Anton Obukhov

The exception is raised based on the support check, meaning that 1.0 doesn't land into the support interval. Since loc and scale aren't given in the snippet, it is hard...

One thing I'd try first is plug these values in the unit test here https://github.com/toshas/torch_truncnorm/blob/main/tests/test.py#L97 and see if it passes the check against scipy. If not, there is a bug..

The documentation currently pulls files from the unmerged PRs here: https://huggingface.co/datasets/huggingface/documentation-images/discussions/338 https://huggingface.co/datasets/huggingface/documentation-images/discussions/339 https://huggingface.co/datasets/huggingface/documentation-images/discussions/340 Once these are merged, paths to images will need to be updated again

Hi @sayakpaul , I made a round of changes, please let me know what you think about the new separation of the documentation!

Thanks, @sayakpaul and @yiyixuxu, for guiding me on this one, It was an amazing experience, and I am very happy with the result!

Thanks for your interest, @al3dv2! Could you please elaborate on how you would tackle converting Hypersim pre-rendered depth maps into this format? Alternatively, if you know another dataset in this...

Please share scripts to automate these steps here, we will consider including these harness bits into the repository at a later stage.

@julienkay I see the folder structure is different: the VAE encoder and decoder were moved to the top level. Is there a way to keep the original structure? If this...

Can you please provide an example and the settings you used?

Maybe it is better to take the padding route from diffusers