Fix dimensionalities in `apply_rotary_emb` functions' comments (#11717)

Fix dimensionality in `apply_rotary_emb` functions' comments.

src/diffusers/models/embeddings.py

@@ -1199,11 +1199,11 @@ def apply_rotary_emb(
 
         if use_real_unbind_dim == -1:
             # Used for flux, cogvideox, hunyuan-dit
-            x_real, x_imag = x.reshape(*x.shape[:-1], -1, 2).unbind(-1)  # [B, S, H, D//2]
+            x_real, x_imag = x.reshape(*x.shape[:-1], -1, 2).unbind(-1)  # [B, H, S, D//2]
             x_rotated = torch.stack([-x_imag, x_real], dim=-1).flatten(3)
         elif use_real_unbind_dim == -2:
             # Used for Stable Audio, OmniGen, CogView4 and Cosmos
-            x_real, x_imag = x.reshape(*x.shape[:-1], 2, -1).unbind(-2)  # [B, S, H, D//2]
+            x_real, x_imag = x.reshape(*x.shape[:-1], 2, -1).unbind(-2)  # [B, H, S, D//2]
             x_rotated = torch.cat([-x_imag, x_real], dim=-1)
         else:
             raise ValueError(f"`use_real_unbind_dim={use_real_unbind_dim}` but should be -1 or -2.")

src/diffusers/models/transformers/transformer_ltx.py

@@ -481,7 +481,7 @@ class LTXVideoTransformer3DModel(ModelMixin, ConfigMixin, FromOriginalModelMixin
 
 def apply_rotary_emb(x, freqs):
     cos, sin = freqs
-    x_real, x_imag = x.unflatten(2, (-1, 2)).unbind(-1)  # [B, S, H, D // 2]
+    x_real, x_imag = x.unflatten(2, (-1, 2)).unbind(-1)  # [B, S, C // 2]
     x_rotated = torch.stack([-x_imag, x_real], dim=-1).flatten(2)
     out = (x.float() * cos + x_rotated.float() * sin).to(x.dtype)
     return out