change to cpu

app.py

@@ -2,14 +2,12 @@ import gradio as gr
 from diffusers import DiffusionPipeline
 import torch
 from PIL import Image, ImageOps
-import requests
-from io import BytesIO
 from transparent_background import Remover
 
 # Initialize the Diffusion Pipeline
 model_id = "yahoo-inc/photo-background-generation"
 pipeline = DiffusionPipeline.from_pretrained(model_id, custom_pipeline=model_id)
-pipeline = pipeline.to('cpu')
+pipeline = pipeline.to('cpu')  # Use CPU instead of CUDA
 
 def resize_with_padding(img, expected_size):
     img.thumbnail((expected_size[0], expected_size[1]))
@@ -21,7 +19,6 @@ def resize_with_padding(img, expected_size):
     return ImageOps.expand(img, padding)
 
 def process_image(input_image, prompt):
-    # Resize and process the input image
     img = resize_with_padding(input_image, (512, 512))
 
     # Load background detection model
@@ -33,10 +30,10 @@ def process_image(input_image, prompt):
     seed = 13
     mask = ImageOps.invert(fg_mask)
     img = resize_with_padding(img, (512, 512))
-    generator = torch.Generator(device='cuda').manual_seed(seed)
+    generator = torch.Generator(device='cpu').manual_seed(seed)  # Use CPU generator
     cond_scale = 1.0
 
-    with torch.autocast("cuda"):
+    with torch.no_grad():  # Disable gradient calculations for inference
         controlnet_image = pipeline(
             prompt=prompt, 
             image=img, 
@@ -55,10 +52,10 @@ def process_image(input_image, prompt):
 iface = gr.Interface(
     fn=process_image, 
     inputs=[
-        gr.inputs.Image(type="pil", label="Upload Image"), 
-        gr.inputs.Textbox(label="Enter Prompt")
+        gr.Image(type="pil", label="Upload Image"), 
+        gr.Textbox(label="Enter Prompt")
     ],
-    outputs=gr.outputs.Image(label="Generated Image"),
+    outputs=gr.Image(label="Generated Image"),
     title="Image Processing with Diffusion Pipeline",
     description="Upload an image and enter a prompt to generate a new image using the diffusion model."
 )