Merge 222b2e3b37a86128b06208309fed84ba10f88640 into fdb8abd2790b5459ddc7066c31861bb0b62e988b

Update minimal diffusers version

.github/workflows/publish.yml

@@ -8,17 +8,19 @@ on:
     paths:
       - "pyproject.toml"
 
+permissions:
+  issues: write
+
 jobs:
   publish-node:
     name: Publish Custom Node to registry
     runs-on: ubuntu-latest
-    # if this is a forked repository. Skipping the workflow.
-    if: github.event.repository.fork == false 
+    if: ${{ github.repository_owner == 'kijai' }}
     steps:
       - name: Check out code
         uses: actions/checkout@v4
       - name: Publish Custom Node
-        uses: Comfy-Org/publish-node-action@main
+        uses: Comfy-Org/publish-node-action@v1
         with:
           ## Add your own personal access token to your Github Repository secrets and reference it here.
           personal_access_token: ${{ secrets.REGISTRY_ACCESS_TOKEN }}

embeddings.py

@@ -67,8 +67,9 @@ class CogVideoXPatchEmbed(nn.Module):
             post_time_compression_frames,
             self.spatial_interpolation_scale,
             self.temporal_interpolation_scale,
+            output_type="pt",
         )
-        pos_embedding = torch.from_numpy(pos_embedding).flatten(0, 1)
+        pos_embedding = pos_embedding.flatten(0, 1)
         joint_pos_embedding = torch.zeros(
             1, self.max_text_seq_length + num_patches, self.embed_dim, requires_grad=False
         )
@@ -173,6 +174,8 @@ def get_3d_rotary_pos_embed(
         grid_t = np.arange(temporal_size, dtype=np.float32)
         grid_t = np.linspace(0, temporal_size, temporal_size, endpoint=False, dtype=np.float32)
     elif grid_type == "slice":
+        if max_size is None:
+            raise ValueError("`max_size` must be provided when `grid_type` is 'slice'")
         max_h, max_w = max_size
         grid_size_h, grid_size_w = grid_size
         grid_h = np.arange(max_h, dtype=np.float32)

requirements.txt

@@ -1,5 +1,5 @@
 huggingface_hub
-diffusers>=0.31.0
+diffusers>=0.33.1
 accelerate>=0.33.0
 einops
 peft