AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

Avoid computing min() that is expensive when do_normalize is False in the image processor (#5896)

Browse Source 
Avoid computing min() that is expensive when do_normalize is False

Avoid extra computing when do_normalize is False
This commit is contained in:
Iván de Prado
2023-11-27 12:46:26 +01:00
committed by GitHub
parent c7bfb8b22a
commit c079cae3d4
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/diffusers/image_processor.py
View File

@@ -326,7 +326,7 @@ class VaeImageProcessor(ConfigMixin):
# expected range [0,1], normalize to [-1,1]
do_normalize = self.config.do_normalize
if image.min() < 0 and do_normalize:
if do_normalize and image.min() < 0:
warnings.warn(
"Passing `image` as torch tensor with value range in [-1,1] is deprecated. The expected value range for image tensor is [0,1] "
f"when passing as pytorch tensor or numpy Array. You passed `image` with value range [{image.min()},{image.max()}]",