Research Article
Bias Analysis in Stable Diffusion and MidJourney Models
@INPROCEEDINGS{10.1007/978-3-031-35081-8_32, author={Luka Aničin and Miloš Stojmenović}, title={Bias Analysis in Stable Diffusion and MidJourney Models}, proceedings={Intelligent Systems and Machine Learning. First EAI International Conference, ICISML 2022, Hyderabad, India, December 16-17, 2022, Proceedings, Part II}, proceedings_a={ICISML PART 2}, year={2023}, month={7}, keywords={Artificial Intelligence AI Generation Models Bias detection}, doi={10.1007/978-3-031-35081-8_32} }- Luka Aničin
Miloš Stojmenović
Year: 2023
Bias Analysis in Stable Diffusion and MidJourney Models
ICISML PART 2
Springer
DOI: 10.1007/978-3-031-35081-8_32
Abstract
In recent months, all kinds of image-generating models got the spot-light, opening many possibilities for further research direction, and from the commercial side, many teams will be able to start experimenting and building products on top of them. A sub-area of image generation that picked the most interest in the eye of the public is text-to-image models, most notably Stable Diffusion and MidJourney. Open sourcing Stable Diffusion and free tier of MidJourney allowed many product teams to start building on top of them with little to no resources. However, applying any pre-trained model without proper testing and experimentation creates unknown risks for companies and teams using them. In this paper, we are demonstrating what might happen if such models are used without additional filtering and testing through bias detection.
