Skip to content

[Modular] Fix dtype assignment when type hint is AutoModel #13271

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
DN6 merged 2 commits into from
Mar 17, 2026
Merged

[Modular] Fix dtype assignment when type hint is AutoModel #13271

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0d87803
update
DN6 Mar 16, 2026
514dd55
update
DN6 Mar 16, 2026
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
12 changes: 3 additions & 9 deletions src/diffusers/modular_pipelines/modular_pipeline_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -309,16 +309,16 @@ def load(self, **kwargs) -> Any:
f"`type_hint` is required when loading a single file model but is missing for component: {self.name}"
)

from diffusers import AutoModel

# `torch_dtype` is not an accepted parameter for tokenizers and processors.
# As a result, it gets stored in `init_kwargs`, which are written to the config
# during save. This causes JSON serialization to fail when saving the component.
if self.type_hint is not None and not issubclass(self.type_hint, torch.nn.Module):
if self.type_hint is not None and not issubclass(self.type_hint, (torch.nn.Module, AutoModel)):
kwargs.pop("torch_dtype", None)

if self.type_hint is None:
try:
from diffusers import AutoModel
Copy link
Collaborator Author

@DN6 DN6 Mar 16, 2026

Choose a reason for hiding this comment

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

Moved this up because now we need to import AutoModel regardless of whether type_hint is provided or not.


component = AutoModel.from_pretrained(pretrained_model_name_or_path, **load_kwargs, **kwargs)
except Exception as e:
raise ValueError(f"Unable to load {self.name} without `type_hint`: {e}")
Expand All @@ -332,12 +332,6 @@ def load(self, **kwargs) -> Any:
else getattr(self.type_hint, "from_pretrained")
)

# `torch_dtype` is not an accepted parameter for tokenizers and processors.
# As a result, it gets stored in `init_kwargs`, which are written to the config
# during save. This causes JSON serialization to fail when saving the component.
if not issubclass(self.type_hint, torch.nn.Module):
kwargs.pop("torch_dtype", None)

try:
component = load_method(pretrained_model_name_or_path, **load_kwargs, **kwargs)
except Exception as e:
Expand Down
Loading