search

kvablack / ddpo-pytorch

DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support
MIT License
397 stars 41 forks source link

On reproducibility and LoRA #2

Closed bhattg closed 1 year ago

bhattg commented 1 year ago

For the reproducibility experiments, right now the script has use_lora=True in the dgx.py. I just want to double check if that is indeed the case because the README.md seems a bit obscure.

kvablack commented 1 year ago

Yes, that is correct. All of the results you see in the image at the top of the README were produced using LoRA.