Update app.py

app.py

@@ -1,105 +1,129 @@
 # FILE: app.py
 # DESCRIPTION: Final Gradio web interface for the ADUC-SDR Video Suite.
-# This version is refactored to use the central LtxAducOrchestrator, simplifying the UI logic
-# and making it a pure client of the backend services.
+# This version is updated to import from the new modular file structure,
+# including the renamed ADUC pipelines and moved managers.
 
 import gradio as gr
 import traceback
 import sys
 import os
 import logging
-from PIL import Image
+from typing import List
+from PIL import Image as PILImage
 
 # ==============================================================================
-# --- IMPORTAÇÃO DOS SERVIÇOS DE BACKEND E UTILS ---
+# --- IMPORTAÇÃO DOS SERVIÇOS DE BACKEND E UTILS (CAMINHOS ATUALIZADOS) ---
 # ==============================================================================
 
-#try:
-    # --- MUDANÇA PRINCIPAL: Importamos apenas o ORQUESTRADOR ---
-    # O orquestrador é agora nosso único ponto de entrada para a geração de vídeo.
-from api.ltx.ltx_aduc_orchestrator import ltx_aduc_orchestrator
+try:
+    # Importa o serviço principal do seu novo local e nome
+    from api.ltx.ltx_aduc_pipeline import video_generation_service
     
-    # O SeedVR (upscaler de resolução) ainda é um serviço separado que pode ser chamado após a geração.
-from api.seedvr.seedvr_aduc_pipeline import seed_aduc_pipeline
-    
-    # Nosso decorador de logging para depuração
-from utils.debug_utils import log_function_io
-    
-logging.info("All backend services (Orchestrator, SeedVR) and debug utils imported successfully.")
-
+    # Importa o decorador de logging do seu novo local
+    from api.utils.debug_utils import log_function_io
 
+    # A importação do SeedVR permanece a mesma, mas verificamos sua existência
+    from api.seedvr_server import seedvr_server_singleton as seedvr_inference_server
+    
+    logging.info("All backend services and utils imported successfully from new paths.")
+
+except ImportError as e:
+    def log_function_io(func): return func
+    logging.warning(f"Could not import a module. Some services or debug logs may be unavailable. Details: {e}")
+    if 'video_generation_service' not in locals():
+        logging.critical(f"FATAL: Main LTX service (ltx_aduc_pipeline) failed to import.", exc_info=True)
+        sys.exit(1)
+    if 'seedvr_inference_server' not in locals():
+        seedvr_inference_server = None
+        logging.warning("SeedVR server could not be initialized. Upscaling tab will be disabled.")
+except Exception as e:
+    logging.critical(f"FATAL ERROR during backend initialization. Details: {e}", exc_info=True)
+    sys.exit(1)
 
 # ==============================================================================
 # --- FUNÇÕES WRAPPER (PONTE ENTRE UI E BACKEND) ---
 # ==============================================================================
 
 @log_function_io
-def run_orchestrated_generation(
-    prompt: str, start_img_path: str, 
+def run_generate_base_video(
+    prompt: str, neg_prompt: str, start_img: PILImage.Image,
     height: int, width: int, duration: float,
-    fp_guidance_preset: str, fp_guidance_scale_list: str, fp_stg_scale_list: str,
-    fp_num_inference_steps: int,
+    fp_num_inference_steps: int, fp_skip_initial_steps: int, fp_skip_final_steps: int,
     progress=gr.Progress(track_tqdm=True)
 ) -> tuple:
     """
-    Função wrapper simplificada que coleta dados da UI e chama o orquestrador principal.
+    Wrapper final que prepara os dados da UI e chama o backend com a API simplificada.
     """
     try:
-        logging.info("[UI] Request received. Submitting job to the main orchestrator...")
-        
-        # Monta o dicionário de configurações avançadas LTX a partir da UI
+        prompt_list = [p.strip() for p in prompt.splitlines() if p.strip()]
+        if not prompt_list:
+            raise gr.Error("O campo de prompt não pode estar vazio.")
+        logging.info(f"[UI] Request received with {len(prompt_list)} scene(s).")
+
+        initial_media_list = []
+        if start_img:
+            initial_media_list.append((start_img, 0, 1.0))
+
         ltx_configs = {
-            "guidance_preset": fp_guidance_preset,
-            "guidance_scale_list": fp_guidance_scale_list,
-            "stg_scale_list": fp_stg_scale_list,
-            "num_inference_steps": fp_num_inference_steps
+            "num_inference_steps": fp_num_inference_steps,
+            "skip_initial_inference_steps": fp_skip_initial_steps,
+            "skip_final_inference_steps": fp_skip_final_steps,
         }
 
-        # Carrega a imagem inicial para um objeto PIL, que é o que o orquestrador espera.
-        initial_image_pil = Image.open(start_img_path).convert("RGB") if start_img_path else None
-
-        # --- CHAMADA ÚNICA E LIMPA PARA O ORQUESTRADOR ---
-        video_path = ltx_aduc_orchestrator(
-            prompt=prompt,
-            initial_image=initial_image_pil,
-            height=height,
-            width=width,
-            duration_in_seconds=duration,
-            ltx_configs=ltx_configs
+        video_path, tensor_path, final_seed = video_generation_service.generate_low_resolution(
+            prompt_list=prompt_list,
+            negative_prompt=neg_prompt,
+            height=height, width=width, duration=duration,
+            initial_media_items=initial_media_list,
+            ltx_configs_override=ltx_configs
         )
         
-        if not video_path:
-            raise RuntimeError("Orchestrator failed to return a valid video path. Check backend logs for details.")
-
-        logging.info(f"[UI] Orchestrator job successful. Video path: {video_path}")
-        
-        # O estado agora pode ser mais simples, apenas guardando o caminho do vídeo gerado para o próximo passo (SeedVR).
-        new_state = {"low_res_video": video_path}
+        if not video_path: raise RuntimeError("Backend failed to return a valid video path.")
+        new_state = {"low_res_video": video_path, "low_res_latents": tensor_path, "used_seed": final_seed}
+        logging.info(f"[UI] Base video generation successful. Seed used: {final_seed}, Path: {video_path}")
         return video_path, new_state, gr.update(visible=True)
         
     except Exception as e:
-        error_message = f"❌ An error occurred during the orchestrated generation:\n{e}"
+        error_message = f"❌ An error occurred during base generation:\n{e}"
+        logging.error(f"{error_message}\nDetails: {traceback.format_exc()}", exc_info=True)
+        raise gr.Error(error_message)
+
+@log_function_io
+def run_ltx_refinement(state: dict, prompt: str, neg_prompt: str, progress=gr.Progress(track_tqdm=True)) -> tuple:
+    """Wrapper para o refinamento de textura LTX."""
+    if not state or not state.get("low_res_latents"):
+        raise gr.Error("Error: Please generate a base video in Step 1 before refining.")
+    try:
+        logging.info(f"[UI] Requesting LTX refinement for latents: {state.get('low_res_latents')}")
+        video_path, tensor_path = video_generation_service.generate_upscale_denoise(
+            latents_path=state["low_res_latents"],
+            prompt=prompt, negative_prompt=neg_prompt,
+            seed=state["used_seed"]
+        )
+        state["refined_video_ltx"] = video_path
+        state["refined_latents_ltx"] = tensor_path
+        logging.info(f"[UI] LTX refinement successful. Path: {video_path}")
+        return video_path, state
+    except Exception as e:
+        error_message = f"❌ An error occurred during LTX Refinement:\n{e}"
         logging.error(f"{error_message}\nDetails: {traceback.format_exc()}", exc_info=True)
         raise gr.Error(error_message)
 
 
 @log_function_io
 def run_seedvr_upscaling(state: dict, seed: int, resolution: int, batch_size: int, fps: int, progress=gr.Progress(track_tqdm=True)) -> tuple:
-    """Wrapper para o upscale de resolução SeedVR. Esta função permanece a mesma."""
+    """Wrapper para o upscale de resolução SeedVR."""
     if not state or not state.get("low_res_video"):
         raise gr.Error("Error: Please generate a base video in Step 1 before upscaling.")
-    if not seed_aduc_pipeline:
+    if not seedvr_inference_server:
         raise gr.Error("Error: The SeedVR upscaling server is not available.")
-    
     try:
         logging.info(f"[UI] Requesting SeedVR upscaling for video: {state.get('low_res_video')}")
         def progress_wrapper(p, desc=""): progress(p, desc=desc)
-        
-        output_filepath = seed_aduc_pipeline.run_inference(
+        output_filepath = seedvr_inference_server.run_inference(
             file_path=state["low_res_video"], seed=int(seed), resolution=int(resolution),
             batch_size=int(batch_size), fps=float(fps), progress=progress_wrapper
         )
-        
         status_message = f"✅ Upscaling complete!\nSaved to: {output_filepath}"
         logging.info(f"[UI] SeedVR upscaling successful. Path: {output_filepath}")
         return gr.update(value=output_filepath), gr.update(value=status_message)
@@ -115,50 +139,56 @@ def run_seedvr_upscaling(state: dict, seed: int, resolution: int, batch_size: in
 def build_ui():
     """Constrói a interface completa do Gradio."""
     with gr.Blocks(theme=gr.themes.Soft(primary_hue="indigo")) as demo:
-        app_state = gr.State(value={"low_res_video": None})
+        app_state = gr.State(value={"low_res_video": None, "low_res_latents": None, "used_seed": None})
         ui_components = {}
-        gr.Markdown("# ADUC-SDR Video Suite - Orchestrated Workflow", elem_id="main-title")
+        gr.Markdown("# ADUC-SDR Video Suite - LTX & SeedVR Workflow", elem_id="main-title")
         with gr.Row():
             with gr.Column(scale=1): _build_generation_controls(ui_components)
             with gr.Column(scale=1):
-                gr.Markdown("### Etapa 1: Vídeo Base Gerado pelo Orquestrador")
+                gr.Markdown("### Etapa 1: Vídeo Base Gerado")
                 ui_components['low_res_video_output'] = gr.Video(label="O resultado aparecerá aqui", interactive=False)
+                ui_components['used_seed_display'] = gr.Textbox(label="Seed Utilizada", interactive=False)
         _build_postprod_controls(ui_components)
         _register_event_handlers(app_state, ui_components)
     return demo
 
 def _build_generation_controls(ui: dict):
-    """Constrói os componentes da UI para a Etapa 1: Geração."""
+    """Constrói os componentes da UI, sem seleção de modo."""
     gr.Markdown("### Configurações de Geração")
-    ui['prompt'] = gr.Textbox(label="Prompt(s) de Geração", 
-                              info="Escreva sua história. Cada nova linha será tratada como uma nova cena.",
-                              value="Um leão majestoso caminha pela savana\nEle sobe em uma grande pedra e olha o horizonte", 
-                              lines=4)
-    ui['start_image'] = gr.Image(label="Imagem de Início (Opcional)", type="filepath", sources=["upload"])
+    ui['prompt'] = gr.Textbox(label="Prompt(s)", info="Para múltiplas cenas (modo narrativo), escreva um prompt por linha.", value="Um leão majestoso caminha pela savana\nEle sobe em uma grande pedra e olha o horizonte", lines=4)
+    ui['neg_prompt'] = gr.Textbox(label="Negative Prompt", value="blurry, low quality, bad anatomy, deformed", lines=2)
+    ui['start_image'] = gr.Image(label="Imagem de Início (Opcional)", type="pil", sources=["upload"])
     
     with gr.Accordion("Parâmetros Principais", open=True):
         ui['duration'] = gr.Slider(label="Duração Total (s)", value=4, step=1, minimum=1, maximum=30)
         with gr.Row():
-            ui['height'] = gr.Slider(label="Altura", value=432, step=8, minimum=256, maximum=1024)
-            ui['width'] = gr.Slider(label="Largura", value=768, step=8, minimum=256, maximum=1024)
+            ui['height'] = gr.Slider(label="Height", value=432, step=8, minimum=256, maximum=1024)
+            ui['width'] = gr.Slider(label="Width", value=768, step=8, minimum=256, maximum=1024)
 
     with gr.Accordion("Opções Avançadas LTX", open=False):
-        ui['fp_num_inference_steps'] = gr.Slider(label="Número de Passos", minimum=1, maximum=100, step=1, value=20)
-        ui['fp_guidance_preset'] = gr.Dropdown(label="Preset de Guiagem", choices=["Padrão (Recomendado)", "Customizado"], value="Padrão (Recomendado)")
-        with gr.Group(visible=False) as ui['custom_guidance_group']:
-            gr.Markdown("⚠️ Edite as listas em formato JSON. Ex: `[1.0, 2.5, 3.0]`")
-            ui['fp_guidance_scale_list'] = gr.Textbox(label="Lista de Guidance Scale", value="[1, 1, 6, 8, 6, 1, 1]")
-            ui['fp_stg_scale_list'] = gr.Textbox(label="Lista de STG Scale (Movimento)", value="[0, 0, 4, 4, 4, 2, 1]")
+        gr.Markdown("#### Configurações de Passos de Inferência")
+        gr.Markdown("*Deixe o valor padrão (ex: 20) ou 0 para usar a configuração do `config.yaml`.*")
+        ui['fp_num_inference_steps'] = gr.Slider(label="Número de Passos", minimum=0, maximum=100, step=1, value=20, info="Padrão LTX: 20.")
+        ui['fp_skip_initial_steps'] = gr.Slider(label="Pular Passos Iniciais", minimum=0, maximum=100, step=1, value=0)
+        ui['fp_skip_final_steps'] = gr.Slider(label="Pular Passos Finais", minimum=0, maximum=100, step=1, value=0)
     
-    ui['generate_low_btn'] = gr.Button("1. Gerar Vídeo via Orquestrador", variant="primary")
+    ui['generate_low_btn'] = gr.Button("1. Gerar Vídeo Base", variant="primary")
 
 def _build_postprod_controls(ui: dict):
-    """Constrói os componentes da UI para a Etapa 2: Pós-Produção (Upscaling)."""
+    """Constrói os componentes da UI para a Etapa 2: Pós-Produção."""
     with gr.Group(visible=False) as ui['post_prod_group']:
         gr.Markdown("--- \n## Etapa 2: Pós-Produção")
         with gr.Tabs():
+            with gr.TabItem("🚀 Upscaler de Textura (LTX)"):
+                with gr.Row():
+                    with gr.Column(scale=1):
+                         gr.Markdown("Usa o prompt e a semente originais para refinar o vídeo, adicionando detalhes e texturas de alta qualidade.")
+                         ui['ltx_refine_btn'] = gr.Button("2. Aplicar Refinamento LTX", variant="primary")
+                    with gr.Column(scale=1):
+                        ui['ltx_refined_video_output'] = gr.Video(label="Vídeo com Textura Refinada", interactive=False)
+            
             with gr.TabItem("✨ Upscaler de Resolução (SeedVR)"):
-                is_seedvr_available = seed_aduc_pipeline is not None
+                is_seedvr_available = seedvr_inference_server is not None
                 if not is_seedvr_available:
                     gr.Markdown("🔴 **AVISO: O serviço SeedVR não está disponível.**")
                 with gr.Row():
@@ -174,20 +204,22 @@ def _build_postprod_controls(ui: dict):
 
 def _register_event_handlers(app_state: gr.State, ui: dict):
     """Registra todos os manipuladores de eventos do Gradio."""
-    def toggle_custom_guidance(preset_choice: str) -> gr.update:
-        return gr.update(visible=(preset_choice == "Customizado"))
-    
-    ui['fp_guidance_preset'].change(fn=toggle_custom_guidance, inputs=ui['fp_guidance_preset'], outputs=ui['custom_guidance_group'])
+    def update_seed_display(state):
+        return state.get("used_seed", "N/A")
 
     gen_inputs = [
-        ui['prompt'], ui['start_image'],
+        ui['prompt'], ui['neg_prompt'], ui['start_image'],
         ui['height'], ui['width'], ui['duration'],
-        ui['fp_guidance_preset'], ui['fp_guidance_scale_list'], ui['fp_stg_scale_list'],
-        ui['fp_num_inference_steps'],
+        ui['fp_num_inference_steps'], ui['fp_skip_initial_steps'], ui['fp_skip_final_steps'],
     ]
     gen_outputs = [ui['low_res_video_output'], app_state, ui['post_prod_group']]
     
-    ui['generate_low_btn'].click(fn=run_orchestrated_generation, inputs=gen_inputs, outputs=gen_outputs)
+    (ui['generate_low_btn'].click(fn=run_generate_base_video, inputs=gen_inputs, outputs=gen_outputs)
+     .then(fn=update_seed_display, inputs=[app_state], outputs=[ui['used_seed_display']]))
+
+    refine_inputs = [app_state, ui['prompt'], ui['neg_prompt']]
+    refine_outputs = [ui['ltx_refined_video_output'], app_state]
+    ui['ltx_refine_btn'].click(fn=run_ltx_refinement, inputs=refine_inputs, outputs=refine_outputs)
     
     if 'run_seedvr_btn' in ui and ui['run_seedvr_btn'].interactive:
         seedvr_inputs = [app_state, ui['seedvr_seed'], ui['seedvr_resolution'], ui['seedvr_batch_size'], ui['seedvr_fps']]
@@ -197,7 +229,15 @@ def _register_event_handlers(app_state: gr.State, ui: dict):
 # ==============================================================================
 # --- PONTO DE ENTRADA DA APLICAÇÃO ---
 # ==============================================================================
-
 if __name__ == "__main__":
-    demo = build_ui()
-    demo.queue().launch(server_name="0.0.0.0", server_port=7860, debug=True, show_error=True)
+    log_level = os.environ.get("ADUC_LOG_LEVEL", "INFO").upper()
+    logging.basicConfig(level=log_level, format='[%(levelname)s] [%(name)s] %(message)s')
+    
+    print("Building Gradio UI...")
+    gradio_app = build_ui()
+    print("Launching Gradio app...")
+    gradio_app.queue().launch(
+        server_name=os.getenv("GRADIO_SERVER_NAME", "0.0.0.0"), 
+        server_port=int(os.getenv("GRADIO_SERVER_PORT", "7860")),
+        show_error=True
+    )