comfyui: add VAE 4D-to-5D latent expansion to patch script

dankclaw/apply_qwen21_patch.py

@@ -32,3 +32,21 @@ if os.path.exists(loader):
             with open(loader, "w") as fh:
                 fh.write(lcode)
             print("Applied qwen_image21 arch list patch")
+
+# Patch VAE decode to expand 4D latents to 5D for video VAEs (latent_dim=3)
+sd = "/opt/ComfyUI/comfy/sd.py"
+with open(sd) as fh:
+    sdc = fh.read()
+if "self.latent_dim == 3 and samples_in.ndim == 4" not in sdc:
+    anchor = "        if self.latent_dim == 2 and samples_in.ndim == 5:\n            samples_in = samples_in[:, :, 0]"
+    replacement = (
+        "        if self.latent_dim == 2 and samples_in.ndim == 5:\n"
+        "            samples_in = samples_in[:, :, 0]\n"
+        "        elif self.latent_dim == 3 and samples_in.ndim == 4:\n"
+        "            samples_in = samples_in.unsqueeze(2)"
+    )
+    if anchor in sdc:
+        sdc = sdc.replace(anchor, replacement)
+        with open(sd, "w") as fh:
+            fh.write(sdc)
+        print("Applied VAE 4D-to-5D latent expansion patch")