Update app.py

app.py

@@ -53,7 +53,7 @@ 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 8 A100 80Go GPUs, achieving an impressive 150 FPS image generation rate!
+Our model has been benchmarked on a node of 8 A100 80Go GPUs, achieving an impressive 170 FPS image generation rate!
 
 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.