AI-generated company visual identity


AI-generated company visual identity

A family clothing brand from Poland, redefines its visual identity in an innovative way that uses technology. As a community-as-hero brand, all it does is engage all fans equally. That’s why the entire brand community creates its new symbol live using Artificial Intelligence (more precisely Generative Adversarial Network).

What and why?

The idea was that the whole community would create the new brand symbol, thereby becoming an inherent part of it. It has been achieved with the help of the newest technologies, more precisely Artificial Intelligence, powered by NeuroSYS. Anyone could download a Cleant mobile app, design their project, and upload it. Then, an AI system developed specifically for this purpose would analyze all logos sent, find patterns, and generate a final sign encompassing the collective vision of how a Cleant logo should look.

My contribiution

Cleant redefines its visual identity in an innovative way, taking advantage of modern technology. The new corporate logo has been generated by Artificial Intelligence, more precisely Generative Adversarial Network (GAN). I had tested different types of GANs to verify their possibilities before I have chosen the final solution. I used GANs, an unsupervised learning technique, which consists of two networks: a generator, which learns to generate new logo samples, and a discriminator which is taught to recognize real examples from generated ones to improve the logo generation process. Additionally, to stabilize network training for limited amounts of data I used an adaptive discriminator augmentation (ADA) mechanism.

Main tasks:

  • verifying possibility of using different types of GANs to generate new logo for the clothing brand, using rather small amount of data (~2k),
  • record neural network training process using ObsStudio,
  • contact with the client.

Technologies used: Python, Pytorch

Methods used: Deep Neural Networks, Generative Adversarial Networks, Unsupervised Deep Learning, Data Augmentation

Learn more about the project

Project’s website: