Skip to content

[Wan2.2 VAE, Qwen-Image-2.1 VAE] Drop redundant input clone in residual up/down blocks #15029

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

Open
luca-888 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[Wan2.2 VAE, Qwen-Image-2.1 VAE] Drop redundant input clone in residual up/down blocks #15029

Show file tree
Hide file tree
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
4 changes: 2 additions & 2 deletions src/diffusers/models/autoencoders/autoencoder_kl_qwenimage21.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -515,7 +515,7 @@ def __init__(self, in_dim, out_dim, dropout, num_res_blocks, temperal_downsample
def forward(self, x, feat_cache=None, feat_idx=None) -> torch.Tensor:
if feat_idx is None:
feat_idx = [0]
x_copy = x.clone()
x_copy = x
for resnet in self.resnets:
x = resnet(x, feat_cache=feat_cache, feat_idx=feat_idx)
if self.downsampler is not None:
Expand Down Expand Up @@ -714,7 +714,7 @@ def forward(self, x, feat_cache=None, feat_idx=None, first_chunk=False) -> torch
Returns:
torch.Tensor: Output tensor
"""
x_copy = x.clone()
x_copy = x

for resnet in self.resnets:
if feat_cache is not None:
Expand Down
4 changes: 2 additions & 2 deletions src/diffusers/models/autoencoders/autoencoder_kl_wan.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -501,7 +501,7 @@ def __init__(self, in_dim, out_dim, dropout, num_res_blocks, temperal_downsample
self.downsampler = None

def forward(self, x, feat_cache=None, feat_idx=[0]) -> torch.Tensor:
x_copy = x.clone()
x_copy = x
for resnet in self.resnets:
x = resnet(x, feat_cache=feat_cache, feat_idx=feat_idx)
if self.downsampler is not None:
Expand Down Expand Up @@ -700,7 +700,7 @@ def forward(self, x, feat_cache=None, feat_idx=[0], first_chunk=False) -> torch.
Returns:
torch.Tensor: Output tensor
"""
x_copy = x.clone()
x_copy = x

for resnet in self.resnets:
if feat_cache is not None:
Expand Down
Loading