We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
I'm trying to run inject_trainable_lora_extended on a UNet2DConditionModel, with Conv2d as the target module:
inject_trainable_lora_extended
UNet2DConditionModel
Conv2d
from lora_diffusion.lora import inject_trainable_lora_extended rank = 4 unet = UNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="unet", torch_dtype=torch.float16, ) unet_lora_params, _ = inject_trainable_lora_extended( unet, target_replace_module=["Conv2d"], r=rank, ) unet_lora_params
I get the following error however: RecursionError: maximum recursion depth exceeded while calling a Python object.
RecursionError: maximum recursion depth exceeded while calling a Python object
Best to reimplement as a for loop to avoid recursion depth bug?
The text was updated successfully, but these errors were encountered:
No branches or pull requests
I'm trying to run
inject_trainable_lora_extended
on aUNet2DConditionModel
, withConv2d
as the target module:I get the following error however:
RecursionError: maximum recursion depth exceeded while calling a Python object
.Best to reimplement as a for loop to avoid recursion depth bug?
The text was updated successfully, but these errors were encountered: