app.py

# app.py

import gradio as gr
import os
import sys
import traceback
from pathlib import Path

# --- Import dos Serviços de Backend ---
try:
    from api.ltx_server_refactored import video_generation_service
except ImportError:
    print("ERRO FATAL: Não foi possível importar 'video_generation_service'.")
    sys.exit(1)

try:
    from api.seedvr_server import SeedVRServer
except ImportError:
    print("AVISO: Não foi possível importar SeedVRServer.")
    SeedVRServer = None

seedvr_inference_server = SeedVRServer() if SeedVRServer else None

# --- ESTADO DA SESSÃO ---
def create_initial_state():
    return {"low_res_video": None, "low_res_latents": None, "used_seed": None}

# --- FUNÇÕES WRAPPER PARA A UI ---
def run_generate_base_video(
    generation_mode, prompt, neg_prompt, start_img, height, width, duration,
    seed, randomize_seed,
    fp_num_inference_steps, ship_initial_inference_steps, ship_final_inference_steps,
    fp_guidance_preset, fp_guidance_scale_list, fp_stg_scale_list, fp_timesteps_list,
    progress=gr.Progress(track_tqdm=True)
):
    print(f"UI: Iniciando geração no modo: {generation_mode}")
    try:
        initial_image_conditions = []
        if start_img:
            num_frames_estimate = int(duration * 24)
            items_list = [[start_img, 0, 1.0]]
            initial_image_conditions = video_generation_service.prepare_condition_items(items_list, height, width, num_frames_estimate)

        used_seed = None if randomize_seed else seed
        
        ltx_configs = {
            "guidance_preset": fp_guidance_preset,
            "guidance_scale_list": fp_guidance_scale_list,
            "stg_scale_list": fp_stg_scale_list,
            "timesteps_list": fp_timesteps_list,
            "fp_num_inference_steps": fp_num_inference_steps,
            "ship_initial_inference_steps": ship_initial_inference_steps,
            "ship_final_inference_steps": ship_final_inference_steps,
        }

        if generation_mode == "Narrativa (Múltiplos Prompts)":
            video_path, tensor_path, final_seed = video_generation_service.generate_narrative_low(
                prompt=prompt, negative_prompt=neg_prompt, height=height, width=width, duration=duration,
                seed=used_seed, initial_image_conditions=initial_image_conditions,
                ltx_configs_override=ltx_configs,
            )
        else:
            video_path, tensor_path, final_seed = video_generation_service.generate_single_low(
                prompt=prompt, negative_prompt=neg_prompt, height=height, width=width, duration=duration,
                seed=used_seed, initial_image_conditions=initial_image_conditions,
                ltx_configs_override=ltx_configs,
            )
        
        if video_path is None:
            raise gr.Error("A geração do vídeo falhou no backend. Verifique os logs do console para detalhes.")

        new_state = {"low_res_video": video_path, "low_res_latents": tensor_path, "used_seed": final_seed}
        return video_path, new_state, gr.update(visible=True)
        
    except Exception as e:
        error_message = f"❌ Ocorreu um erro na Geração Base:\n{e}"
        print(f"{error_message}\nDetalhes: {traceback.format_exc()}")
        raise gr.Error(error_message)

def run_ltx_refinement(state, prompt, neg_prompt, cfg, progress=gr.Progress(track_tqdm=True)):
    if not state or not state.get("low_res_latents"):
        raise gr.Error("Erro: Gere um vídeo base primeiro na Etapa 1.")
    try:
        video_path, tensor_path = video_generation_service.generate_upscale_denoise(
            latents_path=state["low_res_latents"], prompt=prompt,
            negative_prompt=neg_prompt, guidance_scale=cfg, seed=state["used_seed"]
        )
        state["refined_video_ltx"] = video_path; state["refined_latents_ltx"] = tensor_path
        return video_path, state
    except Exception as e:
        raise gr.Error(f"Erro no Refinamento LTX: {e}")

def run_seedvr_upscaling(state, seed, resolution, batch_size, fps, progress=gr.Progress(track_tqdm=True)):
    if not state or not state.get("low_res_video"):
        raise gr.Error("Erro: Gere um vídeo base primeiro na Etapa 1.")
    if not seedvr_inference_server:
        raise gr.Error("Erro: O servidor SeedVR não está disponível.")
    try:
        def progress_wrapper(p, desc=""): progress(p, desc=desc)
        output_filepath = seedvr_inference_server.run_inference(
            file_path=state["low_res_video"], seed=seed, resolution=resolution,
            batch_size=batch_size, fps=fps, progress=progress_wrapper
        )
        return gr.update(value=output_filepath), gr.update(value=f"✅ Concluído!\nSalvo em: {output_filepath}")
    except Exception as e:
        return None, gr.update(value=f"❌ Erro no SeedVR:\n{e}")

# --- DEFINIÇÃO DA INTERFACE GRADIO ---
with gr.Blocks() as demo:
    gr.Markdown("# LTX Video - Geração e Pós-Produção por Etapas")
    app_state = gr.State(value=create_initial_state())

    with gr.Row():
        with gr.Column(scale=1):
            gr.Markdown("### Etapa 1: Configurações de Geração")
            
            generation_mode_input = gr.Radio(
                label="Modo de Geração", choices=["Simples (Prompt Único)", "Narrativa (Múltiplos Prompts)"],
                value="Narrativa (Múltiplos Prompts)", info="Simples para uma ação, Narrativa para uma sequência (uma cena por linha)."
            )
            prompt_input = gr.Textbox(label="Prompt(s)", value="Um leão majestoso caminha pela savana\nEle sobe em uma grande pedra e olha o horizonte", lines=4)
            neg_prompt_input = gr.Textbox(label="Negative Prompt", value="blurry, low quality, bad anatomy", lines=2)
            start_image = gr.Image(label="Imagem de Início (Opcional)", type="filepath", sources=["upload"])
            
            with gr.Accordion("Parâmetros Principais", open=True):
                duration_input = gr.Slider(label="Duração Total (s)", value=8, step=1, minimum=1, maximum=40)
                with gr.Row():
                    height_input = gr.Slider(label="Height", value=512, step=32, minimum=256, maximum=1024)
                    width_input = gr.Slider(label="Width", value=704, step=32, minimum=256, maximum=1024)
                with gr.Row():
                    seed_input = gr.Number(label="Seed", value=42, precision=0)
                    randomize_seed = gr.Checkbox(label="Randomize Seed", value=True)

            with gr.Accordion("Opções Adicionais LTX (Avançado)", open=False):
                with gr.Tabs():
                    with gr.TabItem("Guiagem (First Pass)"):
                        fp_guidance_preset = gr.Dropdown(
                            label="Preset de Guiagem",
                            choices=["Padrão (Recomendado)", "Agressivo", "Suave", "Customizado"],
                            value="Padrão (Recomendado)", info="Muda o comportamento da guiagem ao longo da difusão."
                        )
                        with gr.Group(visible=False) as custom_guidance_group:
                            gr.Markdown("⚠️ Edite as listas em formato JSON. Ex: `[1, 2, 3]`")
                            fp_guidance_scale_list = gr.Textbox(label="Lista de Guidance Scale", value="[1, 1, 6, 8, 6, 1, 1]")
                            fp_stg_scale_list = gr.Textbox(label="Lista de STG Scale (Movimento)", value="[0, 0, 4, 4, 4, 2, 1]")
                            fp_timesteps_list = gr.Textbox(label="Lista de Guidance Timesteps", value="[1.0, 0.996, 0.9933, 0.9850, 0.9767, 0.9008, 0.6180]")
                    
                    with gr.TabItem("Scheduler"):
                        fp_num_inference_steps = gr.Slider(label="Passos de Inferência", minimum=10, maximum=100, step=1, value=30)
                        ship_initial_inference_steps = gr.Slider(label="Pular Passos Iniciais (img2vid)", minimum=0, maximum=100, step=1, value=0)
                        ship_final_inference_steps = gr.Slider(label="Pular Passos Finais", minimum=0, maximum=100, step=1, value=0)
            
            generate_low_btn = gr.Button("1. Gerar Vídeo Base", variant="primary")
        
        with gr.Column(scale=1):
            gr.Markdown("### Vídeo Base Gerado")
            low_res_video_output = gr.Video(label="O resultado da Etapa 1 aparecerá aqui", interactive=False)

def update_custom_guidance_visibility(preset_choice):
        return gr.update(visible=(preset_choice == "Customizado"))
    
    fp_guidance_preset.change(fn=update_custom_guidance_visibility, inputs=fp_guidance_preset, outputs=custom_guidance_group)

    all_ltx_inputs = [
        fp_num_inference_steps, ship_initial_inference_steps, ship_final_inference_steps,
        fp_guidance_preset, fp_guidance_scale_list, fp_stg_scale_list, fp_timesteps_list,
    ]
    
    generate_low_btn.click(
        fn=run_generate_base_video,
        inputs=[
            generation_mode_input, prompt_input, neg_prompt_input, start_image,
            height_input, width_input, duration_input,
            seed_input, randomize_seed,
            *all_ltx_inputs,
            # Passa o `cfg` por último, pois não está no `all_ltx_inputs`
        ],
        outputs=[low_res_video_output, app_state, post_prod_group]
    )

    ltx_refine_btn.click(
        fn=run_ltx_refinement,
        inputs=[app_state, prompt_input, neg_prompt_input, cfg_input],
        outputs=[ltx_refined_video_output, app_state]
    )

    run_seedvr_button.click(
        fn=run_seedvr_upscaling,
        inputs=[app_state, seedvr_seed, seedvr_resolution, seedvr_batch_size, seedvr_fps_output],
        outputs=[seedvr_video_output, seedvr_status_box]
    )

if __name__ == "__main__":
    demo.queue().launch(server_name="0.0.0.0", server_port=7860, debug=True, show_error=True)