Update api/ltx_server_refactored_complete.py

api/ltx_server_refactored_complete.py

@@ -243,6 +243,37 @@ class VideoService:
     # --- UNIDADES DE TRABALHO E HELPERS INTERNOS ---
     # ==========================================================================
 
+    # --- NOVA FUNÇÃO DE LOG DEDICADA ---
+    def _log_conditioning_items(self, items: List[ConditioningItem]):
+        """
+        Logs detailed information about a list of ConditioningItem objects.
+        This is a dedicated debug helper function.
+        """
+        # Só imprime o log se o nível de logging for DEBUG
+        if logging.getLogger().isEnabledFor(logging.INFO):
+            log_str = ["\n" + "="*25 + " INFO: Conditioning Items " + "="*25]
+            if not items:
+                log_str.append("  -> Lista de conditioning_items está vazia.")
+            else:
+                for i, item in enumerate(items):
+                    if hasattr(item, 'media_item') and isinstance(item.media_item, torch.Tensor):
+                        t = item.media_item
+                        log_str.append(
+                            f"  -> Item [{i}]: "
+                            f"Tensor(shape={list(t.shape)}, "
+                            f"device='{t.device}', "
+                            f"dtype={t.dtype}), "
+                            f"Target Frame = {item.media_frame_number}, "
+                            f"Strength = {item.conditioning_strength:.2f}"
+                        )
+                    else:
+                        log_str.append(f"  -> Item [{i}]: Não contém um tensor válido.")
+            log_str.append("="*75 + "\n")
+            
+            # Usa o logger de debug para imprimir a mensagem completa
+            logging.info("\n".join(log_str))
+
+
     @log_function_io
     def _generate_single_chunk_low(self, **kwargs) -> Optional[torch.Tensor]:
         """[WORKER] Calls the pipeline to generate a single chunk of latents."""
@@ -260,11 +291,17 @@ class VideoService:
             "prompt": kwargs['prompt'], "negative_prompt": kwargs['negative_prompt'],
             "height": downscaled_height, "width": downscaled_width, "num_frames": kwargs['num_frames'],
             "frame_rate": DEFAULT_FPS, "generator": torch.Generator(device=self.main_device).manual_seed(kwargs['seed']),
-            "output_type": "latent", "conditioning_items": kwargs['conditioning_items'], **first_pass_config
+            "output_type": "latent", **first_pass_config
         }
+
+        logging.info(f"\n[Info] pipeline_kwargs:\n {pipeline_kwargs}\n\n")
+        self._log_conditioning_items(kwargs['conditioning_items'])
         
         with torch.autocast(device_type=self.main_device.type, dtype=self.runtime_autocast_dtype, enabled="cuda" in self.main_device.type):
-            latents_raw = self.pipeline(**pipeline_kwargs).images
+            latents_raw = self.pipeline(
+                "conditioning_items": kwargs['conditioning_items']
+                **pipeline_kwargs
+        ).images
         
         return latents_raw.to(self.main_device)