Skip to content

add post init for safty checker #12794

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
sayakpaul merged 4 commits into from
Dec 8, 2025
+4 −1
Merged

add post init for safty checker #12794

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0961a03
add post init for safty checker
jiqing-feng Dec 5, 2025
b026e0e
Merge branch 'main' into post
jiqing-feng Dec 8, 2025
80df03d
check transformers version before post init
jiqing-feng Dec 8, 2025
312e0fb
Apply style fixes
github-actions[bot] Dec 8, 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
1 change: 1 addition & 0 deletions src/diffusers/pipelines/stable_diffusion/safety_checker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,7 @@ def __init__(self, config: CLIPConfig):

self.concept_embeds_weights = nn.Parameter(torch.ones(17), requires_grad=False)
self.special_care_embeds_weights = nn.Parameter(torch.ones(3), requires_grad=False)
self.post_init()
Copy link
Member

@sayakpaul sayakpaul Dec 5, 2025

Choose a reason for hiding this comment

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

Should we condition this based on the transformers version being used?

Copy link
Contributor Author

@jiqing-feng jiqing-feng Dec 8, 2025

Choose a reason for hiding this comment

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

Maybe better to use try except?

Copy link
Member

@sayakpaul sayakpaul Dec 8, 2025

Choose a reason for hiding this comment

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

IMO, opinion it's better to be explicit about conditioning with versioning since we know that it's a versioning problem.

Copy link
Contributor Author

@jiqing-feng jiqing-feng Dec 8, 2025

Choose a reason for hiding this comment

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

OK, done.


@torch.no_grad()
def forward(self, clip_input, images):
Expand Down