Make LatentCompositeMasked work with basic video latents. (#10023)

comfy_extras/nodes_mask.py

@@ -12,35 +12,38 @@ from nodes import MAX_RESOLUTION
 def composite(destination, source, x, y, mask = None, multiplier = 8, resize_source = False):
     source = source.to(destination.device)
     if resize_source:
-        source = torch.nn.functional.interpolate(source, size=(destination.shape[2], destination.shape[3]), mode="bilinear")
+        source = torch.nn.functional.interpolate(source, size=(destination.shape[-2], destination.shape[-1]), mode="bilinear")
 
     source = comfy.utils.repeat_to_batch_size(source, destination.shape[0])
 
-    x = max(-source.shape[3] * multiplier, min(x, destination.shape[3] * multiplier))
-    y = max(-source.shape[2] * multiplier, min(y, destination.shape[2] * multiplier))
+    x = max(-source.shape[-1] * multiplier, min(x, destination.shape[-1] * multiplier))
+    y = max(-source.shape[-2] * multiplier, min(y, destination.shape[-2] * multiplier))
 
     left, top = (x // multiplier, y // multiplier)
-    right, bottom = (left + source.shape[3], top + source.shape[2],)
+    right, bottom = (left + source.shape[-1], top + source.shape[-2],)
 
     if mask is None:
         mask = torch.ones_like(source)
     else:
         mask = mask.to(destination.device, copy=True)
-        mask = torch.nn.functional.interpolate(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(source.shape[2], source.shape[3]), mode="bilinear")
+        mask = torch.nn.functional.interpolate(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(source.shape[-2], source.shape[-1]), mode="bilinear")
         mask = comfy.utils.repeat_to_batch_size(mask, source.shape[0])
 
     # calculate the bounds of the source that will be overlapping the destination
     # this prevents the source trying to overwrite latent pixels that are out of bounds
     # of the destination
-    visible_width, visible_height = (destination.shape[3] - left + min(0, x), destination.shape[2] - top + min(0, y),)
+    visible_width, visible_height = (destination.shape[-1] - left + min(0, x), destination.shape[-2] - top + min(0, y),)
 
     mask = mask[:, :, :visible_height, :visible_width]
+    if mask.ndim < source.ndim:
+        mask = mask.unsqueeze(1)
+
     inverse_mask = torch.ones_like(mask) - mask
 
-    source_portion = mask * source[:, :, :visible_height, :visible_width]
-    destination_portion = inverse_mask  * destination[:, :, top:bottom, left:right]
+    source_portion = mask * source[..., :visible_height, :visible_width]
+    destination_portion = inverse_mask  * destination[..., top:bottom, left:right]
 
-    destination[:, :, top:bottom, left:right] = source_portion + destination_portion
+    destination[..., top:bottom, left:right] = source_portion + destination_portion
     return destination
 
 class LatentCompositeMasked: