Update app.py

app.py

@@ -52,10 +52,9 @@ Prompt used for every video: "A robotic arm with a gripper and a small cube on a
 
 """
 
-
 perfo_description = """
 Our model has been benchmarked on a node of 4 Titan RTX 24Go GPUs, achieving an impressive 13 FPS image generation rate!
-The Table on the right shows the performances of our models running on different nodes.
+
 To make the benchmark, we loaded one of our model on every GPUs of the node. We then retrieve an episode of our simulation.
 For every frame of the episode, we preprocess the image (resize, canny, …) and process the Canny image on the GPUs.
 We repeated this procedure for different Batch Size (BS).