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.

Backward compatibility patch for changes in the method signature of `InpaintModelConditioning`. (#5825)

Dr.Lt.Data82c530856162
diff --git a/nodes.py b/nodes.py
index cc21181b5..6907bd4de 100644
--- a/nodes.py
+++ b/nodes.py
@@ -392,7 +392,7 @@ class InpaintModelConditioning:
CATEGORY = "conditioning/inpaint"
- def encode(self, positive, negative, pixels, vae, mask, noise_mask):
+ def encode(self, positive, negative, pixels, vae, mask, noise_mask=True):
x = (pixels.shape[1] // 8) * 8
y = (pixels.shape[2] // 8) * 8
mask = torch.nn.functional.interpolate(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(pixels.shape[1], pixels.shape[2]), mode="bilinear")