RuntimeError: One of the differentiated Tensors does not require grad

cloneofsimo / lora

Using Low-rank adaptation to quickly fine-tune diffusion models.

https://arxiv.org/abs/2106.09685

Apache License 2.0

6.83k stars 473 forks source link

RuntimeError: One of the differentiated Tensors does not require grad #253

Open void-jw opened 1 year ago

void-jw commented 1 year ago

I was trying to apply this repo to another SD implementation, basically following here.

However, I am getting the above error msg and I wonder how to fix it.

Thanks in advance!

CreamyLong commented 1 year ago

I have the same issue, do anyone figure it out?

Haodong-Alex-Yao commented 11 months ago

Same here. Please let me know if you have resolved it. Thanks.

Little-Podi commented 11 months ago

For SD project, set use_checkpoint as False can solve this issue. It won't affect the performance, but may increase your GPU memory requirement a little bit.