Update app.py

app.py

@@ -1,4 +1,4 @@
-# app.py
+# app_refactored_with_postprod.py (com Presets de Guiagem e Opções LTX Completas)
 
 import gradio as gr
 import os
@@ -10,13 +10,13 @@ from pathlib import Path
 try:
     from api.ltx_server_refactored import video_generation_service
 except ImportError:
-    print("ERRO FATAL: Não foi possível importar 'video_generation_service'.")
+    print("ERRO FATAL: Não foi possível importar 'video_generation_service' de 'api.ltx_server_refactored'.")
     sys.exit(1)
 
 try:
     from api.seedvr_server import SeedVRServer
 except ImportError:
-    print("AVISO: Não foi possível importar SeedVRServer.")
+    print("AVISO: Não foi possível importar SeedVRServer. A aba de upscaling SeedVR será desativada.")
     SeedVRServer = None
 
 seedvr_inference_server = SeedVRServer() if SeedVRServer else None
@@ -26,14 +26,18 @@ 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,
+    # Parâmetros de Geração
+    generation_mode, prompt, neg_prompt, start_img, height, width, duration, cfg, seed, randomize_seed,
     fp_guidance_preset, fp_guidance_scale_list, fp_stg_scale_list, fp_timesteps_list,
     progress=gr.Progress(track_tqdm=True)
 ):
+    """
+    Função wrapper que decide qual pipeline de backend chamar, passando todas as configurações LTX.
+    """
     print(f"UI: Iniciando geração no modo: {generation_mode}")
+    
     try:
         initial_image_conditions = []
         if start_img:
@@ -43,33 +47,34 @@ def run_generate_base_video(
 
         used_seed = None if randomize_seed else seed
         
+        # Agrupa todas as configurações LTX em um único dicionário para o backend
         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,
         }
 
+        # Decide qual função de backend chamar com base no modo
         if generation_mode == "Narrativa (Múltiplos Prompts)":
-            video_path, tensor_path, final_seed = video_generation_service.generate_low(
-                prompt=prompt, negative_prompt=neg_prompt, height=height, width=width, duration=duration,
-                seed=used_seed, conditions_itens=initial_image_conditions,
+            video_path, tensor_path, final_seed = video_generation_service.generate_narrative_low(
+                prompt=prompt, negative_prompt=neg_prompt,
+                height=height, width=width, duration=duration,
+                guidance_scale=cfg, 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_low(
-                prompt=prompt, negative_prompt=neg_prompt, height=height, width=width, duration=duration,
-                seed=used_seed, conditions_itens=initial_image_conditions,
+        else: # Modo "Simples (Prompt Único)"
+            video_path, tensor_path, final_seed = video_generation_service.generate_single_low(
+                prompt=prompt, negative_prompt=neg_prompt,
+                height=height, width=width, duration=duration,
+                guidance_scale=cfg, 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:
@@ -77,13 +82,13 @@ def run_generate_base_video(
         print(f"{error_message}\nDetalhes: {traceback.format_exc()}")
         raise gr.Error(error_message)
 
-def run_ltx_refinement(state, prompt, neg_prompt, progress=gr.Progress(track_tqdm=True)):
+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, seed=state["used_seed"]
+            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
@@ -108,6 +113,7 @@ def run_seedvr_upscaling(state, seed, resolution, batch_size, fps, progress=gr.P
 # --- 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():
@@ -122,16 +128,21 @@ with gr.Blocks() as demo:
             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.Accordion("Parâmetros Principais", open=False):
+                duration_input = gr.Slider(label="Duração Total (s)", value=1, 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)
+                    height_input = gr.Slider(label="Height", value=720, step=32, minimum=256, maximum=1024)
+                    width_input = gr.Slider(label="Width", value=720, 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):
+                cfg_input = gr.Slider(label="Guidance Scale (CFG)", info="Afeta o refinamento (se usado) e não tem efeito no First Pass dos modelos 'distilled'.", value=0.0, step=1, minimum=0.0, maximum=10.0)
+                fp_num_inference_steps = gr.Slider(label="Passos de Inferência (First Pass)", minimum=10, maximum=100, step=1, value=10)
+                ship_initial_inference_steps = gr.Slider(label="Passos de Inferência (Ship First)", minimum=0, maximum=100, step=1, value=0)
+                ship_final_inference_steps = gr.Slider(label="Passos de Inferência (Ship Last)", minimum=0, maximum=100, step=1, value=0)
+            
                 with gr.Tabs():
                     with gr.TabItem("Guiagem (First Pass)"):
                         fp_guidance_preset = gr.Dropdown(
@@ -144,12 +155,7 @@ with gr.Blocks() as demo:
                             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):
@@ -179,33 +185,30 @@ with gr.Blocks() as demo:
                     with gr.Column(scale=1):
                         seedvr_video_output = gr.Video(label="Vídeo com Upscale SeedVR", interactive=False)
                         seedvr_status_box = gr.Textbox(label="Status", value="Aguardando...", lines=3, interactive=False)
-                        
-    
+
+    # --- LÓGICA DE EVENTOS ---
     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,
+        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`
+            generation_mode_input, prompt_input, neg_prompt_input, start_image, height_input, width_input, 
+            duration_input, 4, seed_input, randomize_seed,
+            *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],
+        inputs=[app_state, prompt_input, neg_prompt_input, cfg_input],
         outputs=[ltx_refined_video_output, app_state]
     )