Update app.py

app.py

@@ -1,3 +1,4 @@
+import spaces
 from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL, EulerAncestralDiscreteScheduler
 from diffusers.utils import load_image
 from PIL import Image
@@ -28,7 +29,7 @@ pipe.scheduler = EulerAncestralDiscreteScheduler(
     steps_offset=1
 )
 # pipe.enable_freeu(b1=1.1, b2=1.1, s1=0.5, s2=0.7)
-pipe.enable_xformers_memory_efficient_attention()
+# pipe.enable_xformers_memory_efficient_attention()
 pipe.force_zeros_for_empty_prompt = False
 
 from transformers import DPTFeatureExtractor, DPTForDepthEstimation
@@ -65,21 +66,29 @@ def get_depth_map(image):
     return image
 
 
+@spaces.GPU
+def generate_(prompt, negative_prompt, canny_image, num_steps, controlnet_conditioning_scale, seed):
+    generator = torch.Generator("cuda").manual_seed(seed)    
+    images = pipe(
+    prompt, negative_prompt=negative_prompt, image=canny_image, num_inference_steps=num_steps, controlnet_conditioning_scale=float(controlnet_conditioning_scale),
+    generator=generator,
+    ).images
+    return images
+
+@spaces.GPU
 def process(input_image, prompt, negative_prompt, num_steps, controlnet_conditioning_scale, seed):
-    generator = torch.manual_seed(seed)
     
     # resize input_image to 1024x1024
     input_image = resize_image(input_image)
     
     depth_image = get_depth_map(input_image)
   
-    images = pipe(
-        prompt, negative_prompt=negative_prompt, image=depth_image, num_inference_steps=num_steps, controlnet_conditioning_scale=float(controlnet_conditioning_scale),
-        generator=generator,
-        ).images
+    images = generate_(prompt, negative_prompt, depth_image, num_steps, controlnet_conditioning_scale, seed)
 
     return [depth_image, images[0]]
-    
+
+
+
 block = gr.Blocks().queue()
 
 with block: