This paper presents great visual images and quantitative scores for an autoencoder-based generative model. All reviewers agree on this aspect, and this is primarily the reason why acceptance is warranted. Certainly an AE pipeline with this capability is a worthwhile contribution to the community. However, the proposed method is mostly some engineered enhancements to the basic VQ-VAE model that has already been published. Moreover, full architectural details and hyperparamter settings were not provided in the original submission but were promised for the final version. For an enhanced AE model with modest novelty, this is a bit problematic and at least partially obfuscates proper evaluation of the complete system by reviewers. Even so, I would give the authors the benefit of the doubt and assume that the final version will include all the missing details.