Update api/ltx/ltx_aduc_pipeline.py

api/ltx/ltx_aduc_pipeline.py

@@ -25,7 +25,6 @@ from api.ltx.vae_aduc_pipeline import vae_aduc_pipeline
 from tools.video_encode_tool import video_encode_tool_singleton
 
 
-
 # ==============================================================================
 # --- SETUP E IMPORTAÇÕES DO PROJETO ---
 # ==============================================================================
@@ -206,7 +205,7 @@ class LtxAducPipeline:
                 if is_narrative and i < num_chunks - 1:
                     overlap_latents = chunk_latents[:, :, -overlap_frames:, :, :].clone()
                     overlap_condition_item = LatentConditioningItem(
-                        latent_tensor=overlap_latents.cpu(),
+                        latent_tensor=overlap_latents,
                         media_frame_number=0,
                         conditioning_strength=1.0
                     )
@@ -225,10 +224,7 @@ class LtxAducPipeline:
             all_tensors_cpu = [torch.load(p) for p in temp_latent_paths]
             final_latents = torch.cat(all_tensors_cpu, dim=2)
 
-            for path in temp_latent_paths:
-                if path.exists(): path.unlink()
-            self.finalize()
-            
+        
             video_path, latents_path = self._finalize_generation(final_latents, base_filename, used_seed)
             return video_path, latents_path, used_seed
             
@@ -237,37 +233,6 @@ class LtxAducPipeline:
     # --- UNIDADES DE TRABALHO E HELPERS INTERNOS ---
     # ==========================================================================
 
-    @log_function_io
-    def _log_conditioning_items(self, items: List[LatentConditioningItem]):
-        """
-        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" + "="*10 + " INFO: Conditioning Items " + "="*10]
-            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("="*30 + "\n")
-            
-            # Usa o logger de debug para imprimir a mensagem completa
-            logging.info("\n".join(log_str))
-
     @log_function_io
     def _finalize_generation(self, final_latents: torch.Tensor, base_filename: str, seed: int) -> Tuple[str, str]:
         """Delegates final decoding and encoding to specialist services."""
@@ -291,7 +256,8 @@ class LtxAducPipeline:
             if ui_value and ui_value > 0:
                 config_dict[key] = ui_value
                 logging.info(f"Override: '{key}' set to {ui_value} by UI.")
-  
+
+    @log_function_io
     def _save_and_log_video(self, pixel_tensor: torch.Tensor, base_filename: str) -> Path:
         with tempfile.TemporaryDirectory() as temp_dir:
             temp_path = os.path.join(temp_dir, f"{base_filename}.mp4")