.

app.py

@@ -120,11 +120,11 @@ def text_to_3d(
             "cfg_strength": slat_guidance_strength,
         },
     )
-    # 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 = 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)
+    imageio.mimsave(video_path, video, fps=15)
     state = pack_state(outputs['gaussian'][0], outputs['mesh'][0])
     torch.cuda.empty_cache()
     return state, video_path

trellis/pipelines/trellis_text_to_3d.py

@@ -220,15 +220,10 @@ class TrellisTextTo3DPipeline(Pipeline):
             slat_sampler_params (dict): Additional parameters for the structured latent sampler.
             formats (List[str]): The formats to decode the structured latent to.
         """
-        print(0)
         cond = self.get_cond([prompt])
-        print(1)
         torch.manual_seed(seed)
-        print(2)
         coords = self.sample_sparse_structure(cond, num_samples, sparse_structure_sampler_params)
-        print(3)
         slat = self.sample_slat(cond, coords, slat_sampler_params)
-        print(4)
         return self.decode_slat(slat, formats)
 '''    
     def voxelize(self, mesh: o3d.geometry.TriangleMesh) -> torch.Tensor: