Network data arise in a wide range of applications, including social, biological, economic and transportation networks, among others. One of the main inferential goals in the analysis of such data is the identification of groups of nodes with similar connectivity patterns. Among model-based approaches to node clustering, stochastic block models stand out for their combination of simplicity and flexibility. In particular, the broader class of extended stochastic block models (ESBMs) proposed by Legramanti et al. (2022) allows for greater flexibility in the specification of the prior on the node partition, as well as for a natural incorporation of node-level covariates. Besides reviewing this framework, the seminar will also illustrate ongoing research on calibrating the contribution of node-level covariates in ESBMs.