Update api/ltx/ltx_aduc_pipeline.py

api/ltx/ltx_aduc_pipeline.py

@@ -232,8 +232,12 @@ class LtxAducPipeline:
         if kwargs.get("ltx_configs_override"):
             self._apply_ui_overrides(first_pass_config, kwargs.get("ltx_configs_override"))
 
+        
         # 3. Monta o dicionário de argumentos SEM conditioning_items primeiro
         pipeline_kwargs = {
+            "num_inference_steps": first_pass_config.get("num_inference_steps"),
+            "skip_final_inference_steps": first_pass_config.get("skip_final_inference_steps")
+            'cfg_star_rescale": "true",
             "prompt": kwargs['prompt'],
             "negative_prompt": kwargs['negative_prompt'],
             "height": downscaled_height,
@@ -242,25 +246,18 @@ class LtxAducPipeline:
             "frame_rate": int(DEFAULT_FPS),
             "generator": torch.Generator(device=self.main_device).manual_seed(kwargs['seed']),
             "output_type": "latent",
-            #"conditioning_items": conditioning_items if conditioning_items else None,
             "media_items": None,
             "decode_timestep": self.config["decode_timestep"],
             "decode_noise_scale": self.config["decode_noise_scale"],
             "stochastic_sampling": self.config["stochastic_sampling"],
-            "image_cond_noise_scale": 0.01,
+            "image_cond_noise_scale": 0.05,
             "is_video": True,
             "vae_per_channel_normalize": True,
             "mixed_precision": (self.config["precision"] == "mixed_precision"),
             "offload_to_cpu": False,
             "enhance_prompt": False,
-            #"skip_layer_strategy": SkipLayerStrategy.AttentionValues,
-            **first_pass_config
         }
-        
-        # --- Bloco de Logging para Depuração ---
-        # 4. Loga os argumentos do pipeline (sem os tensores de condição)
-        logging.info(f"\n[Info] Pipeline Arguments (BASE):\n {json.dumps(pipeline_kwargs, indent=2, default=str)}\n")
-        
+                
         # Loga os conditioning_items separadamente com a nossa função helper
         conditioning_items_list = kwargs.get('conditioning_items')
         self._log_conditioning_items(conditioning_items_list)