Update app.py

things were done

app.py

@@ -14,14 +14,17 @@ tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint)
 model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)
 
 
-def predict(image, max_length=64, num_beams=4):
+def predict(image):
+    """Predict the generic image caption from the image """
     image = image.convert('RGB')
     image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
     clean_text = lambda x: x.replace('<|endoftext|>', '').split('\n')[0]
-    caption_ids = model.generate(image, max_length=max_length)[0]
+    caption_ids = model.generate(image, max_length=125)[0]
     img_caption_text = clean_text(tokenizer.decode(caption_ids))
+    
     caption_text = creative_caption(img_caption_text)
     hashtags = caption_hashtags(img_caption_text)
+    
     return caption_text, hashtags
 
 
@@ -33,13 +36,13 @@ def caption_hashtags(text):
     return co_client.generate(prompt=f"Write some trendy instagram hashtags for the following prompt - {text}")
 
 
-input_upload = gr.inputs.Image(label="Upload any Image", type='pil', optional=True)
+input_upload = gr.Image(label="Upload any Image", type='pil', optional=True)
 output = [
-    gr.outputs.Textbox(type="auto", label="Captions"),
-    gr.outputs.Textbox(type="auto", label="Hashtags"),
+    gr.Textbox(type="auto", label="Captions"),
+    gr.Textbox(type="auto", label="Hashtags"),
 ]
 
-title = "Image Captioning "
+title = "Instagram Image Captioning"
 description = "Made for Linesh"
 interface = gr.Interface(