Skip to content

fixed a dtype bfloat16 bug in torch_utils.py #10125

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 6 commits into from
Dec 6, 2024
Merged

fixed a dtype bfloat16 bug in torch_utils.py #10125

Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
ac04a9d
fixed a dtype bfloat16 bug in torch_utils.py
zhangp365 Dec 5, 2024
833129f
Merge branch 'main' into main
hlky Dec 5, 2024
7a88918
remove whitespace in torch_utils.py
zhangp365 Dec 5, 2024
d8ca6a8
Update src/diffusers/utils/torch_utils.py
hlky Dec 5, 2024
8141aa6
Merge branch 'huggingface:main' into main
zhangp365 Dec 6, 2024
e25f141
Update torch_utils.py
hlky Dec 6, 2024
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
7 changes: 2 additions & 5 deletions src/diffusers/utils/torch_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,11 +98,8 @@ def fourier_filter(x_in: "torch.Tensor", threshold: int, scale: int) -> "torch.T
"""
x = x_in
B, C, H, W = x.shape

# Non-power of 2 images must be float32
if (W & (W - 1)) != 0 or (H & (H - 1)) != 0:
x = x.to(dtype=torch.float32)

x = x.to(dtype=torch.float32)

# FFT
x_freq = fftn(x, dim=(-2, -1))
x_freq = fftshift(x_freq, dim=(-2, -1))
Expand Down