app.py

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('cuda')

def resize_with_padding(img, expected_size):
    img.thumbnail((expected_size[0], expected_size[1]))
    delta_width = expected_size[0] - img.size[0]
    delta_height = expected_size[1] - img.size[1]
    pad_width = delta_width // 2
    pad_height = delta_height // 2
    padding = (pad_width, pad_height, delta_width - pad_width, delta_height - pad_height)
    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
    remover = Remover(mode='base')

    # Get foreground mask
    fg_mask = remover.process(img, type='map')

    seed = 13
    mask = ImageOps.invert(fg_mask)
    img = resize_with_padding(img, (512, 512))
    generator = torch.Generator(device='cuda').manual_seed(seed)
    cond_scale = 1.0

    with torch.autocast("cuda"):
        controlnet_image = pipeline(
            prompt=prompt, 
            image=img, 
            mask_image=mask, 
            control_image=mask, 
            num_images_per_prompt=1, 
            generator=generator, 
            num_inference_steps=20, 
            guess_mode=False, 
            controlnet_conditioning_scale=cond_scale
        ).images[0]

    return controlnet_image

# Create Gradio interface
iface = gr.Interface(
    fn=process_image, 
    inputs=[
        gr.inputs.Image(type="pil", label="Upload Image"), 
        gr.inputs.Textbox(label="Enter Prompt")
    ],
    outputs=gr.outputs.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."
)

# Launch the interface
iface.launch()