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

Convert RGB to BGR for the SDXL watermark encoder (#7013)

Browse Source 
* Convert channel order to BGR for the watermark encoder. Convert the watermarked BGR images back to RGB. Fixes #6292

* Revert channel order before stacking images to overcome limitations that negative strides are currently not supported

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
This commit is contained in:
btlorch
2024-04-26 02:44:53 +02:00
committed by GitHub
parent fa750a15bd
commit ebc99a77aa
1 changed files with 8 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/diffusers/pipelines/stable_diffusion_xl/watermark.py
View File

@@ -28,9 +28,15 @@ class StableDiffusionXLWatermarker:
images = (255 * (images / 2 + 0.5)).cpu().permute(0, 2, 3, 1).float().numpy()
images = [self.encoder.encode(image, "dwtDct") for image in images]
# Convert RGB to BGR, which is the channel order expected by the watermark encoder.
images = images[:, :, :, ::-1]
images = torch.from_numpy(np.array(images)).permute(0, 3, 1, 2)
# Add watermark and convert BGR back to RGB
images = [self.encoder.encode(image, "dwtDct")[:, :, ::-1] for image in images]
images = np.array(images)
images = torch.from_numpy(images).permute(0, 3, 1, 2)
images = torch.clamp(2 * (images / 255 - 0.5), min=-1.0, max=1.0)
return images