Update app.py

app.py

@@ -3,27 +3,24 @@ import numpy as np
 import random
 from diffusers import DiffusionPipeline
 import torch
+import spaces
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
-if torch.cuda.is_available():
-    torch.cuda.max_memory_allocated(device=device)
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
-    pipe.enable_xformers_memory_efficient_attention()
-    pipe = pipe.to(device)
-else: 
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
-    pipe = pipe.to(device)
+device = "cuda"
 
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
 
+@spaces.GPU
 def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
 
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
         
     generator = torch.Generator().manual_seed(seed)
+
+    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
+    pipe.enable_xformers_memory_efficient_attention()
+    pipe = pipe.to(device)
     
     image = pipe(
         prompt = prompt, 
@@ -50,10 +47,8 @@ css="""
 }
 """
 
-if torch.cuda.is_available():
-    power_device = "GPU"
-else:
-    power_device = "CPU"
+
+power_device = "GPU"
 
 with gr.Blocks(css=css) as demo: