even earlier

app.py

@@ -89,7 +89,7 @@ def text_to_3d(
     slat_guidance_strength: float,
     slat_sampling_steps: int,
     req: gr.Request,
-) -> Tuple[dict, str, dict]:
+) -> Tuple[dict, str]:
     """
     Convert an text prompt to a 3D model.
     Args:
@@ -102,7 +102,6 @@ def text_to_3d(
     Returns:
         dict: The information of the generated 3D model.
         str: The path to the video of the 3D model.
-        dict: The state of the generated 3D model.
     """
     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
     os.makedirs(user_dir, exist_ok=True)
@@ -126,8 +125,7 @@ def text_to_3d(
     imageio.mimsave(video_path, video, fps=15)
     state = pack_state(outputs['gaussian'][0], outputs['mesh'][0])
     torch.cuda.empty_cache()
-    # Return state for JSON, video path for Video, and state again for internal buffer
-    return state, video_path, state
+    return state, video_path
 
 
 @spaces.GPU(duration=90)