Update app.py

app.py

@@ -44,7 +44,7 @@ os.makedirs('result')
 
 ## resize if necessary (not used)
 def resize(img):
-    max_side = 512
+    max_side = 430
     w = img.size[0]
     h = img.size[1]
     if max(h, w) > max_side:
@@ -57,9 +57,9 @@ def resize(img):
 #################### low res ##################
 ## inference  
 def inference(LR, Ref):
-    ## resize for user selected input (not used)
-    #LR = resize(LR)
-    #Ref = resize(Ref)
+    ## resize for user selected input
+    LR = resize(LR)
+    Ref = resize(Ref)
     
     ## Input setup (creates folders and places inputs corresponding to the original RefVSR code)
     LR.save(os.path.join(LR_path, '0000.png'))
@@ -82,14 +82,14 @@ def inference(LR, Ref):
                 --is_gradio")             
     return "result/0000.png"
 
-title="RefVSR"
+title="RefVSR | 4xSR on a single low-resolution frame (480x270)"
 description="Demo application for Reference-based Video Super-Resolution (RefVSR). Upload a low-resolution frame and a reference frame to 'LR' and 'Ref' input windows, respectively. The demo runs on CPUs and takes about 150s."
 
-article = "<p style='text-align: center'><b>To check the full capability of the module, we recommend to clone Github repository and run RefVSR models on videos using GPUs.</b></p><p style='text-align: center'>This demo runs on CPUs and only supports RefVSR for a single LR and Ref frame due to computational complexity. Hence, the model will not take advantage of temporal LR and Ref frames.</p><p style='text-align: center'>The model is trained by the proposed pre-training strategy only. The sample frames are in 430x270 resolution and saved in the PNG format. </p><p style='text-align: center'><a href='https://junyonglee.me/projects/RefVSR' target='_blank'>Project</a> | <a href='https://arxiv.org/abs/2203.14537' target='_blank'>arXiv</a> | <a href='https://github.com/codeslake/RefVSR' target='_blank'>Github</a></p>"
+article = "<p style='text-align: center'><b>To check the full capability of the module, we recommend to clone Github repository and run RefVSR models on videos using GPUs.</b></p><p style='text-align: center'>This demo runs on CPUs and only supports RefVSR for a single LR and Ref frame due to computational complexity. Hence, the model will not take advantage of temporal LR and Ref frames.</p><p style='text-align: center'>The model is trained by the proposed pre-training strategy only. The sample frames are in 480x270 resolution and saved in the PNG format</p><p style='text-align: center'>For user given frames, the size will be adjusted for the longer side to have 480 pixels.</p><p style='text-align: center'><a href='https://junyonglee.me/projects/RefVSR' target='_blank'>Project</a> | <a href='https://arxiv.org/abs/2203.14537' target='_blank'>arXiv</a> | <a href='https://github.com/codeslake/RefVSR' target='_blank'>Github</a></p>"
 
-## resize for sample (not used)
-#LR = resize(Image.open('LR.png')).save('LR.png')
-#Ref = resize(Image.open('Ref.png')).save('Ref.png')
+## resize for sample
+LR = resize(Image.open('LR.png')).save('LR.png')
+Ref = resize(Image.open('Ref.png')).save('Ref.png')
 
 ## input
 examples=[['LR.png', 'Ref.png']]