Sterling G. Baird

Maybe related #59

I'm also interested in why there is the factor: `(2.0 / (1 - p))` in the coverage penalties.

I get a similar issue - submodule in GitHub Desktop reports "never fetched", but everything seems to work normally otherwise. I don't use `--separate-git-dir`; at least I've never specified that...

```python 0%| | 0/700000 [00:00

If anyone tries this out, would be great if you could link to some code or provide a MWE. Or if anyone is aware of other implementations

See also https://github.com/lucidrains/denoising-diffusion-pytorch/issues/21#issuecomment-1143989193

Related: - https://github.com/Janspiry/Image-Super-Resolution-via-Iterative-Refinement - https://github.com/Janspiry/Palette-Image-to-Image-Diffusion-Models Haven't tried SR3, and haven't been able to get Palette to run to completion on the example datasets, despite a lot of troubleshooting and dealing...

So, should we be using a commit from March? Has anyone else verified the change in behavior from March until now? @XDUWQ do you have any examples of the difference...

Hmm, I worked around this somewhat manually using `conda-souschef` (https://github.com/marcelotrevisani/souschef/issues/32). Not sure I understand the idea behind using `config.yaml` as described here. Is the idea to do a local installation...

@BastianZim where should `config.yaml` be placed? Should I make a folder structure in the project: `grayskull/pypi/config.yaml`? Didn't see any files on `grayskull` called `config.yaml`: https://github.com/conda-incubator/grayskull/search?q=config.yaml More just wondering how/if I...