTS
Comments are moderated and generally will be posted if they are on-topic and not abusive.
For more information, please see our Comments FAQ