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.

LTXV: fix key frame noise mask dimensions for when real noise mask exists (#9425)

Harel Cainfe01885acf89
diff --git a/comfy_extras/nodes_lt.py b/comfy_extras/nodes_lt.py
index b5058667a..f82337a67 100644
--- a/comfy_extras/nodes_lt.py
+++ b/comfy_extras/nodes_lt.py
@@ -166,7 +166,7 @@ class LTXVAddGuide:
negative = self.add_keyframe_index(negative, frame_idx, guiding_latent, scale_factors)
mask = torch.full(
- (noise_mask.shape[0], 1, guiding_latent.shape[2], 1, 1),
+ (noise_mask.shape[0], 1, guiding_latent.shape[2], noise_mask.shape[3], noise_mask.shape[4]),
1.0 - strength,
dtype=noise_mask.dtype,
device=noise_mask.device,