Skip to content

Inferer modification - save_intermediates clashes with latent shape adjustment in latent diffusion inferers #8343

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
merged 11 commits into from
Feb 18, 2025
Merged

Inferer modification - save_intermediates clashes with latent shape adjustment in latent diffusion inferers #8343

Changes from 3 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
08aef50
There was a bug in the LatentDiffusionInferer and ControlnetLatentDif…
Feb 14, 2025
e5aa008
There was a bug in the LatentDiffusionInferer and ControlnetLatentDif…
Feb 14, 2025
d664f3d
Merge branch 'Project-MONAI:dev' into inferer_modification
virginiafdez Feb 17, 2025
ae32d2e
Added tests for new functionality.
Feb 18, 2025
52de9a7
Added tests for new functionality.
Feb 18, 2025
0f5609e
Added tests for new functionality.
Feb 18, 2025
2e4424e
Merge remote-tracking branch 'origin/inferer_modification' into infer…
Feb 18, 2025
22e21fe
Update monai/inferers/inferer.py
KumoLiu Feb 18, 2025
83e3dd6
Update monai/inferers/inferer.py
KumoLiu Feb 18, 2025
4a985da
Remove debugging related print statements.
Feb 18, 2025
f4dc28e
Merge remote-tracking branch 'origin/inferer_modification' into infer…
Feb 18, 2025
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
16 changes: 10 additions & 6 deletions monai/inferers/inferer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1202,9 +1202,11 @@ def sample( # type: ignore[override]

if self.autoencoder_latent_shape is not None:
latent = torch.stack([self.autoencoder_resizer(i) for i in decollate_batch(latent)], 0)
latent_intermediates = [
torch.stack([self.autoencoder_resizer(i) for i in decollate_batch(l)], 0) for l in latent_intermediates
]
if save_intermediates:
latent_intermediates = [
torch.stack([self.autoencoder_resizer(i) for i in decollate_batch(l)], 0)
for l in latent_intermediates
]

decode = autoencoder_model.decode_stage_2_outputs
if isinstance(autoencoder_model, SPADEAutoencoderKL):
Expand Down Expand Up @@ -1727,9 +1729,11 @@ def sample( # type: ignore[override]

if self.autoencoder_latent_shape is not None:
latent = torch.stack([self.autoencoder_resizer(i) for i in decollate_batch(latent)], 0)
latent_intermediates = [
torch.stack([self.autoencoder_resizer(i) for i in decollate_batch(l)], 0) for l in latent_intermediates
]
if save_intermediates:
latent_intermediates = [
torch.stack([self.autoencoder_resizer(i) for i in decollate_batch(l)], 0)
for l in latent_intermediates
]

decode = autoencoder_model.decode_stage_2_outputs
if isinstance(autoencoder_model, SPADEAutoencoderKL):
Expand Down
Loading