app.py

# Import necessary libraries
from PIL import Image
import numpy as np
import torch
from transformers import AutoImageProcessor, Swin2SRForImageSuperResolution
import gradio as gr
import spaces

# Function to resize image to max 2048x2048 while maintaining aspect ratio
def resize_image(image, max_size=2048):
    width, height = image.size
    if width > max_size or height > max_size:
        aspect_ratio = width / height
        if width > height:
            new_width = max_size
            new_height = int(new_width / aspect_ratio)
        else:
            new_height = max_size
            new_width = int(new_height * aspect_ratio)
        image = image.resize((new_width, new_height), Image.LANCZOS)
    return image

# Function to upscale an image using Swin2SR
def upscale_image(image, model, processor, device):
    # Convert the image to RGB format
    image = image.convert("RGB")
    # Process the image for the model
    inputs = processor(image, return_tensors="pt")
    # Move inputs to the same device as model
    inputs = {k: v.to(device) for k, v in inputs.items()}
    # Perform inference (upscale)
    with torch.no_grad():
        outputs = model(**inputs)
    # Move output back to CPU for further processing
    output = outputs.reconstruction.data.squeeze().cpu().float().clamp_(0, 1).numpy()
    output = np.moveaxis(output, source=0, destination=-1)
    output_image = (output * 255.0).round().astype(np.uint8)  # Convert from float32 to uint8
    # Remove 32 pixels from the bottom and right of the image
    output_image = output_image[:-32, :-32]
    return Image.fromarray(output_image)

@spaces.GPU
def main(image, model_choice, save_as_jpg=True):
    # Check if GPU is available and set the device accordingly
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    
    # Resize the input image
    image = resize_image(image)
    
    # Define model paths
    model_paths = {
        "Pixel Perfect": "caidas/swin2SR-classical-sr-x4-64",
        "PSNR Match (Recommended)": "caidas/swin2SR-realworld-sr-x4-64-bsrgan-psnr"
    }
    
    # Load the selected Swin2SR model and processor for 4x upscaling
    processor = AutoImageProcessor.from_pretrained(model_paths[model_choice])
    model = Swin2SRForImageSuperResolution.from_pretrained(model_paths[model_choice])
    # Move the model to the device (GPU or CPU)
    model.to(device)
    
    # Upscale the image
    upscaled_image = upscale_image(image, model, processor, device)
    
    if save_as_jpg:
        # Save the upscaled image as JPG with 98% compression
        upscaled_image.save("upscaled_image.jpg", quality=98)
        return "upscaled_image.jpg"
    else:
        # Save the upscaled image as PNG
        upscaled_image.save("upscaled_image.png")
        return "upscaled_image.png"

# Gradio interface
def gradio_interface(image, model_choice, save_as_jpg):
    return main(image, model_choice, save_as_jpg)

# Create a Gradio interface
interface = gr.Interface(
    fn=gradio_interface,
    inputs=[
        gr.Image(type="pil", label="Upload Image"),
        gr.Dropdown(
            choices=["PSNR Match (Recommended)", "Pixel Perfect"],
            label="Select Model",
            value="PSNR Match (Recommended)"
        ),
        gr.Checkbox(value=True, label="Save as JPEG"),
    ],
    outputs=gr.File(label="Download Upscaled Image"),
    title="Image Upscaler",
    description="Upload an image, select a model, upscale it, and download the new image. Images larger than 2048x2048 will be resized while maintaining aspect ratio.",
)

# Launch the interface
interface.launch()