xinyun/ComfyUI
1
0
Fork 0
mirror of https://git.datalinker.icu/comfyanonymous/ComfyUI synced 2025-12-09 05:54:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

Make Batch Images node add alpha channel when one of the inputs has it (#10816)

Browse Source 
* When one Batch Image input has alpha and one does not, add empty alpha channel

* Use torch.nn.functional.pad
This commit is contained in:
Jedrzej Kosinski 2025-11-20 14:42:46 -08:00 committed by GitHub
parent f5e66d5e47
commit 9e00ce5b76
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
nodes.py
View File

@ -1853,9 +1853,10 @@ class ImageBatch:
def batch(self, image1, image2): def batch(self, image1, image2):
if image1.shape[-1] != image2.shape[-1]: if image1.shape[-1] != image2.shape[-1]:
channels = min(image1.shape[-1], image2.shape[-1]) if image1.shape[-1] > image2.shape[-1]:
image1 = image1[..., :channels] image2 = torch.nn.functional.pad(image2, (0,1), mode='constant', value=1.0)
image2 = image2[..., :channels] else:
image1 = torch.nn.functional.pad(image1, (0,1), mode='constant', value=1.0)
if image1.shape[1:] != image2.shape[1:]: if image1.shape[1:] != image2.shape[1:]:
image2 = comfy.utils.common_upscale(image2.movedim(-1,1), image1.shape[2], image1.shape[1], "bilinear", "center").movedim(1,-1) image2 = comfy.utils.common_upscale(image2.movedim(-1,1), image1.shape[2], image1.shape[1], "bilinear", "center").movedim(1,-1)
s = torch.cat((image1, image2), dim=0) s = torch.cat((image1, image2), dim=0)