Suraj Patil

Hi @mengyahuUSTC-PU , the checkpoints saved by lightening can't be loaded directly in HF models. To do that ```python3 model = T5FineTuner.load_from_checkpoint("lightening checkpoint path") # save the model in HF...

HI @bhadreshpsavani , very sorry for the late reply. Were you able to solve this ? What your transformers version ? In new transformers version `DataCollaor` is not a `Class`...

I'll try to update it as soon as possible for me, but the above solution should help

change `__cal__` to `__call__`

Hi @ZhiliWang Sorry for the late response. One disclaimer before I write my answer, I'm not the best person to ask this question but I'll try my best to answer....

Are you share you ran all the cells ? In particular, the `prior_loss_weight` is defined in this cell https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb#scrollTo=8i_vLTBxAXpE, so make sure you run those.

Could you post the command that you used to launch ?

Thanks for the issue! @briansemrau answer seems right! We have verified the script with the orginal `.ckpt` file and works as expected, please check if you have not modified anything.

Fix is here #445, #446

Thanks a lot for the issue! We should definitely follow CompVis initialization here. Feel free to open a PRm happy to help with it!