Nils Lehmann

> instead of what is currently in `__getitem__` we can use something like: > > ``` > items = TODO # list of the STAC Items that the current query...

> At the moment this STACAPIDataset implementation seems to be specific to just Sentinel-2, and it also assumes the use of Planetary Computer. Maybe we should have a think about...

Apologies, I have been busy finishing my master thesis until a couple of days ago. I was planning to pick this up again but it seems like there is a...

I am also currently trying to get some reasonable results for the FFHQ dataset, and also want to try Celeba-HQ. ```python from denoising_diffusion_pytorch import Unet, GaussianDiffusion, Trainer from torch.utils.data import...

These are results on the CelebHQ datset: 

> @nilsleh Would love to get this in the 0.5.2 release! Thanks for the reminder :)

@adamjstewart and @isaaccorley not sure how to simulate repeated calls to the function after restarting script/kernel, so I thought separate processes might be a way to go, but actually not...

> This is really cool! I wonder if there is any generalization between this and the Cyclone dataset Stay tuned:)

@adamjstewart not sure how I can fix the read the docs error, do I need to add the TypedDict to init?

Thanks, yeah option 1 makes sense, because the `TypedDict` is nicer for understanding the code.