# import os # import subprocess # # Убираем pyenv, если вдруг остался .python-version # os.environ.pop("PYENV_VERSION", None) # # Установка зависимостей # subprocess.run(["pip", "install", "torch", "wheel"], check=True) # subprocess.run([ # "pip", "install", "--no-build-isolation", # "diso@git+https://github.com/SarahWeiii/diso.git" # ], check=True) # # Импорты # import gradio as gr # import uuid # import torch # import zipfile # import requests # import traceback # import trimesh # from trimesh.exchange.gltf import export_glb # print("Trimesh version:", trimesh.__version__) # from inference_triposg import run_triposg # from triposg.pipelines.pipeline_triposg import TripoSGPipeline # from briarmbg import BriaRMBG # # Настройки устройства # device = "cuda" if torch.cuda.is_available() else "cpu" # dtype = torch.float16 if device == "cuda" else torch.float32 # # Загрузка весов # weights_dir = "pretrained_weights" # triposg_path = os.path.join(weights_dir, "TripoSG") # rmbg_path = os.path.join(weights_dir, "RMBG-1.4") # if not (os.path.exists(triposg_path) and os.path.exists(rmbg_path)): # print("📦 Downloading pretrained weights...") # url = "https://huggingface.co/datasets/endlesstools/pretrained-assets/resolve/main/pretrained_models.zip" # zip_path = "pretrained_models.zip" # with requests.get(url, stream=True) as r: # r.raise_for_status() # with open(zip_path, "wb") as f: # for chunk in r.iter_content(chunk_size=8192): # f.write(chunk) # print("📦 Extracting weights...") # with zipfile.ZipFile(zip_path, "r") as zip_ref: # zip_ref.extractall(weights_dir) # os.remove(zip_path) # print("✅ Weights ready.") # # Загрузка моделей # pipe = TripoSGPipeline.from_pretrained(triposg_path).to(device, dtype) # rmbg_net = BriaRMBG.from_pretrained(rmbg_path).to(device) # rmbg_net.eval() # # Генерация .glb # # def generate(image_path): # def generate(image_path, face_number=50000, guidance_scale=5.0, num_steps=25): # print("[API CALL] image_path received:", image_path) # print("[API CALL] File exists:", os.path.exists(image_path)) # temp_id = str(uuid.uuid4()) # output_path = f"/tmp/{temp_id}.glb" # print("[DEBUG] Generating mesh from:", image_path) # try: # # mesh = run_triposg( # # pipe=pipe, # # image_input=image_path, # # rmbg_net=rmbg_net, # # seed=42, # # num_inference_steps=25, # # guidance_scale=5.0, # # faces=-1, # # ) # mesh = run_triposg( # pipe=pipe, # image_input=image_path, # rmbg_net=rmbg_net, # seed=42, # num_inference_steps=int(num_steps), # guidance_scale=float(guidance_scale), # faces=int(face_number), # ) # # if mesh is None: # # raise ValueError("Mesh generation failed") # # mesh.export(output_path) # # print(f"[DEBUG] Mesh saved to {output_path}") # # return output_path if os.path.exists(output_path) else "Error: output file not found" # # if mesh is None: # # raise ValueError("Mesh generation failed") # # # Убираем визуал, метаданные, обертки # # mesh.visual = None # # mesh.metadata.clear() # # mesh.name = "endless_tools" # # # Экспорт только геометрии # # glb_data = mesh.export(file_type="glb") # # with open(output_path, "wb") as f: # # f.write(glb_data) # # print(f"[DEBUG] Mesh saved to {output_path}") # # return output_path if os.path.exists(output_path) else "Error: output file not found" # if mesh is None: # raise ValueError("Mesh generation returned None") # # Очистка визуала, метаданных и имени # mesh.visual = None # mesh.metadata.clear() # mesh.name = "geometry_0" # # glb_data = mesh.export(file_type="glb") # glb_data = export_glb(mesh) # with open(output_path, "wb") as f: # f.write(glb_data) # # Экспорт .glb вручную (иначе Trimesh добавляет сцену) # # glb_data = mesh.export(file_type="glb") # # with open(output_path, "wb") as f: # # f.write(glb_data) # print(f"[DEBUG] Mesh saved to {output_path}") # return output_path if os.path.exists(output_path) else None # # except Exception as e: # # print("[ERROR]", e) # # return f"Error: {e}" # except Exception as e: # # import traceback # print("[ERROR]", e) # traceback.print_exc() # ← выведет полную трассировку в логи # return f"Error: {e}" # # Интерфейс Gradio # demo = gr.Interface( # fn=generate, # inputs=gr.Image(type="filepath", label="Upload image"), # outputs=gr.File(label="Download .glb"), # title="TripoSG Image to 3D", # description="Upload an image to generate a 3D model (.glb)", # ) # # Запуск # demo.launch() import os import subprocess # Убираем pyenv os.environ.pop("PYENV_VERSION", None) # Установка зависимостей subprocess.run(["pip", "install", "torch", "wheel"], check=True) subprocess.run([ "pip", "install", "--no-build-isolation", "diso@git+https://github.com/SarahWeiii/diso.git" ], check=True) # Импорты (перенесены после установки зависимостей) import gradio as gr import uuid import torch import zipfile import requests import traceback import trimesh from trimesh.exchange.gltf import export_glb from inference_triposg import run_triposg from triposg.pipelines.pipeline_triposg import TripoSGPipeline from briarmbg import BriaRMBG print("Trimesh version:", trimesh.__version__) # Настройки устройства device = "cuda" if torch.cuda.is_available() else "cpu" dtype = torch.float16 if device == "cuda" else torch.float32 # Загрузка весов weights_dir = "pretrained_weights" triposg_path = os.path.join(weights_dir, "TripoSG") rmbg_path = os.path.join(weights_dir, "RMBG-1.4") if not (os.path.exists(triposg_path) and os.path.exists(rmbg_path)): print("📦 Downloading pretrained weights...") url = "https://huggingface.co/datasets/endlesstools/pretrained-assets/resolve/main/pretrained_models.zip" zip_path = "pretrained_models.zip" with requests.get(url, stream=True) as r: r.raise_for_status() with open(zip_path, "wb") as f: for chunk in r.iter_content(chunk_size=8192): f.write(chunk) print("📦 Extracting weights...") with zipfile.ZipFile(zip_path, "r") as zip_ref: zip_ref.extractall(weights_dir) os.remove(zip_path) print("✅ Weights ready.") # Загрузка моделей pipe = TripoSGPipeline.from_pretrained(triposg_path).to(device, dtype) rmbg_net = BriaRMBG.from_pretrained(rmbg_path).to(device) rmbg_net.eval() # Генерация .glb def generate(image_path, face_number=50000, guidance_scale=5.0, num_steps=25): print("[API CALL] image_path received:", image_path) print("[API CALL] File exists:", os.path.exists(image_path)) temp_id = str(uuid.uuid4()) output_path = f"/tmp/{temp_id}.glb" print("[DEBUG] Generating mesh from:", image_path) try: mesh = run_triposg( pipe=pipe, image_input=image_path, rmbg_net=rmbg_net, seed=42, num_inference_steps=int(num_steps), guidance_scale=float(guidance_scale), faces=int(face_number), ) if mesh is None or mesh.vertices.shape[0] == 0 or mesh.faces.shape[0] == 0: raise ValueError("Mesh generation returned an empty mesh") # Безопасная очистка визуала if hasattr(mesh, "visual") and mesh.visual is not None: try: mesh.visual = None except Exception: print("[WARN] Failed to clear visual, skipping") mesh.metadata.clear() mesh.name = "endless_tools_mesh" # Экспорт .glb # glb_data = export_glb(mesh) glb_data = mesh.export(file_type='glb') with open(output_path, "wb") as f: f.write(glb_data) print(f"[DEBUG] Mesh saved to {output_path}") return output_path if os.path.exists(output_path) else None except Exception as e: print("[ERROR]", e) traceback.print_exc() return f"Error: {e}" # Интерфейс Gradio demo = gr.Interface( fn=generate, inputs=gr.Image(type="filepath", label="Upload image"), outputs=gr.File(label="Download .glb"), title="TripoSG Image to 3D", description="Upload an image to generate a 3D model (.glb)", ) # Запуск demo.launch()