Skip to content

Use default torch device for wrapper fallback rng #87

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
Beinsezii merged 1 commit into from
Apr 14, 2026
Merged

Use default torch device for wrapper fallback rng #87

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
2 changes: 1 addition & 1 deletion skrample/diffusers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,7 +307,7 @@ def get_step_noise[T: TensorNoiseProps | None](
# multiply by step index to spread the values and minimize clash
# does not work across batch sizes but at least Flux will have something mostly deterministic
seeds = [
torch.Generator().manual_seed(
torch.Generator(torch.get_default_device()).manual_seed(
int(b.reshape(b.numel())[b.numel() // 2].item() * 1e4 * (step.position() + 1))
)
for b in sample
Expand Down
Loading