add octree depth controls

app.py

@@ -67,7 +67,9 @@ rmbg_net = BriaRMBG.from_pretrained(rmbg_path).to(device)
 rmbg_net.eval()
 
 
-def generate(image_path, face_number=50000, guidance_scale=5.0, num_steps=25):
+# def generate(image_path, face_number=50000, guidance_scale=5.0, num_steps=25):
+def generate(image_path, face_number=50000, octree_depth=9, guidance_scale=5.0, num_steps=25):
+    print(f"[INPUT] octree_depth={octree_depth}, face_number={face_number}, guidance_scale={guidance_scale}, num_steps={num_steps}")# 👈 добавлено
     print("[API CALL] image_path received:", image_path)
     print("[API CALL] File exists:", os.path.exists(image_path))
 
@@ -84,6 +86,7 @@ def generate(image_path, face_number=50000, guidance_scale=5.0, num_steps=25):
             num_inference_steps=int(num_steps),
             guidance_scale=float(guidance_scale),
             faces=int(face_number),
+            octree_depth=int(octree_depth), # 👈 добавлено
         )
 
         if mesh is None or mesh.vertices.shape[0] == 0 or mesh.faces.shape[0] == 0:
@@ -125,7 +128,14 @@ def generate(image_path, face_number=50000, guidance_scale=5.0, num_steps=25):
 # Интерфейс Gradio
 demo = gr.Interface(
     fn=generate,
-    inputs=gr.Image(type="filepath", label="Upload image"),
+    # inputs=gr.Image(type="filepath", label="Upload image"),
+    inputs=[
+        gr.Image(type="filepath", label="Upload image"),
+        gr.Slider(10000, 150000, step=10000, value=50000, label="Face count"),
+        gr.Slider(6, 10, step=1, value=9, label="Octree Depth"),
+        gr.Slider(1.0, 10.0, step=0.5, value=5.0, label="Guidance Scale"),
+        gr.Slider(10, 100, step=5, value=25, label="Steps"),
+    ], # 👈 добавлено
     outputs=gr.File(label="Download .glb"),
     title="TripoSG Image to 3D",
     description="Upload an image to generate a 3D model (.glb)",

app_backlog.py

@@ -302,6 +302,192 @@
 
 
 
+# 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
+# import numpy as np
+# 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")
+
+# #         mesh = trimesh.Trimesh(vertices=mesh.vertices, faces=mesh.faces)
+# #         mesh.rezero()
+# #         mesh.fix_normals()
+# #         mesh.apply_translation(-mesh.center_mass)  
+
+# #         # Масштабируем, чтобы модель вписывалась в размер 1x1x1 
+# #         # Если нужно будет подгонять под размер в Endless Tools, то можно использовать:
+# #         # scale_factor = 1.0 / np.max(np.linalg.norm(mesh.vertices, axis=1))
+# #         # mesh.apply_scale(scale_factor)
+
+
+# #         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}"
+
+# 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")
+
+#         # 🔧 Пересоздаём Trimesh и гарантируем чистоту геометрии
+#         mesh = trimesh.Trimesh(vertices=mesh.vertices, faces=mesh.faces, process=True)
+
+#         # ✅ Центрируе�� модель
+#         mesh.apply_translation(-mesh.center_mass)
+
+#         # ✅ Масштабируем к единичному размеру (все модели ~одинаковые)
+#         scale_factor = 1.0 / np.max(np.linalg.norm(mesh.vertices, axis=1))
+#         mesh.apply_scale(scale_factor)
+
+#         # ✅ Гарантированно пересчитываем нормали
+#         mesh.fix_normals()
+
+#         # print("[DEBUG] Normals present:", mesh.has_vertex_normals)
+#         if hasattr(mesh, "vertex_normals"):
+#             print("[DEBUG] Normals shape:", mesh.vertex_normals.shape)
+#         else:
+#             print("[DEBUG] Normals missing.")
+
+
+#         # 💾 Сохраняем GLB
+#         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()
+
+
+
+
+
+
+
+
+
+
 import os
 import subprocess
 
@@ -324,12 +510,15 @@ import requests
 import traceback
 import trimesh
 import numpy as np
+
+
 from trimesh.exchange.gltf import export_glb
 
 from inference_triposg import run_triposg
 from triposg.pipelines.pipeline_triposg import TripoSGPipeline
 from briarmbg import BriaRMBG
 
+GLTF_PACK = "/tmp/gltfpack"
 
 print("Trimesh version:", trimesh.__version__)
 
@@ -365,51 +554,6 @@ 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")
-
-#         mesh = trimesh.Trimesh(vertices=mesh.vertices, faces=mesh.faces)
-#         mesh.rezero()
-#         mesh.fix_normals()
-#         mesh.apply_translation(-mesh.center_mass)  
-
-#         # Масштабируем, чтобы модель вписывалась в размер 1x1x1 
-#         # Если нужно будет подгонять под размер в Endless Tools, то можно использовать:
-#         # scale_factor = 1.0 / np.max(np.linalg.norm(mesh.vertices, axis=1))
-#         # mesh.apply_scale(scale_factor)
-
-
-#         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}"
 
 def generate(image_path, face_number=50000, guidance_scale=5.0, num_steps=25):
     print("[API CALL] image_path received:", image_path)
@@ -452,7 +596,6 @@ def generate(image_path, face_number=50000, guidance_scale=5.0, num_steps=25):
         else:
             print("[DEBUG] Normals missing.")
 
-
         # 💾 Сохраняем GLB
         glb_data = mesh.export(file_type='glb')
         with open(output_path, "wb") as f:
@@ -476,5 +619,7 @@ demo = gr.Interface(
     description="Upload an image to generate a 3D model (.glb)",
 )
 
+
+
 # Запуск
 demo.launch()

inference_triposg.py

@@ -54,6 +54,7 @@ def run_triposg(
     num_inference_steps: int = 50,
     guidance_scale: float = 7.0,
     faces: int = -1,
+    octree_depth: int = 9, # 👈 добавлено
 ) -> trimesh.Scene:
     print("[DEBUG] Preparing image...")
     img_pil = prepare_image(image_input, bg_color=np.array([1.0, 1.0, 1.0]), rmbg_net=rmbg_net)
@@ -64,6 +65,7 @@ def run_triposg(
         generator=torch.Generator(device=pipe.device).manual_seed(seed),
         num_inference_steps=num_inference_steps,
         guidance_scale=guidance_scale,
+        flash_octree_depth=octree_depth, # 👈 добавлено
     ).samples[0]
 
     print("[DEBUG] TripoSG output keys:", type(outputs), outputs[0].shape, outputs[1].shape)