Update app.py

app.py

@@ -10,6 +10,13 @@ from sam2.sam2_image_predictor import SAM2ImagePredictor
 import numpy as np
 from simple_lama_inpainting import SimpleLama
 
+if device.type == "cuda":
+    # use bfloat16 for the entire notebook
+    torch.autocast("cuda", dtype=torch.bfloat16).__enter__()
+    # turn on tfloat32 for Ampere GPUs (https://pytorch.org/docs/stable/notes/cuda.html#tensorfloat-32-tf32-on-ampere-devices)
+    if torch.cuda.get_device_properties(0).major >= 8:
+        torch.backends.cuda.matmul.allow_tf32 = True
+        torch.backends.cudnn.allow_tf32 = True
 
 pipe = FluxFillPipeline.from_pretrained(
     "black-forest-labs/FLUX.1-Fill-dev", torch_dtype=torch.bfloat16