from transformers import pipeline

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
pipe = pipeline(task="image-to-image", model="caidas/swin2SR-lightweight-x2-64", device=device)

from PIL import Image
import requests

url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/cat.jpg"
image = Image.open(requests.get(url, stream=True).raw)

print(image.size)

upscaled = pipe(image)
print(upscaled.size)

from transformers import Swin2SRForImageSuperResolution, Swin2SRImageProcessor 

model = Swin2SRForImageSuperResolution.from_pretrained("caidas/swin2SR-lightweight-x2-64").to(device)
processor = Swin2SRImageProcessor("caidas/swin2SR-lightweight-x2-64")

pixel_values = processor(image, return_tensors="pt").pixel_values
print(pixel_values.shape)

pixel_values = pixel_values.to(device)

import torch

with torch.no_grad():
  outputs = model(pixel_values)

(loss=None, reconstruction=tensor([[[[0.8270, 0.8269, 0.8275,  ..., 0.7463, 0.7446, 0.7453],
          [0.8287, 0.8278, 0.8283,  ..., 0.7451, 0.7448, 0.7457],
          [0.8280, 0.8273, 0.8269,  ..., 0.7447, 0.7446, 0.7452],
          ...,
          [0.5923, 0.5933, 0.5924,  ..., 0.0697, 0.0695, 0.0706],
          [0.5926, 0.5932, 0.5926,  ..., 0.0673, 0.0687, 0.0705],
          [0.5927, 0.5914, 0.5922,  ..., 0.0664, 0.0694, 0.0718]]]],
       device='cuda:0'), hidden_states=None, attentions=None)

outputs.reconstruction.data.shape
# torch.Size([1, 3, 880, 1072])


import numpy as np

# squeeze, take to CPU and clip the values
output = outputs.reconstruction.data.squeeze().cpu().clamp_(0, 1).numpy()
# rearrange the axes
output = np.moveaxis(output, source=0, destination=-1)
# bring values back to pixel values range
output = (output * 255.0).round().astype(np.uint8)
Image.fromarray(output)