Ensure input tensor is on the same device as model weights in FrozenOpenCLIPEmbedder. This change improves compatibility and performance by preventing device mismatch during image encoding.

imagedream/ldm/modules/encoders/modules.py

@@ -243,6 +243,8 @@ class FrozenOpenCLIPEmbedder(AbstractEncoder, nn.Module):
     
     def encode_image_with_transformer(self, x):
         visual = self.model.visual
+        # Ensure x is on the same device as the model weights
+        x = x.to(visual.conv1.weight.device)
         x = visual.conv1(x)  # shape = [*, width, grid, grid]
         x = x.reshape(x.shape[0], x.shape[1], -1)  # shape = [*, width, grid ** 2]
         x = x.permute(0, 2, 1)  # shape = [*, grid ** 2, width]