Update app.py

app.py

@@ -1,3 +1,5 @@
+# app.py (en el Space de Hugging Face para Boceto a 3D)
+
 import gradio as gr
 import spaces
 import os
@@ -17,6 +19,10 @@ import torchvision.transforms.functional as TF
 from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
 from diffusers import DDIMScheduler, EulerAncestralDiscreteScheduler
 from pathlib import Path
+import logging
+
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - HF_SPACE_BOCETO - %(levelname)s - %(message)s')
+
 style_list = [
     {
         "name": "(No style)",
@@ -41,29 +47,42 @@ style_list = [
 ]
 styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list}
 STYLE_NAMES = list(styles.keys())
-DEFAULT_STYLE_NAME = "(No style)"
+DEFAULT_STYLE_NAME = "3D Model"
 MAX_SEED = np.iinfo(np.int32).max
 TMP_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tmp')
 os.makedirs(TMP_DIR, exist_ok=True)
 
-def reset_canvas():
-    return gr.update(value={"background":Image.new("RGB", (512, 512), (255, 255, 255)), "layers":[Image.new("RGB", (512, 512), (255, 255, 255))], "composite":Image.new("RGB", (512, 512), (255, 255, 255))})
+def start_session(req: gr.Request):
+    session_hash = str(req.session_hash)
+    user_dir = os.path.join(TMP_DIR, session_hash)
+    logging.info(f"START SESSION: Creando directorio para la sesión {session_hash} en {user_dir}")
+    os.makedirs(user_dir, exist_ok=True)
+
+def end_session(req: gr.Request):
+    session_hash = str(req.session_hash)
+    user_dir = os.path.join(TMP_DIR, session_hash)
+    logging.info(f"END SESSION: Intentando eliminar el directorio de la sesión {session_hash} en {user_dir}")
+    if os.path.exists(user_dir):
+        try:
+            shutil.rmtree(user_dir)
+            logging.info(f"Directorio de la sesión {session_hash} eliminado correctamente.")
+        except Exception as e:
+            logging.error(f"Error al eliminar el directorio de la sesión {session_hash}: {e}")
+    else:
+        logging.warning(f"El directorio de la sesión {session_hash} no fue encontrado al intentar eliminarlo. Es posible que ya haya sido limpiado.")
 
 def apply_style(style_name: str, positive: str, negative: str = "") -> tuple[str, str]:
     p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
     return p.replace("{prompt}", positive), n + negative
 
-def start_session(req: gr.Request):
-    user_dir = os.path.join(TMP_DIR, str(req.session_hash))
-    os.makedirs(user_dir, exist_ok=True)
-
-def end_session(req: gr.Request):
-    user_dir = os.path.join(TMP_DIR, str(req.session_hash))
-    shutil.rmtree(user_dir)
+def get_seed(randomize_seed: bool, seed: int) -> int:
+    new_seed = np.random.randint(0, MAX_SEED) if randomize_seed else seed
+    logging.info(f"Usando seed: {new_seed}")
+    return new_seed
 
 @spaces.GPU
 def preprocess_image(
-    image: Image.Image,
+    image: dict,
     prompt: str = "",
     negative_prompt: str = "",
     style_name: str = "",
@@ -71,24 +90,28 @@ def preprocess_image(
     guidance_scale: float = 5,
     controlnet_conditioning_scale: float = 1.0,
     req: gr.Request = None,
-) -> Image.Image:
-    user_dir = os.path.join(TMP_DIR, str(req.session_hash))
-    os.makedirs(user_dir, exist_ok=True)
-    
-    width, height = image['composite'].size
+) -> str:
+    session_hash = str(req.session_hash)
+    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.")
+
+    input_image = image['composite']
+    width, height = input_image.size
     ratio = np.sqrt(1024.0 * 1024.0 / (width * height))
     new_width, new_height = int(width * ratio), int(height * ratio)
-    image = image['composite'].resize((new_width, new_height))
-    image = ImageOps.invert(image)
-    print("image:", type(image))
+    input_image = input_image.resize((new_width, new_height))
+    input_image = ImageOps.invert(input_image)
     
     prompt, negative_prompt = apply_style(style_name, prompt, negative_prompt)
-    print("params:", prompt, negative_prompt, style_name, num_steps, guidance_scale, controlnet_conditioning_scale)
     
-    output = pipe_control(
+    output_image = pipe_control(
         prompt=prompt,
         negative_prompt=negative_prompt,
-        image=image,
+        image=input_image,
         num_inference_steps=num_steps,
         controlnet_conditioning_scale=controlnet_conditioning_scale,
         guidance_scale=guidance_scale,
@@ -97,54 +120,14 @@ def preprocess_image(
     ).images[0]
     
     processed_image_path = os.path.join(user_dir, 'processed_image.png')
-    output.save(processed_image_path)
-
-    processed_image = pipeline.preprocess_image(output)
+    output_image.save(processed_image_path)
+    logging.info(f"[{session_hash}] Imagen preprocesada y guardada en: {processed_image_path}")
     
-    return processed_image  
-
-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(),
-        },
-    }
-
-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._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'),
-    )
-    return gs, mesh
-
-def get_seed(randomize_seed: bool, seed: int) -> int:
-    return np.random.randint(0, MAX_SEED) if randomize_seed else seed
+    return processed_image_path
 
 @spaces.GPU
 def image_to_3d(
-    image: Image.Image,
+    image_path: str,
     seed: int,
     ss_guidance_strength: float,
     ss_sampling_steps: int,
@@ -152,9 +135,14 @@ def image_to_3d(
     slat_sampling_steps: int,
     req: gr.Request,
 ) -> Tuple[dict, str]:
-    user_dir = os.path.join(TMP_DIR, str(req.session_hash))
+    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(
-        image,  
+        processed_image,  
         seed=seed,
         formats=["gaussian", "mesh"],
         preprocess_image=False,
@@ -167,13 +155,17 @@ def image_to_3d(
             "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)
@@ -183,17 +175,56 @@ def extract_glb(
     texture_size: int,
     req: gr.Request,
 ) -> Tuple[str, str]:
-    user_dir = os.path.join(TMP_DIR, str(req.session_hash))
+    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 reset_do_preprocess():
-    return True
+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(),
+        },
+    }
 
+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._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'),
+    )
+    return gs, mesh
+
+@spaces.GPU
 def extract_gaussian(state: dict, req: gr.Request) -> Tuple[str, str]:
     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
     gs, _ = unpack_state(state)
@@ -201,7 +232,7 @@ 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
@@ -213,20 +244,20 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
     with gr.Row():
         with gr.Column():
             with gr.Column():    
-                image_prompt = gr.ImageEditor(label="Input sketch", type="pil", image_mode="RGB", height=512, value={"background":Image.new("RGB", (512, 512), (255, 255, 255)), "layers":[Image.new("RGB", (512, 512), (255, 255, 255))], "composite":Image.new("RGB", (512, 512), (255, 255, 255))})
+                image_prompt = gr.ImageEditor(label="Input sketch", type="pil", image_mode="RGB", height=512)
                 with gr.Row():
-                    sketch_btn = gr.Button("process sketch")
+                    sketch_btn = gr.Button("Process Sketch")
                     generate_btn = gr.Button("Generate 3D")
                 with gr.Row():
                     prompt = gr.Textbox(label="Prompt")
                     style = gr.Dropdown(label="Style", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
                 with gr.Accordion(label="Generation Settings", open=False):
-                    with gr.Tab(label="sketch-to-image generation"):
+                    with gr.Tab(label="Sketch-to-Image Generation"):
                         negative_prompt = gr.Textbox(label="Negative prompt")
                         num_steps = gr.Slider(1, 20, label="Number of steps", value=8, step=1)
                         guidance_scale = gr.Slider(0.1, 10.0, label="Guidance scale", value=5, step=0.1)
-                        controlnet_conditioning_scale = gr.Slider(0.5, 5.0, label="controlnet conditioning scale", value=0.85, step=0.01)
-                    with gr.Tab(label="3D generation"):
+                        controlnet_conditioning_scale = gr.Slider(0.5, 5.0, label="ControlNet Conditioning Scale", value=0.85, step=0.01)
+                    with gr.Tab(label="3D Generation"):
                         seed = gr.Slider(0, MAX_SEED, label="Seed", value=0, step=1)
                         randomize_seed = gr.Checkbox(label="Randomize Seed", value=True)
                         gr.Markdown("Stage 1: Sparse Structure Generation")
@@ -245,31 +276,22 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
                 extract_gs_btn = gr.Button("Extract Gaussian", interactive=False)
         with gr.Column():
             video_output = gr.Video(label="Generated 3D Asset", autoplay=True, loop=True, height=300)
-            image_prompt_processed = gr.Image(label="processed sketch", interactive=False, type="pil", height=512)
+            image_prompt_processed = gr.Image(label="Processed Sketch", interactive=False, type="filepath", height=512)
             model_output = gr.Model3D(label="Extracted GLB/Gaussian", height=300)
             with gr.Row():
                 download_glb = gr.DownloadButton(label="Download GLB", interactive=False)
                 download_gs = gr.DownloadButton(label="Download Gaussian", interactive=False)  
 
-    do_preprocess = gr.State(True)
     output_buf = gr.State()
 
     demo.load(start_session)
     demo.unload(end_session)
 
-    image_prompt.clear(
-        fn=reset_canvas,
-        outputs = [image_prompt]
-    )
-
     sketch_btn.click(
-        get_seed,
-        inputs=[randomize_seed, seed],
-        outputs=[seed],
-    ).then(
         preprocess_image,
         inputs=[image_prompt, prompt, negative_prompt, style, num_steps, guidance_scale, controlnet_conditioning_scale],
         outputs=[image_prompt_processed],
+        api_name="preprocess_image" 
     )
 
     generate_btn.click(
@@ -280,7 +302,10 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
         image_to_3d,
         inputs=[image_prompt_processed, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps],
         outputs=[output_buf, video_output],
-    ).then(
+        api_name="image_to_3d"
+    )
+
+    generate_btn.click(
         lambda: tuple([gr.Button(interactive=True), gr.Button(interactive=True)]),
         outputs=[extract_glb_btn, extract_gs_btn],
     )
@@ -294,18 +319,24 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
         extract_glb,
         inputs=[output_buf, mesh_simplify, texture_size],
         outputs=[model_output, download_glb],
-    ).then(
+        api_name="extract_glb" 
+    )
+    
+    extract_glb_btn.click(
         lambda: gr.Button(interactive=True),
-        outputs=[download_glb],
+        outputs=[download_glb]
     )
-
+    
     extract_gs_btn.click(
         extract_gaussian,
         inputs=[output_buf],
         outputs=[model_output, download_gs],
-    ).then(
+        api_name="extract_gaussian" 
+    )
+
+    extract_gs_btn.click(
         lambda: gr.Button(interactive=True),
-        outputs=[download_gs],
+        outputs=[download_gs]
     )
 
     model_output.clear(
@@ -317,22 +348,13 @@ if __name__ == "__main__":
     pipeline = TrellisImageTo3DPipeline.from_pretrained("cavargas10/TRELLIS")
     pipeline.cuda()
     device = "cuda" if torch.cuda.is_available() else "cpu"
-    #scribble controlnet
-    controlnet = ControlNetModel.from_pretrained(
-    "xinsir/controlnet-scribble-sdxl-1.0",
-    torch_dtype=torch.float16
-)
+    controlnet = ControlNetModel.from_pretrained("xinsir/controlnet-scribble-sdxl-1.0", torch_dtype=torch.float16)
     vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
-    pipe_control = StableDiffusionXLControlNetPipeline.from_pretrained(
-        "sd-community/sdxl-flash",
-        controlnet=controlnet,
-        vae=vae,
-        torch_dtype=torch.float16,
-    )
+    pipe_control = StableDiffusionXLControlNetPipeline.from_pretrained("sd-community/sdxl-flash", controlnet=controlnet, vae=vae, torch_dtype=torch.float16)
     pipe_control.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe_control.scheduler.config)
     pipe_control.to(device)
     try:
-        pipeline.preprocess_image(Image.fromarray(np.zeros((512, 512, 3), dtype=np.uint8)))    # Preload rembg
+        pipeline.preprocess_image(Image.fromarray(np.zeros((512, 512, 3), dtype=np.uint8)))
     except:
         pass
     demo.launch()