Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Adding default alpha when splitting RGB images

MoonRide303585fb0475bba
diff --git a/comfy_extras/nodes_compositing.py b/comfy_extras/nodes_compositing.py
index 6899e4a86..b0ae2dfa0 100644
--- a/comfy_extras/nodes_compositing.py
+++ b/comfy_extras/nodes_compositing.py
@@ -153,7 +153,7 @@ class SplitImageWithAlpha:
def split_image_with_alpha(self, image: torch.Tensor):
out_images = [i[:,:,:3] for i in image]
- out_alphas = [i[:,:,3] for i in image]
+ out_alphas = [i[:,:,3] if i.shape[2] > 3 else torch.ones_like(i[:,:,0]) for i in image]
result = (torch.stack(out_images), torch.stack(out_alphas))
return result