Update trellis/pipelines/trellis_text_to_3d.py

trellis/pipelines/trellis_text_to_3d.py

@@ -3,7 +3,7 @@ import torch
 import torch.nn as nn
 import numpy as np
 from transformers import CLIPTextModel, AutoTokenizer
-import open3d as o3d
+#import open3d as o3d
 from .base import Pipeline
 from . import samplers
 from ..modules import sparse as sp
@@ -225,16 +225,9 @@ class TrellisTextTo3DPipeline(Pipeline):
         coords = self.sample_sparse_structure(cond, num_samples, sparse_structure_sampler_params)
         slat = self.sample_slat(cond, coords, slat_sampler_params)
         return self.decode_slat(slat, formats)
-    
+    """
     def voxelize(self, mesh: o3d.geometry.TriangleMesh) -> torch.Tensor:
-        """
-        Voxelize a mesh.
 
-        Args:
-            mesh (o3d.geometry.TriangleMesh): The mesh to voxelize.
-            sha256 (str): The SHA256 hash of the mesh.
-            output_dir (str): The output directory.
-        """
         vertices = np.asarray(mesh.vertices)
         aabb = np.stack([vertices.min(0), vertices.max(0)])
         center = (aabb[0] + aabb[1]) / 2
@@ -256,17 +249,7 @@ class TrellisTextTo3DPipeline(Pipeline):
         slat_sampler_params: dict = {},
         formats: List[str] = ['mesh', 'gaussian', 'radiance_field'],
     ) -> dict:
-        """
-        Run the pipeline for making variants of an asset.
 
-        Args:
-            mesh (o3d.geometry.TriangleMesh): The base mesh.
-            prompt (str): The text prompt.
-            num_samples (int): The number of samples to generate.
-            seed (int): The random seed
-            slat_sampler_params (dict): Additional parameters for the structured latent sampler.
-            formats (List[str]): The formats to decode the structured latent to.
-        """
         cond = self.get_cond([prompt])
         coords = self.voxelize(mesh)
         coords = torch.cat([
@@ -276,3 +259,4 @@ class TrellisTextTo3DPipeline(Pipeline):
         torch.manual_seed(seed)
         slat = self.sample_slat(cond, coords, slat_sampler_params)
         return self.decode_slat(slat, formats)
+    """