4.3. Presentation: Visit the Product Store

The dataset is accessible through the https://lttrface.com/ai-font-tester website. The interface provides comprehensive instructions for downloading the dataset, along with multiple access options tailored to different use cases. A free demonstration version offers a limited subset of the dataset, whilst researchers may request complimentary access to the complete dataset. Commercial licensing options are also available for industry applications.

Figure presents the website interface for accessing the LTTR/SET. On the left are UI controllers to preview the font-variant, in the middle, the font preview which text is editable, on the top right buttons to download the previewed font or access the complete dataset as a package.

The font files within the dataset follow a systematic naming convention that encodes the parameter values for each axis. The filename structure comprises axis identifiers (00-99) followed by their corresponding locations (00-99), arranged in the sequence: skeleton axes, weight axis, and tilt axis. For instance, given the parameters SHAP: 001 = 25, SHAP: 002 = 80, WGHT = 70, TCON = 50, TILT = 40, the resulting filename would be 25-80-70-50-40.otf.

The dataset employs a granularity of five steps per axis, allowing for precise control over the parameter space. This structured naming system enables users to filter and download specific subsets of the dataset based on their requirements. For example, one might select files within a particular weight range or focus on specific skeleton variations. This modular approach to dataset access ensures efficient utilisation of resources, as users need only download the font files relevant to their application.

License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License .

Creative Commons License

Citation

If this work is useful for your research, please cite it as:

@phdthesis{paldia2025generative,
  title={Research and development of generative neural networks for type design},
  author={Paldia, Filip},
  year={2025},
  school={Academy of Fine Arts and Design in Bratislava},
  address={Bratislava, Slovakia},
  type={Doctoral thesis},
  url={https://lttrface.com/doctoral-thesis/},
  note={Department of Visual Communication, Studio Typo}
}