monophthongal

I found a workaround for a similar issue in https://github.com/facebook/create-react-app/issues/11897#issuecomment-1007206461, does it resolve the problem for you?

Any way to adapt the attention code to support larger images? The most common use case for this model would be upscaling outputs from SD.

Yes of course - here is another example with images saved at each step. Note that instead of using the repo's outpainting code, I'm generating shifted images and masks and...

Ah OK, that makes sense. I wondered if it might be some kind of image compression but didn't know the VAE was responsible. For now I'll explore using the npy...