Skip to content

Fix AsymmetricAutoencoderKL forward #8378

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

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

Merged
yiyixuxu merged 1 commit into from
Jun 4, 2024
Merged

Fix AsymmetricAutoencoderKL forward #8378

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/diffusers/models/autoencoders/autoencoder_asym_kl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,7 +176,7 @@ def forward(
z = posterior.sample(generator=generator)
else:
z = posterior.mode()
dec = self.decode(z, sample, mask).sample
dec = self.decode(z, generator, sample, mask).sample
Copy link
Member

@sayakpaul sayakpaul Jun 3, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Tend to agree with @tolgacangoz's comments here. It's not used in the decode() function. Similar to AutoencoderKL. It's used in the forward():

diffusers/src/diffusers/models/autoencoders/autoencoder_kl.py

Line 445 in 4136044

z = posterior.sample(generator=generator)

Copy link
Member

@sayakpaul sayakpaul Jun 3, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't think there's a stochastic component in the decode() function in the first place. So, I further think there's no need to have generator in here too:

diffusers/src/diffusers/models/autoencoders/autoencoder_kl.py

Line 286 in 4136044

def decode(self, z: torch.Tensor, return_dict: bool = True, generator=None) -> Union[DecoderOutput, torch.Tensor]:

@yiyixuxu WDYT here?

Copy link
Contributor Author

@townwish4git townwish4git Jun 3, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

i think this comment answered the question:
https://github.com/huggingface/diffusers/pull/5694/files#r1387349283

Copy link
Collaborator

@yiyixuxu yiyixuxu Jun 3, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@sayakpaul I had the same questions, but their explanation makes sense I think


if not return_dict:
return (dec,)
Expand Down