Update description

app.py

@@ -102,7 +102,8 @@ def main():
             The model used in the demo was trained on **Objaverse-LVIS on 2 A6000 GPUs for 3.5 days**.
             Locally, on an NVIDIA V100 GPU, reconstruction (forward pass of the network) can be done at 38FPS and rendering (with Gaussian Splatting) at 588FPS.
             Upload an image of an object or click on one of the provided examples to see how the Splatter Image does.
-            For best results clone the [main repository](https://github.com/szymanowiczs/splatter-image) and run the demo locally.
+            The 3D viewer will render a .ply object exported from the 3D Gaussians, which is only an approximation.
+            For best results run the demo locally and render locally with Gaussian Splatting - to do so, clone the [main repository](https://github.com/szymanowiczs/splatter-image).
             """
             )
         with gr.Row(variant="panel"):
@@ -158,7 +159,7 @@ def main():
             1. If you run the demo online, the first example you upload should take about 4.5 seconds (with preprocessing, saving and overhead), the following take about 1.5s.
             2. The 3D viewer shows a .ply mesh extracted from a mix of 3D Gaussians. This is only an approximations and artefacts might show.
             3. Known limitations include:
-            - sphere-like artefacts on the object and white halo around it: this is due to how the .ply mesh is extracted and limitations of the Gradio viewer
+            - a black dot appearing on the model from some viewpoints
             - see-through parts of objects, especially on the back: this is due to the model performing less well on more complicated shapes
             - back of objects are blurry: this is a model limiation due to it being deterministic
             4. Our model is of comparable quality to state-of-the-art methods, and is **much** cheaper to train and run.