Which Human Faces Can an Ai Generate? Lack of Diversity in This Person Does Not Exist

Abstract

In this abstract we show the results of an interdisciplinary research in which we audit fake human faces generated by the website This Person Does Not Exist (TPDNE), and discuss how this system can help perpetuate normativities supported by a dependency on a limited database. Our analysis is centered on the “default generic face” that we created by overlapping random samples of fake human faces generated by TPDNE's algorithms – a version of Generative Adversarial Network, the StyleGAN2. To carry these experiments, we built a database with 4100 fake human faces taken from TPDNE via web scraping; we analysed them through a Python language script; and discussed behaviours identified in results. Our analyses are based on the use of images, called “cluster-images”, created from this overlapping of N arbitrary fake human faces by the TPDNE's algorithm. Our experiments showed that, independently of the group of fake human faces sampled, the same generic white face always appeared as a result. These results intrigue particularly because the lack of diversity of TPDNE's generated faces is not a mere problem to be fixed in this system in this digital infrastructure, but a dynamic of reinforcing standards that historically regulate bodies, territories and practices.

Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

“…Text-to-image generation models, in particular, have the potential to extend image-editing capabilities and lead to the development of new tools for creative practitioners. On the other hand, generative methods can be leveraged for malicious purposes, including harassment and misinformation spread [20], and raise many concerns regarding social and cultural exclusion and bias [67,62,68]. These considerations inform our decision to not to release code or a public demo.…”

Creative AI for HRI Design Explorations

“…Instead of looking at these results as failures, we rather suggest to embrace those 'anticipated' or 'biased' outputs. As these models are trained on real-world datasets and thus incorporate human biases [67,72], they can help to surface, identify, and confront existing assumptions and preconceptions. As such, using generative AI models can be an effective approach to make robot and social stereotypes visible [2] in order to then challenge them through designerly action.…”