gwang-kim / DiffusionCLIP

[CVPR 2022] Official PyTorch Implementation for DiffusionCLIP: Text-guided Image Manipulation Using Diffusion Models
Other
799 stars 118 forks source link

Current implementation does not support multi-gpu finetuning. #22

Open GiannisPikoulis opened 2 years ago

GiannisPikoulis commented 2 years ago

Hello

Even though you have DataParallel inside your code, it won't work properly cause your implementation only supports a bs_train=bs_test=1.

ryliu68 commented 1 year ago

Hi, have you solved this problem? I had the same problem. Thx. @GiannisPikoulis