[train_text_to_image] allow using non-ema weights for training (#1834)
* allow using non-ema weights for training
* Apply suggestions from code review
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* address more review comment
* reorganise a few lines
* always pad text to max_length to match original training
* ifx collate_fn
* remove unused code
* don't prepare ema_unet, don't register lr scheduler
* style
* assert => ValueError
* add allow_tf32
* set log level
* fix comment
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>