Skip to content
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.

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

Added SPADE functionality on the decode call for the sample methods. #441

Conversation

virginiafdez
Copy link
Contributor

Added partial to SPADE autoencoder in the sample methods.

Comment on lines 384 to 388
call = (
partial(super().__call__, seg=seg)
if isinstance(diffusion_model, SPADEDiffusionModelUNet)
else super().__call__
)
Copy link
Member

Choose a reason for hiding this comment

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

Suggested change
call = (
partial(super().__call__, seg=seg)
if isinstance(diffusion_model, SPADEDiffusionModelUNet)
else super().__call__
)
call = super().__call__
if isinstance(diffusion_model, SPADEDiffusionModelUNet):
call = partial(call, seg=seg)

I feel once a if-else expression is multi-line you should use an if statement instead.

Comment on lines 462 to 467
decode = (
partial(autoencoder_model.decode_stage_2_outputs, seg=seg)
if isinstance(autoencoder_model, SPADEAutoencoderKL)
else autoencoder_model.decode_stage_2_outputs
)
image = decode(latent / self.scale_factor)
Copy link
Member

Choose a reason for hiding this comment

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

Same idea here.

@marksgraham marksgraham merged commit 7896dda into main Dec 6, 2023
@marksgraham marksgraham deleted the 440-addition-of-spadeautoencoder-case-to-controlnet-and-normal-latentdiffusioninferer branch December 6, 2023 14:45
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Addition of SPADEAutoencoder case to ControlNet and normal LatentDiffusionInferer
3 participants