Skip to content

Don't add tiny bit of random noise when VAE encoding. #8705

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
comfyanonymous merged 1 commit into from
Jun 27, 2025
Merged

Don't add tiny bit of random noise when VAE encoding. #8705

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
8 changes: 2 additions & 6 deletions comfy/ldm/models/autoencoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,24 +11,20 @@
import comfy.ops

class DiagonalGaussianRegularizer(torch.nn.Module):
def __init__(self, sample: bool = True):
def __init__(self, sample: bool = False):
super().__init__()
self.sample = sample

def get_trainable_parameters(self) -> Any:
yield from ()

def forward(self, z: torch.Tensor) -> Tuple[torch.Tensor, dict]:
log = dict()
posterior = DiagonalGaussianDistribution(z)
if self.sample:
z = posterior.sample()
else:
z = posterior.mode()
kl_loss = posterior.kl()
kl_loss = torch.sum(kl_loss) / kl_loss.shape[0]
log["kl_loss"] = kl_loss
return z, log
return z, None


class AbstractAutoencoder(torch.nn.Module):
Expand Down