A new mobile app called FaceApp uses neural networks to edit your selfie via photo-realistic filters – letting you add a smile, swap genders, and can take years off your age.
Developed and self-funded by a small group out of Russia in eight months, the app uses CUDA, TITAN X Pascal GPUs, Tesla K80s and the cuDNN-accelerated TensorFlow deep learning framework to train their deep generative convolutional neural networks. The app then sends the selfies to the cloud (Microsoft Azure’s Tesla K80 GPU instance) to transform them.
In regards to how FaceApp is different from the viral style transfer app Prisma, “Prisma changes the style of a photo, but doesn’t modify the content,” said Yaroslav Goncharov, founder and CEO of the app. “FaceApp changes the content (by adding a smile), but keeps the style (so the picture stays photorealistic).”
The app is now available as a free download for iOS and Android.
Download now >
This AI Selfie Transformation App Can Even Make Mona Lisa Smile
Feb 08, 2017
Discuss (0)
AI-Generated Summary
- FaceApp is a new mobile app that uses neural networks to edit selfies with photo-realistic filters, allowing users to add a smile, swap genders, or make themselves look younger.
- The app was developed by a small team in Russia using NVIDIA's CUDA and cuDNN-accelerated TensorFlow deep learning framework, and was trained on powerful GPUs including the TITAN X Pascal and Tesla K80.
- FaceApp differs from other photo editing apps like Prisma in that it changes the content of the image rather than just the style, while still maintaining a photorealistic look.
AI-generated content may summarize information incompletely. Verify important information. Learn more
About the Authors
