# media & entertainment
ML-powered logo maker to instantly create custom logo designs
3
different ways to generate a logo6
weeks to complete a proof of concept5.6s
average time of generating 25 logo designs40
design patterns for logosproblems to solve
Our client (global stock content agency) had a vision of making a powerful branding available to everyone, regardless of skill level or background in design. Therefore, there arose a need for building a user-friendly AI-fuelled tool that empowers users to instantly and easily create good-looking custom-made logos.
The key challenges were:
- implementing good colour matching of particular elements within generated logos,
- allowing users to fine-tune selected logos,
- providing well-looking generated logos in vector graphic format.
solutions
The project boiled down to creating a proof of concept version (POC) of the Python application in order to demonstrate its feasibility and verify a practical potential of the concept.
In brief, the main user flow looks as follows: user inputs name of the business, selects industry, chooses a few pre-designed styles from templates, picks up colour schemes. These several steps were supposed to lead to the automated generation of a logo with a watermark.
A fundamental job that determined the success of the project was designing the model of logo generator's engine.
This came down to the following flow:
- at the beginning of the process, a batch of logos with random parameters was created,
- from this batch, those which broke some base design principle were filtered out i.e. those without sufficient contrast between colours,
- finally, a Machine Learning classifier, trained on examples hand-labeled as good or bad, filtered out those logos that didn’t reach a certain quality.
The model used as machine learning classifier was a neural network created in TensorFlow. This framework exposes to programmer low-level API that allows having better control over the architecture of the neural network.
view examples


key features
-
logo generator
creating logos based on three design patterns namely an icon, name, and initials based ones
-
machine learning classifier
a neural network created in TensorFlow that fuelled logo generator's engine
-
logo editor
allowing users to customize and fine-tuning elements of automatically generated logos