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.

Support the 5B fun inpaint model. (#9614)

comfyanonymousc7bb3e2bceaa
diff --git a/comfy_extras/nodes_wan.py b/comfy_extras/nodes_wan.py
index 8c1d36613..4f73369f5 100644
--- a/comfy_extras/nodes_wan.py
+++ b/comfy_extras/nodes_wan.py
@@ -206,7 +206,8 @@ class WanFirstLastFrameToVideo(io.ComfyNode):
@classmethod
def execute(cls, positive, negative, vae, width, height, length, batch_size, start_image=None, end_image=None, clip_vision_start_image=None, clip_vision_end_image=None) -> io.NodeOutput:
- latent = torch.zeros([batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
+ spacial_scale = vae.spacial_compression_encode()
+ latent = torch.zeros([batch_size, vae.latent_channels, ((length - 1) // 4) + 1, height // spacial_scale, width // spacial_scale], device=comfy.model_management.intermediate_device())
if start_image is not None:
start_image = comfy.utils.common_upscale(start_image[:length].movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
if end_image is not None: