Mateus Souza

found a workaround: `writer._comet_logger._experiment.set_name(EXP_NAME)`

you should provide which error you are facing and specify your environment. It does works.

Adding `--device cuda` worked for me. It looks like a change setted CPU to be used by default https://github.com/Stability-AI/stablediffusion/pull/147/files#diff-048b7bba4049f97b2038502af5686b6c5f53a882ff02771fcb0d733d22a0ab6cR180-R186, I think it was messing up data types.

Instead of compiling xformers, I followed the recommended from their [repo](https://github.com/facebookresearch/xformers#installing-xformers) and just installed the prebuilt binaries (you may need reacreate ldm using python version 3.9): `conda install xformers` https://github.com/Stability-AI/stablediffusion/issues/38#issuecomment-1327522703

This repo is the implementation of ViT. You can train your model, there is a example training on [cats and dogs dataset](https://github.com/lucidrains/vit-pytorch/blob/main/examples/cats_and_dogs.ipynb)