Address code review feedback: fix formatting and clarify messages

Co-authored-by: hsliuustc0106 <222337142+hsliuustc0106@users.noreply.github.com>

examples/offline_inference/ltx2/text_to_video.py

@@ -66,7 +66,8 @@ def main():
         if hasattr(first_item, "final_output_type"):
             if first_item.final_output_type != "image":
                 raise ValueError(
-                    f"Unexpected output type '{first_item.final_output_type}', expected 'image' for video generation."
+                    f"Unexpected output type '{first_item.final_output_type}', "
+                    f"expected 'image' for video frames output."
                 )
 
             # Pipeline mode: extract from nested request_output

vllm_omni/diffusion/models/ltx2/pipeline_ltx2.py

@@ -55,9 +55,8 @@ def get_ltx2_pre_process_func(
 
 
 class LTX2Pipeline(nn.Module):
-    """
-    Wrapper for Lightricks LTX-2 text-to-video pipeline.
-    
+    """Wrapper for Lightricks LTX-2 text-to-video pipeline.
+
     This model uses the diffusers LTXVideoPipeline for efficient video generation.
     Supports text-to-video and image-to-video generation.
     """
@@ -105,9 +104,8 @@ class LTX2Pipeline(nn.Module):
         generator: Optional[torch.Generator] = None,
         **kwargs,
     ) -> DiffusionOutput:
-        """
-        Generate video from text prompt.
-        
+        """Generate video from text prompt.
+
         Args:
             req: OmniDiffusionRequest containing generation parameters
             prompt: Text prompt for video generation
@@ -120,7 +118,7 @@ class LTX2Pipeline(nn.Module):
             output_type: Output format ("np", "pt", or "pil")
             generator: Random generator for reproducibility
             **kwargs: Additional arguments passed to the pipeline
-            
+
         Returns:
             DiffusionOutput containing the generated video frames
         """

vllm_omni/diffusion/registry.py

@@ -105,7 +105,7 @@ def initialize_model(
     if model_class is not None:
         model = model_class(od_config=od_config)
         # Configure VAE memory optimization settings from config
-        # For pipelines that wrap diffusers pipelines (like LTX2Pipeline), 
+        # For pipelines that wrap diffusers pipelines (like LTX2Pipeline),
         # VAE is accessed via model.pipe.vae
         vae = None
         if hasattr(model, "vae"):