brian6091

Frozen for v0.0.2 To test on mix

Where are you running the script? If you are using the notebook, does the error occur when you launch the training? Or somewhere before? I only have access to Google...

Ok, I actually haven't tried the notebook on the main branch for awhile. I will test tonight. Thanks for reporting.

Are you referring to the notebook on the main branch?

Ok thanks. I'll have a look today.

So I've fixed a couple of things and checked that the dependencies are all ok (at least on Google Colab). Please try the Notebook linked below. Two things: 1) I...

Are train_batch_size and sample_batch_size both equal to 1? Can you post the args.json output here (it will be in your output_dir). It OOMed at a weird step, so I'm not...

https://androidkt.com/how-to-copy-pytorch-tensor-using-clone-detach-and-deepcopy/ https://stackoverflow.com/questions/62437509/what-is-the-difference-between-detach-clone-and-deepcopy-in-pytorch-tensors-in https://androidkt.com/copy-pytorch-model-using-deepcopy-and-state_dict/ https://ofstack.com/python/40554/solve-the-state_dict-of-copy-problem-of-pytorch.html

https://ofstack.com/python/39062/detailed-explanation-of-copy-and-local-operation-in-pytorch.html

> for step, batch in enumerate(train_dataloader): > # TODO: how to handle context setting when unet is not training? > # https://stackoverflow.com/a/14029481 > #train_all = train_unet and train_text_encoder > #with...