Open huanzhizun opened 1 year ago
@huanzhizun Could you give more details about the Dreambooth implementation?
https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth.py Above link is the dreambooth implementation. When I try to apply Alpa to it, I find that there are some problems along with JAX.
Can alpa support the fine-tuning of Dreambooth for faster training?