Create app.py

app.py

@@ -0,0 +1,47 @@
+import gradio as gr
+import requests
+from PIL import Image
+import os
+import torch
+from transformers import AutoImageProcessor, Swin2SRForImageSuperResolution
+
+processor = AutoImageProcessor.from_pretrained("caidas/swin2SR-classical-sr-x2-64")
+model = Swin2SRForImageSuperResolution.from_pretrained("caidas/swin2SR-classical-sr-x2-64")
+
+def enhance(image):
+    # prepare image for the model
+    inputs = processor(image, return_tensors="pt")
+
+    # forward pass
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    # postprocess
+    output = outputs.reconstruction.data.squeeze().float().cpu().clamp_(0, 1).numpy()
+    output = np.moveaxis(output, source=0, destination=-1)
+    output = (output * 255.0).round().astype(np.uint8)  # float32 to uint8
+    
+    return Image.fromarray(output)
+
+title = "Swin2SR demo for Image Super-Resolution 🚀🚀🔥"
+description = ''' 
+
+**This Demo expects low-quality and low-resolution JPEG compressed images, in the near future we will support any kind of input**
+
+**We are looking for collaborators! Collaborator를 찾고 있습니다!** 🇬🇧 🇪🇸 🇰🇷 🇫🇷 🇷🇴 🇩🇪 🇨🇳
+
+**Please check our github project: https://github.com/mv-lab/swin2sr or paper: https://arxiv.org/abs/2209.11345 feel free to contact us**
+
+**Demos also available at [google colab](https://colab.research.google.com/drive/1paPrt62ydwLv2U2eZqfcFsePI4X4WRR1?usp=sharing) and [Kaggle](https://www.kaggle.com/code/jesucristo/super-resolution-demo-swin2sr-official/)**
+</br>
+'''
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2209.11345' target='_blank'>Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration</a> | <a href='https://github.com/mv-lab/swin2sr' target='_blank'>Github Repo</a></p>"
+
+gr.Interface(
+    enhance, 
+    gr.inputs.Image(type="pil", label="Input").style(height=260),
+    gr.inputs.Image(type="pil", label="Ouput").style(height=240),
+    title=title,
+    description=description,
+    article=article,
+    ).launch(enable_queue=True)