Dhruv Nair

@yunseongcho Would you mind sharing a checkpoint we could use to test with?

Hi @yunseongcho sorry for the delay. Yes I'm okay to merge this.

Is the plan here to eventually map the `Transformer2DModel` to the variant? e.g A pipeline that uses `Transformer2DModel` with patched inference will now try to create `PatchedTransformer2DModel` under the hood?...

@Hellcat1005 It is difficult to debug this without a reproducible example. What dataset are you trying to use here? Is it a custom one? If you try running with `dataloader_num_workers>0`...

Thanks for investigating @isamu-isozaki! Hmm so the core issue seems to be with Pytorch multiprocessing on Windows then? Perhaps @Hellcat1005 you can modify the script to move the functions @isamu-isozaki...

@rishabh063 The Discussions section would be a better place for this question.

@sayakpaul could you take a look here please.

Closing for now as this seems to be an issue related to the Geowizard repo. Feel free to reopen if needed.

@xinli2008 Could you share the command you used to train your textual inversion model please? Also I think you've uploaded a full text model rather than the inversion embedding [here](https://huggingface.co/shaoniana1997/my-textual-inversion-model/tree/main)....

Hmm strange. Some tensors are not being saved in the OpenCLIP model when calling `save_pretrained`. Taking a look.