Update app_wan.py

app_wan.py

@@ -1,37 +1,86 @@
-# app_wan.py (trechos essenciais)
+# app_wan.py
 
 import os
-# (mantenha o hack de instalação se necessário)
-#os.system('pip install --upgrade --pre --extra-index-url https://download.pytorch.org/whl/nightly/cu126 "torch<2.9" spaces')
+
+# 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
-from PIL import Image
-import numpy as np
 import tempfile
+import numpy as np
+from PIL import Image
+import random
+from gradio_client import Client, handle_file
 
-# === mantém as constantes de UI exatamente como no arquivo atual ===
+# === 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
 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 = "..."  # mesmo valor do arquivo original
 
-# === novo: importar e instanciar o serviço ===
+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()
 
-# (opcional) manter generate_end_frame e switch_to_upload_tab como estão
-# def generate_end_frame(...): ...    # inalterado
-# def switch_to_upload_tab(): ...     # inalterado
+# === 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
 
-# Wrapper fino: a UI constrói images_condition_items e delega ao serviço
+    progress(1.0, desc="Done!")
+    return result
+
+# Wrapper: a UI monta images_condition_items e delega ao serviço
 def ui_generate_video(
     start_image_pil,
     start_frame_text,
@@ -47,14 +96,15 @@ def ui_generate_video(
     guidance_scale_2=1.0,
     seed=42,
     randomize_seed=False,
-    progress=gr.Progress(track_tqdm=True)
+    progress=gr.Progress(track_tqdm=True),
 ):
-    # Conversão robusta básica (UI “burra”, sem semântica adicional)
+    # UI “burra”: apenas parses simples
     def to_int_safe(v, default=0):
         try:
             return int(v)
         except:
             return default
+
     def to_float_safe(v, default=1.0):
         try:
             return float(v)
@@ -63,22 +113,36 @@ def ui_generate_video(
 
     images_condition_items = [
         [start_image_pil, to_int_safe(start_frame_text, 0), to_float_safe(start_peso, 1.0)],
-        [end_image_pil,   to_int_safe(end_frame_text,   0), to_float_safe(end_peso,   1.0)],
+        [end_image_pil, to_int_safe(end_frame_text, 0), to_float_safe(end_peso, 1.0)],
     ]
+
     return wan_manager.generate_video_from_conditions(
         images_condition_items=images_condition_items,
         prompt=prompt,
         negative_prompt=negative_prompt,
-        duration_seconds=duration_seconds,
-        steps=steps,
-        guidance_scale=guidance_scale,
-        guidance_scale_2=guidance_scale_2,
-        seed=seed,
-        randomize_seed=randomize_seed,
+        duration_seconds=float(duration_seconds),
+        steps=int(steps),
+        guidance_scale=float(guidance_scale),
+        guidance_scale_2=float(guidance_scale_2),
+        seed=int(seed),
+        randomize_seed=bool(randomize_seed),
     )
 
-# === UI Gradio (adicionar frame/peso abaixo de cada imagem) ===
-css = ''' ... (mantém igual) ... '''
+# === UI 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")
 
@@ -94,22 +158,33 @@ with gr.Blocks(theme=gr.themes.Citrus(), css=css) as app:
                         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="80")
+                                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"
+                                elem_id="or_item",
                             )
                 prompt = gr.Textbox(label="Prompt", info="Describe the transition between the two images")
 
                 with gr.Accordion("Advanced Settings", open=False):
-                    duration_seconds_input = gr.Slider(minimum=MIN_DURATION, maximum=MAX_DURATION, step=0.1, value=2.1, label="Video Duration (seconds)")
+                    duration_seconds_input = gr.Slider(
+                        minimum=MIN_DURATION,
+                        maximum=MAX_DURATION,
+                        step=0.1,
+                        value=2.1,
+                        label="Video Duration (seconds)",
+                        info=f"Clamped to model's {MIN_FRAMES_MODEL}-{MAX_FRAMES_MODEL} frames at {FIXED_FPS}fps.",
+                    )
                     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")
-                    guidance_scale_2_input = gr.Slider(minimum=0.0, maximum=10.0, step=0.5, value=1.0, label="Guidance Scale - low noise")
+                    guidance_scale_input = gr.Slider(
+                        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"
+                    )
                     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)
@@ -119,21 +194,23 @@ with gr.Blocks(theme=gr.themes.Citrus(), css=css) as app:
         with gr.Column():
             output_video = gr.Video(label="Generated Video", autoplay=True)
 
-    # Inputs/outputs atualizados para o wrapper
+    # Inputs/outputs para o wrapper
     ui_inputs = [
         start_image, start_frame_tb, start_peso_sl,
         end_image, end_frame_tb, end_peso_sl,
         prompt, negative_prompt_input, duration_seconds_input,
         steps_slider, guidance_scale_input, guidance_scale_2_input,
-        seed_input, randomize_seed_checkbox
+        seed_input, randomize_seed_checkbox,
     ]
     ui_outputs = [output_video, seed_input]
 
     generate_button.click(fn=ui_generate_video, inputs=ui_inputs, outputs=ui_outputs)
 
-    # Cadeia “5 seconds”: mantém a lógica, apenas troca a função final para ui_generate_video
+    # Cadeia “5 seconds”: alterna aba, gera end frame e já dispara render
     generate_5seconds.click(
-        fn=switch_to_upload_tab, inputs=None, outputs=[tabs]
+        fn=switch_to_upload_tab,
+        inputs=None,
+        outputs=[tabs]
     ).then(
         fn=lambda img: generate_end_frame(
             img,
@@ -147,14 +224,28 @@ with gr.Blocks(theme=gr.themes.Citrus(), css=css) as app:
         outputs=ui_outputs
     )
 
-    # Examples permanecem; os campos de frame/peso usam defaults
-    gr.Examples(
-        examples=[
-            ["frame_1.png", "frame_2.png", "the man speed motorcycle"],
-            ["frame_1.png", "frame_3.png", "the man return on road motorcycle"],
-        ],
-        inputs=[start_image, end_image, prompt],
-        outputs=ui_outputs,
-        fn=ui_generate_video,
-        cache_examples="lazy",
-    )
+    # Exemplos opcionais (campos de frame/peso usam defaults atuais do componente)
+    # gr.Examples(
+    #     examples=[
+    #         ["poli_tower.png", "tower_takes_off.png", "the man turns around"],
+    #         ["ugly_sonic.jpeg", "squatting_sonic.png", "the character dodges the missiles"],
+    #         ["capyabara_zoomed.png", "capyabara.webp", "a dramatic dolly zoom"],
+    #     ],
+    #     inputs=[start_image, end_image, prompt],
+    #     outputs=ui_outputs,
+    #     fn=ui_generate_video,
+    #     cache_examples="lazy",
+    # )
+
+if __name__ == "__main__":
+    # Assets opcionais de exemplo mínimos
+    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
+
+    # Lança a app
+    app.launch(server_name="0.0.0.0", server_port=7860, show_error=True)