There are a few more books that were published after 2016 that cover some of the topics you are interested in. I've not read any of them, so I don't really know whether they are good or not, but I try to summarise if they cover some of the topics you may be interested in.
Deep Learning with Python (2017), by Francois Chollet (author of the initial Keras library), which covers GANs in section 8.5 (p. 305), but it does not seem to cover transformers and attention mechanisms, although it covers other intermediate/advanced topics (not sure to which extent), such as text generation with LSTMs, DeepDream, Neural Style Transfer and VAEs
Grokking deep learning (2019), by Andrew Trask, which seems to cover some intermediate/advanced topics (such as LSTMs and related tasks), but no transformers or GANs (unless I missed them); you can find the accompanying code here
Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play, by David Foster, which covers many variants of GANs, VAEs and other stuff
The first transformer was published in 2017, so I guess there may not yet be a book that extensively covers it and other related models, such as the GPT models (if you're interested in CV, check this blog post, although it seems to list books that cover mostly traditional CV techniques). The attention mechanisms are older and can probably be found in textbooks that cover machine translation topics (such as seq2seq models with LSTMs), such as this one.