# FILE: app.py # DESCRIPTION: Final Gradio web interface for the ADUC-SDR Video Suite. # Features dimension sliders locked to multiples of 8, a unified LTX workflow, # advanced controls, integrated SeedVR upscaling, and detailed debug logging. import gradio as gr import traceback import sys import os import logging # ============================================================================== # --- IMPORTAÇÃO DOS SERVIÇOS DE BACKEND E UTILS --- # ============================================================================== try: # Serviço principal para geração LTX from api.ltx_server_refactored_complete import video_generation_service # Nosso decorador de logging para depuração from api.utils.debug_utils import log_function_io # Serviço especialista para upscaling de resolução (SeedVR) from api.seedvr_server import seedvr_server_singleton as seedvr_inference_server logging.info("All backend services (LTX, SeedVR) and debug utils imported successfully.") except ImportError as e: def log_function_io(func): return func logging.warning(f"Could not import a module, debug logger might be disabled. SeedVR might be unavailable. Details: {e}") if 'video_generation_service' not in locals(): logging.critical(f"FATAL: Main LTX service 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. The SeedVR upscaling tab will be disabled.") except Exception as e: logging.critical(f"FATAL ERROR: An unexpected error occurred during backend initialization. Details: {e}", exc_info=True) sys.exit(1) # ============================================================================== # --- FUNÇÕES WRAPPER (PONTE ENTRE UI E BACKEND) --- # ============================================================================== @log_function_io def run_generate_base_video( generation_mode: str, prompt: str, neg_prompt: str, start_img: str, 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_skip_initial_steps: int, fp_skip_final_steps: int, progress=gr.Progress(track_tqdm=True) ) -> tuple: """Wrapper para a geração do vídeo base LTX.""" try: logging.info(f"[UI] Request received. Selected mode: {generation_mode}") initial_conditions = [] if start_img: num_frames_estimate = int(duration * 24) items_list = [[start_img, 0, 1.0]] initial_conditions = video_generation_service.prepare_condition_items( items_list, height, width, num_frames_estimate ) 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, "skip_initial_inference_steps": fp_skip_initial_steps, "skip_final_inference_steps": fp_skip_final_steps, } video_path, tensor_path, final_seed = video_generation_service.generate_low_resolution( prompt=prompt, negative_prompt=neg_prompt, height=height, width=width, duration=duration, initial_conditions=initial_conditions, ltx_configs_override=ltx_configs ) 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 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.""" 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 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 = 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) except Exception as e: error_message = f"❌ An error occurred during SeedVR Upscaling:\n{e}" logging.error(f"{error_message}\nDetails: {traceback.format_exc()}", exc_info=True) return None, gr.update(value=error_message) # ============================================================================== # --- CONSTRUÇÃO DA INTERFACE GRADIO --- # ============================================================================== 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, "low_res_latents": None, "used_seed": None}) ui_components = {} 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") 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.""" gr.Markdown("### Configurações de Geração") ui['generation_mode'] = gr.Radio(label="Modo de Geração", choices=["Simples (Prompt Único)", "Narrativa (Múltiplos Prompts)"], value="Narrativa (Múltiplos Prompts)", info="Simples para uma ação contínua, Narrativa para uma sequência (uma cena por linha).") ui['prompt'] = gr.Textbox(label="Prompt(s)", 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="filepath", 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="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): gr.Markdown("#### Configurações de Passos de Inferência (First Pass)") 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) with gr.Tabs(): with gr.TabItem("Configurações de Guiagem (First Pass)"): ui['fp_guidance_preset'] = gr.Dropdown(label="Preset de Guiagem", choices=["Padrão (Recomendado)", "Agressivo", "Suave", "Customizado"], value="Padrão (Recomendado)", info="Controla o comportamento da guiagem durante a difusão.") 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]") 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.""" 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 = seedvr_inference_server is not None if not is_seedvr_available: gr.Markdown("🔴 **AVISO: O serviço SeedVR não está disponível.**") with gr.Row(): with gr.Column(scale=1): ui['seedvr_seed'] = gr.Slider(minimum=0, maximum=999999, value=42, step=1, label="Seed") ui['seedvr_resolution'] = gr.Slider(minimum=720, maximum=2160, value=1080, step=8, label="Resolução Vertical Alvo") ui['seedvr_batch_size'] = gr.Slider(minimum=1, maximum=16, value=4, step=1, label="Batch Size por GPU") ui['seedvr_fps'] = gr.Number(label="FPS de Saída (0 = original)", value=0) ui['run_seedvr_btn'] = gr.Button("2. Iniciar Upscaling SeedVR", variant="primary", interactive=is_seedvr_available) with gr.Column(scale=1): ui['seedvr_video_output'] = gr.Video(label="Vídeo com Upscale SeedVR", interactive=False) ui['seedvr_status_box'] = gr.Textbox(label="Status do SeedVR", value="Aguardando...", lines=3, interactive=False) 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['generation_mode'], 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_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_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']] seedvr_outputs = [ui['seedvr_video_output'], ui['seedvr_status_box']] ui['run_seedvr_btn'].click(fn=run_seedvr_upscaling, inputs=seedvr_inputs, outputs=seedvr_outputs) # ============================================================================== # --- PONTO DE ENTRADA DA APLICAÇÃO --- # ============================================================================== if __name__ == "__main__": 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 )