Update app.py

app.py

@@ -16,14 +16,14 @@ if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo may not work on CPU.</p>"
 
 MAX_SEED = np.iinfo(np.int32).max
-CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES", "1") == "0"
+CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES", "1") == "1"
 MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "1536"))
 USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE", "0") == "1"
 ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD", "0") == "1"
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-NUM_IMAGES_PER_PROMPT = 16
+NUM_IMAGES_PER_PROMPT = 8
 
 if torch.cuda.is_available():
     pipe = DiffusionPipeline.from_pretrained(