Update app.py

app.py

@@ -1,7 +1,11 @@
 import gradio as gr
+from transformers import pipeline
 from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel 
 from PIL import Image
 
+# Load text generation model
+text_generation_model = pipeline(task="text-generation")
+
 # Load image captioning model
 encoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
 decoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
@@ -11,6 +15,8 @@ feature_extractor = ViTFeatureExtractor.from_pretrained(encoder_checkpoint)
 tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint)
 model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint)
 
+
+
 def generate_story(image, genre, style):
     try:
         # Preprocess the image
@@ -32,16 +38,18 @@ def generate_story(image, genre, style):
         return f"An error occurred during inference: {str(e)}"
 
 
+
 # Gradio interface
 input_image = gr.Image(label="Select Image",type="pil")
 input_genre = gr.Dropdown(["Hindi", "Spanish", "Portuguese", "French", "German", "Italian", "Russian", "Japanese"], label="Input Genre")
 input_style = gr.Dropdown(["Hindi", "Spanish", "Portuguese", "French", "German", "Italian", "Russian", "Japanese"], label="Input Style")
 output_text = gr.Textbox(label="Generated Story",lines=8)
 
+
 gr.Interface(
     fn=generate_story,
     inputs=[input_image, input_genre, input_style],
     outputs=output_text,
     title="Image to Story Generator",
-    description="Generate a story from an image taking genre and style as input."
-).launch()
+    description="Generate a story from an image taking genre and style as input.",
+).launch()