remove and to device

app.py

@@ -18,7 +18,7 @@ auth_token = os.environ.get("API_TOKEN") or True
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", dtype=torch.float16, revision="fp16", use_auth_token=auth_token)
+pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", dtype=torch.float16, revision="fp16", use_auth_token=auth_token).to(device)
 
 transform = transforms.Compose([
       transforms.ToTensor(),
@@ -35,10 +35,9 @@ def read_content(file_path: str) -> str:
     return content
 
 def predict(dict, prompt=""):
-    with autocast("cuda"):
-        init_image = dict["image"].convert("RGB").resize((512, 512))
-        mask = dict["mask"].convert("RGB").resize((512, 512))
-        output = pipe(prompt = prompt, image=init_image, mask_image=mask,guidance_scale=7.5)
+    init_image = dict["image"].convert("RGB").resize((512, 512))
+    mask = dict["mask"].convert("RGB").resize((512, 512))
+    output = pipe(prompt = prompt, image=init_image, mask_image=mask,guidance_scale=7.5)
     return output.images[0]