Update app.py

app.py

@@ -80,7 +80,7 @@ def get_seed(randomize_seed: bool, seed: int) -> int:
 
 @spaces.GPU
 def preprocess_image(
-    image: dict,
+    image: Image.Image,
     prompt: str = "",
     negative_prompt: str = "",
     style_name: str = "",
@@ -93,17 +93,26 @@ def preprocess_image(
     user_dir = os.path.join(TMP_DIR, session_hash)
     logging.info(f"[{session_hash}] Iniciando preprocess_image con prompt: '{prompt[:50]}...'")
 
-    if not image or 'composite' not in image or not isinstance(image['composite'], Image.Image):
-        logging.error(f"[{session_hash}] La entrada de imagen no es válida o está vacía.")
-        raise ValueError("Entrada de boceto no válida. Por favor, dibuja algo.")
+    if image is None:
+        logging.error(f"[{session_hash}] La entrada de imagen es nula.")
+        raise ValueError("La imagen de entrada no puede estar vacía.")
 
-    input_image = image['composite']
+    input_image = image
+    
     width, height = input_image.size
     ratio = np.sqrt(1024.0 * 1024.0 / (width * height))
     new_width, new_height = int(width * ratio), int(height * ratio)
     input_image = input_image.resize((new_width, new_height))
-    input_image = ImageOps.invert(input_image)
     
+    if input_image.mode == 'RGBA':
+        r, g, b, a = input_image.split()
+        rgb_image = Image.merge('RGB', (r, g, b))
+        inverted_image = ImageOps.invert(rgb_image)
+        inverted_image.putalpha(a)
+        input_image = inverted_image
+    else:
+        input_image = ImageOps.invert(input_image.convert('RGB'))
+
     prompt, negative_prompt = apply_style(style_name, prompt, negative_prompt)
     
     output_image = pipe_control(
@@ -136,90 +145,53 @@ def image_to_3d(
     session_hash = str(req.session_hash)
     user_dir = os.path.join(TMP_DIR, session_hash)
     logging.info(f"[{session_hash}] Iniciando image_to_3d desde la imagen: {image_path}")
-
     processed_image = pipeline.preprocess_image(Image.open(image_path))
-
     outputs = pipeline.run(
         processed_image,  
         seed=seed,
         formats=["gaussian", "mesh"],
         preprocess_image=False,
-        sparse_structure_sampler_params={
-            "steps": ss_sampling_steps,
-            "cfg_strength": ss_guidance_strength,
-        },
-        slat_sampler_params={
-            "steps": slat_sampling_steps,
-            "cfg_strength": slat_guidance_strength,
-        },
+        sparse_structure_sampler_params={"steps": ss_sampling_steps, "cfg_strength": ss_guidance_strength},
+        slat_sampler_params={"steps": slat_sampling_steps, "cfg_strength": slat_guidance_strength},
     )
-    
     logging.info(f"[{session_hash}] Generación del modelo completada. Renderizando video...")
     video = render_utils.render_video(outputs['gaussian'][0], num_frames=120)['color']
     video_geo = render_utils.render_video(outputs['mesh'][0], num_frames=120)['normal']
     video = [np.concatenate([video[i], video_geo[i]], axis=1) for i in range(len(video))]
     video_path = os.path.join(user_dir, 'sample.mp4')
     imageio.mimsave(video_path, video, fps=15)
-    
     state = pack_state(outputs['gaussian'][0], outputs['mesh'][0])
     torch.cuda.empty_cache()
     logging.info(f"[{session_hash}] Video renderizado y estado empaquetado. Devolviendo: {video_path}")
     return state, video_path
 
 @spaces.GPU(duration=90)
-def extract_glb(
-    state: dict,
-    mesh_simplify: float,
-    texture_size: int,
-    req: gr.Request,
-) -> Tuple[str, str]:
+def extract_glb(state: dict, mesh_simplify: float, texture_size: int, req: gr.Request) -> Tuple[str, str]:
     session_hash = str(req.session_hash)
     user_dir = os.path.join(TMP_DIR, session_hash)
     logging.info(f"[{session_hash}] Iniciando extract_glb...")
-
     gs, mesh = unpack_state(state)
     glb = postprocessing_utils.to_glb(gs, mesh, simplify=mesh_simplify, texture_size=texture_size, verbose=False)
     glb_path = os.path.join(user_dir, 'sample.glb')
     glb.export(glb_path)
-    
     torch.cuda.empty_cache()
     logging.info(f"[{session_hash}] GLB extraído. Devolviendo: {glb_path}")
     return glb_path, glb_path
 
 def pack_state(gs: Gaussian, mesh: MeshExtractResult) -> dict:
     return {
-        'gaussian': {
-            **gs.init_params,
-            '_xyz': gs._xyz.cpu().numpy(),
-            '_features_dc': gs._features_dc.cpu().numpy(),
-            '_scaling': gs._scaling.cpu().numpy(),
-            '_rotation': gs._rotation.cpu().numpy(),
-            '_opacity': gs._opacity.cpu().numpy(),
-        },
-        'mesh': {
-            'vertices': mesh.vertices.cpu().numpy(),
-            'faces': mesh.faces.cpu().numpy(),
-        },
+        'gaussian': {**gs.init_params, '_xyz': gs._xyz.cpu().numpy(), '_features_dc': gs._features_dc.cpu().numpy(), '_scaling': gs._scaling.cpu().numpy(), '_rotation': gs._rotation.cpu().numpy(), '_opacity': gs._opacity.cpu().numpy()},
+        'mesh': {'vertices': mesh.vertices.cpu().numpy(), 'faces': mesh.faces.cpu().numpy()},
     }
 
 def unpack_state(state: dict) -> Tuple[Gaussian, edict, str]:
-    gs = Gaussian(
-        aabb=state['gaussian']['aabb'],
-        sh_degree=state['gaussian']['sh_degree'],
-        mininum_kernel_size=state['gaussian']['mininum_kernel_size'],
-        scaling_bias=state['gaussian']['scaling_bias'],
-        opacity_bias=state['gaussian']['opacity_bias'],
-        scaling_activation=state['gaussian']['scaling_activation'],
-    )
+    gs = Gaussian(aabb=state['gaussian']['aabb'], sh_degree=state['gaussian']['sh_degree'], mininum_kernel_size=state['gaussian']['mininum_kernel_size'], scaling_bias=state['gaussian']['scaling_bias'], opacity_bias=state['gaussian']['opacity_bias'], scaling_activation=state['gaussian']['scaling_activation'])
     gs._xyz = torch.tensor(state['gaussian']['_xyz'], device='cuda')
     gs._features_dc = torch.tensor(state['gaussian']['_features_dc'], device='cuda')
     gs._scaling = torch.tensor(state['gaussian']['_scaling'], device='cuda')
     gs._rotation = torch.tensor(state['gaussian']['_rotation'], device='cuda')
     gs._opacity = torch.tensor(state['gaussian']['_opacity'], device='cuda')
-    mesh = edict(
-        vertices=torch.tensor(state['mesh']['vertices'], device='cuda'),
-        faces=torch.tensor(state['mesh']['faces'], device='cuda'),
-    )
+    mesh = edict(vertices=torch.tensor(state['mesh']['vertices'], device='cuda'), faces=torch.tensor(state['mesh']['faces'], device='cuda'))
     return gs, mesh
 
 @spaces.GPU
@@ -230,7 +202,7 @@ def extract_gaussian(state: dict, req: gr.Request) -> Tuple[str, str]:
     gs.save_ply(gaussian_path)
     torch.cuda.empty_cache()
     return gaussian_path, gaussian_path
-    
+
 with gr.Blocks(delete_cache=(600, 600)) as demo:
     gr.Markdown("""
     # UTPL - Conversión de Boceto a objetos 3D usando IA
@@ -241,15 +213,10 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
     """)
     with gr.Row():
         with gr.Column():
-            with gr.Column():    
-                image_prompt = gr.Image(
-                        label="Image Prompt", 
-                        format="png", 
-                        image_mode="RGBA", 
-                        type="pil", 
-                        height=300,
-                        show_label=False
-                    )
+            with gr.Column():
+                # --- ¡MODIFICADO! Cambiamos ImageEditor por Image ---
+                image_prompt = gr.Image(label="Input sketch", type="pil", image_mode="RGBA", height=512)
+                
                 with gr.Row():
                     sketch_btn = gr.Button("Process Sketch")
                     generate_btn = gr.Button("Generate 3D")