We are using GANs AI (Generative Artificial Intelligence) for our solutions,
which is very new within the AI deep learning field.
What is a GAN ?
A GAN in the artificial intelligence field is a certain architecture of neural networks which is able to generate hyper realistic images. (Please check our blog about "Everyone is talking about GANs, but what is it?")
Gan is short for Generative Adversarial Networks. It has been created in 2014 by Ian Goodfellow and is a hot topic subject in the AI research as of today!
How to build a GAN ?
To build a GAN, you need :
first to create a training image dataset of a few hundred thousand images,
second to set up a virtual architecture of GANs 2 neural networks: a generator network creating new images and a discriminator detecting if an image is a real image of the training set or a fake.
third train for a few days the GAN on a huge computing machine, so it can learn the mathematical distribution of the image dataset.
Finally get your GAN : a reusable and scalable easy to use artificial intelligence able to generate High-resolution realistic colors and images faster than any human.
Why use GAN?
GANs role at Eva Engines:
NO MORE WASTE IN CREATION PROCESS
Eva Engines is eager to build a better fashion industry with GANs. We are searching every day for ways to improve the fashion industry in its biggest challenges: better processes, ethical relationships, respect for models and care of the environment.
Thanks to our expertise on GAN’s and AI, we are working on a solution for the technical photoshootings of tomorrow and assistance on the creation process of brands to avoid waste of fabrics and prototypes. By putting these technologies at the center of our product, we are able to generate images of garments and faces to develop constructive tools for fashion businesses with tech on our side.
No more waste in creation process, use our GANs instead of wasting tons of samples.