Update app_wan.py

app_wan.py

@@ -1,85 +1,24 @@
 # app_wan.py
 
 import os
-
-# PyTorch 2.8 (temporary hack) — manter conforme app original
-#os.system('pip install --upgrade --pre --extra-index-url https://download.pytorch.org/whl/nightly/cu126 "torch<2.9" spaces')
-
 import gradio as gr
 import tempfile
 import numpy as np
 from PIL import Image
-from gradio_client import Client, handle_file
-
-# === Constantes (espelhando o app original) ===
-MODEL_ID = "Wan-AI/Wan2.2-I2V-A14B-Diffusers"
-
-# Dimensões
-MAX_DIMENSION = 832
-MIN_DIMENSION = 480
-DIMENSION_MULTIPLE = 16
-SQUARE_SIZE = 480
 
-# Geração
+# === Constantes ===
 MAX_SEED = np.iinfo(np.int32).max
 FIXED_FPS = 16
 MIN_FRAMES_MODEL = 8
 MAX_FRAMES_MODEL = 81
-
 MIN_DURATION = round(MIN_FRAMES_MODEL / FIXED_FPS, 1)
 MAX_DURATION = round(MAX_FRAMES_MODEL / FIXED_FPS, 1)
 
-default_negative_prompt = (
-    "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，"
-    "JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，"
-    "手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走,过曝，"
-)
-
 # === Importa o serviço de geração (manager) ===
 from aduc_framework.managers.wan_manager import WanManager
 wan_manager = WanManager()
 
-# === Utilidades de UI ===
-def switch_to_upload_tab():
-    # Atualiza o Tabs existente para a aba "Upload"
-    return gr.Tabs.update(selected="upload_tab")
-
-def generate_end_frame(start_img, gen_prompt, progress=gr.Progress(track_tqdm=True)):
-    """
-    Chama uma API Gradio externa para gerar uma imagem (end frame).
-    """
-    if start_img is None:
-        raise gr.Error("Please provide a Start Frame first.")
-
-    hf_token = os.getenv("HF_TOKEN")
-    if not hf_token:
-        raise gr.Error("HF_TOKEN not found in environment variables. Please set it in your Space secrets.")
-
-    with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmpfile:
-        start_img.save(tmpfile.name)
-        tmp_path = tmpfile.name
-
-    progress(0.1, desc="Connecting to image generation API...")
-    client = Client("multimodalart/nano-banana")
-
-    progress(0.5, desc=f"Generating with prompt: '{gen_prompt}'...")
-    try:
-        result = client.predict(
-            prompt=gen_prompt,
-            images=[{"image": handle_file(tmp_path)}],
-            manual_token=hf_token,
-            api_name="/unified_image_generator",
-        )
-    finally:
-        try:
-            os.remove(tmp_path)
-        except:
-            pass
-
-    progress(1.0, desc="Done!")
-    return result
-
-# Wrapper: a UI monta images_condition_items e delega ao serviço
+# === Wrapper da UI para o Serviço ===
 def ui_generate_video(
     start_image_pil,
     start_frame_text,
@@ -90,40 +29,31 @@ def ui_generate_video(
     end_frame_text,
     end_peso,
     prompt,
-    negative_prompt=default_negative_prompt,
-    duration_seconds=2.1,
-    steps=8,
-    guidance_scale=1.0,
-    guidance_scale_2=1.0,
-    seed=42,
-    randomize_seed=False,
+    negative_prompt,
+    duration_seconds,
+    steps,
+    guidance_scale,
+    guidance_scale_2,
+    seed,
+    randomize_seed,
     progress=gr.Progress(track_tqdm=True),
 ):
-    # Conversões simples
     def to_int_safe(v, default=0):
-        try:
-            return int(v)
-        except:
-            return default
-
+        try: return int(v)
+        except: return default
     def to_float_safe(v, default=1.0):
-        try:
-            return float(v)
-        except:
-            return default
+        try: return float(v)
+        except: return default
 
-    # Peso da imagem inicial é fixo 1.0
+    # Prepara a lista de imagens de condição
     start_item = [start_image_pil, to_int_safe(start_frame_text, 0), 1.0]
-
-    # Handle é opcional: se não houver imagem, não enviar item
     items = [start_item]
     if handle_image_pil is not None:
-        items.append([handle_image_pil, to_int_safe(handle_frame_text, 4), to_float_safe(handle_peso, 1.0)])
-
-    # Último item (end) sempre presente
+        items.append([handle_image_pil, to_int_safe(handle_frame_text, 17), to_float_safe(handle_peso, 1.0)])
     items.append([end_image_pil, to_int_safe(end_frame_text, MAX_FRAMES_MODEL - 1), to_float_safe(end_peso, 1.0)])
 
-    return wan_manager.generate_video_from_conditions(
+    # Chama o manager, que agora retorna 4 valores
+    video_path, current_seed, debug_video_path, grid_image_path = wan_manager.generate_video_from_conditions(
         images_condition_items=items,
         prompt=prompt,
         negative_prompt=negative_prompt,
@@ -134,82 +64,76 @@ def ui_generate_video(
         seed=int(seed),
         randomize_seed=bool(randomize_seed),
     )
+    
+    # Retorna os 4 valores para os componentes da UI
+    return video_path, current_seed, debug_video_path, grid_image_path
 
-# === UI Gradio ===
+# === Interface Gradio ===
 css = '''
 .fillable{max-width: 1100px !important}
 .dark .progress-text {color: white}
 #general_items{margin-top: 2em}
-#group_all{overflow:visible}
-#group_all .styler{overflow:visible}
-#group_tabs .tabitem{padding: 0}
-.tab-wrapper{margin-top: -33px;z-index: 999;position: absolute;width: 100%;background-color: var(--block-background-fill);padding: 0;}
-#component-9-button{width: 50%;justify-content: center}
-#component-11-button{width: 50%;justify-content: center}
-#or_item{text-align: center; padding-top: 1em; padding-bottom: 1em; font-size: 1.1em;margin-left: .5em;margin-right: .5em;width: calc(100% - 1em)}
-#fivesec{margin-top: 5em;margin-left: .5em;margin-right: .5em;width: calc(100% - 1em)}
 '''
 
-with gr.Blocks(theme=gr.themes.Citrus(), css=css) as app:
-    gr.Markdown("# Wan 2.2 Aduca-sdr")
+with gr.Blocks(theme=gr.themes.Glass(), css=css) as app:
+    gr.Markdown("# Wan 2.2 Aduca-SDR")
 
     with gr.Row(elem_id="general_items"):
-        with gr.Column():
-            with gr.Group(elem_id="group_all"):
+        with gr.Column(scale=2):
+            with gr.Group():
                 with gr.Row():
-                    # Coluna: Start (peso fixo 1.0)
+                    # Coluna: Start
                     with gr.Column():
                         start_image = gr.Image(type="pil", label="Start Frame", sources=["upload", "clipboard"])
-                        start_frame_tb = gr.Textbox(label="Start Frame (int)", value="0")
+                        start_frame_tb = gr.Textbox(label="Start Frame Index", value="0", interactive=False)
 
                     # Coluna: Handle (opcional)
                     with gr.Column():
                         handle_image = gr.Image(type="pil", label="Handle Image", sources=["upload", "clipboard"])
-                        handle_frame_tb = gr.Textbox(label="Handle Frame (int)", value="4")
-                        handle_peso_sl = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, value=1.0, label="Handle Peso")
-
-                    # Coluna: End (Upload/Generate)
-                    with gr.Tabs(elem_id="group_tabs") as tabs:
-                        with gr.TabItem("Upload", id="upload_tab"):
-                            with gr.Column():
-                                end_image = gr.Image(type="pil", label="End Frame", sources=["upload", "clipboard"])
-                                end_frame_tb = gr.Textbox(label="End Frame (int)", value=str(MAX_FRAMES_MODEL - 1))
-                                end_peso_sl = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, value=1.0, label="End Peso")
-                        with gr.TabItem("Generate", id="generate_tab"):
-                            generate_5seconds = gr.Button("Generate scene 5 seconds in the future", elem_id="fivesec")
-                            gr.Markdown(
-                                "Generate a custom end-frame with an edit model like Nano Banana or Qwen Image Edit",
-                                elem_id="or_item",
-                            )
-                prompt = gr.Textbox(label="Prompt", info="Describe the transition between the two images")
+                        handle_frame_tb = gr.Textbox(label="Handle Frame Index", value="17")
+                        handle_peso_sl = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, value=1.0, label="Handle Weight")
+
+                    # Coluna: End
+                    with gr.Column():
+                        end_image = gr.Image(type="pil", label="End Frame", sources=["upload", "clipboard"])
+                        end_frame_tb = gr.Textbox(label="End Frame Index", value=str(MAX_FRAMES_MODEL - 1), interactive=False)
+                        end_peso_sl = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, value=1.0, label="End Weight")
+                
+                prompt = gr.Textbox(
+                    label="Prompt",
+                    info="Descreva a transição e a cena. Ex: 'a beautiful woman walking on the beach, cinematic'."
+                )
 
                 with gr.Accordion("Advanced Settings", open=False):
                     duration_seconds_input = gr.Slider(
-                        minimum=MIN_DURATION,
-                        maximum=MAX_DURATION,
-                        step=0.1,
-                        value=2.1,
+                        minimum=MIN_DURATION, maximum=MAX_DURATION, step=0.1, value=3.2,
                         label="Video Duration (seconds)",
-                        info=f"Clamped to model's {MIN_FRAMES_MODEL}-{MAX_FRAMES_MODEL} frames at {FIXED_FPS}fps.",
+                        info=f"Será ajustado para o formato 4n+1. Mín: {MIN_FRAMES_MODEL} frames, Máx: {MAX_FRAMES_MODEL} frames."
+                    )
+                    negative_prompt_input = gr.Textbox(
+                        label="Negative Prompt",
+                        value=wan_manager.default_negative_prompt,
+                        lines=3
                     )
-                    negative_prompt_input = gr.Textbox(label="Negative Prompt", value=default_negative_prompt, lines=3)
                     steps_slider = gr.Slider(minimum=1, maximum=30, step=1, value=8, label="Inference Steps")
                     guidance_scale_input = gr.Slider(
-                        minimum=0.0, maximum=10.0, step=0.5, value=1.0, label="Guidance Scale - high noise"
+                        minimum=0.0, maximum=10.0, step=0.5, value=1.0, label="Guidance Scale (High Noise)"
                     )
                     guidance_scale_2_input = gr.Slider(
-                        minimum=0.0, maximum=10.0, step=0.5, value=1.0, label="Guidance Scale - low noise"
+                        minimum=0.0, maximum=10.0, step=0.5, value=1.0, label="Guidance Scale (Low Noise)"
                     )
                     with gr.Row():
-                        seed_input = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=42)
-                        randomize_seed_checkbox = gr.Checkbox(label="Randomize seed", value=True)
+                        seed_input = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=42, interactive=True)
+                        randomize_seed_checkbox = gr.Checkbox(label="Randomize Seed", value=True)
 
                 generate_button = gr.Button("Generate Video", variant="primary")
 
-        with gr.Column():
+        with gr.Column(scale=1):
             output_video = gr.Video(label="Generated Video", autoplay=True)
+            with gr.Accordion("Debugging Visuals", open=True):
+                debug_video = gr.Video(label="Denoising Process Video", autoplay=False)
+                steps_grid_image = gr.Image(label="Denoising Steps Grid", interactive=False, type="filepath")
 
-    # Inputs/outputs para o wrapper
     ui_inputs = [
         start_image, start_frame_tb,
         handle_image, handle_frame_tb, handle_peso_sl,
@@ -218,35 +142,9 @@ with gr.Blocks(theme=gr.themes.Citrus(), css=css) as app:
         steps_slider, guidance_scale_input, guidance_scale_2_input,
         seed_input, randomize_seed_checkbox,
     ]
-    ui_outputs = [output_video, seed_input]
+    ui_outputs = [output_video, seed_input, debug_video, steps_grid_image]
 
     generate_button.click(fn=ui_generate_video, inputs=ui_inputs, outputs=ui_outputs)
 
-    # Cadeia “5 seconds”: alterna aba, gera end frame e dispara render
-    generate_5seconds.click(
-        fn=switch_to_upload_tab,
-        inputs=None,
-        outputs=[tabs]
-    ).then(
-        fn=lambda img: generate_end_frame(
-            img,
-            "this image is a still frame from a movie. generate a new frame with what happens on this scene 5 seconds in the future"
-        ),
-        inputs=[start_image],
-        outputs=[end_image]
-    ).success(
-        fn=ui_generate_video,
-        inputs=ui_inputs,
-        outputs=ui_outputs
-    )
-
 if __name__ == "__main__":
-    os.makedirs("examples", exist_ok=True)
-    try:
-        Image.new('RGB', (832, 480), color=(73, 109, 137)).save("examples/frame_1.png")
-        Image.new('RGB', (832, 480), color=(173, 109, 237)).save("examples/frame_2.png")
-        Image.new('RGB', (832, 480), color=(255, 255, 0)).save("examples/frame_3.png")
-    except:
-        pass
-
-    app.launch(server_name="0.0.0.0", server_port=7860, show_error=True)
+    app.launch(server_name="0.0.0.0", server_port=7860, show_error=True)