Skip to content

Conditionally import torchvision in Cosmos transformer #11524

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 1 commit into from
May 8, 2025
Merged

Conditionally import torchvision in Cosmos transformer #11524

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
6 changes: 5 additions & 1 deletion src/diffusers/models/transformers/transformer_cosmos.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,9 @@
import torch
import torch.nn as nn
import torch.nn.functional as F
from torchvision import transforms

from ...configuration_utils import ConfigMixin, register_to_config
from ...utils import is_torchvision_available
from ..attention import FeedForward
from ..attention_processor import Attention
from ..embeddings import Timesteps
Expand All @@ -29,6 +29,10 @@
from ..normalization import RMSNorm


if is_torchvision_available():
from torchvision import transforms


class CosmosPatchEmbed(nn.Module):
def __init__(
self, in_channels: int, out_channels: int, patch_size: Tuple[int, int, int], bias: bool = True
Expand Down
Loading