lora_wrap_diffusion_head problem

#2
by PakdamanAli - opened

Hello,
Thank you for sharing your experience.
I fine-tuned this model on my own dataset for 30 epochs using --train_diffusion_head True, but the results were not satisfactory.
Now I want to fine-tune it using --lora_wrap_diffusion_head True, but I'm getting the following error.

TypeError: linear(): argument 'input' (position 1) must be Tensor, not NoneType

Can you help me?

Sign up or log in to comment