Update app.py

app.py

@@ -8,7 +8,7 @@ from PIL import Image
 import numpy as np
 import os
 import time
-# import spaces  # Import spaces for ZeroGPU compatibility
+import spaces  # Import spaces for ZeroGPU compatibility
 
 
 # Load model and processor
@@ -29,7 +29,7 @@ tokenizer = vl_chat_processor.tokenizer
 cuda_device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
 @torch.inference_mode()
-# @spaces.GPU(duration=120) 
+@spaces.GPU(duration=120) 
 # Multimodal Understanding function
 def multimodal_understanding(image, question, seed, top_p, temperature):
     # Clear CUDA cache before generating
@@ -132,7 +132,7 @@ def unpack(dec, width, height, parallel_size=5):
 
 
 @torch.inference_mode()
-# @spaces.GPU(duration=120)  # Specify a duration to avoid timeout
+@spaces.GPU(duration=120)  # Specify a duration to avoid timeout
 def generate_image(prompt,
                    seed=None,
                    guidance=5,