Update app.py

app.py

@@ -1,8 +1,6 @@
 # -*- coding: utf-8 -*-
 """gen ai project f.ipynb
-
 Automatically generated by Colab.
-
 Original file is located at
     https://colab.research.google.com/drive/1iF7hdOjWNeFUtGvUYdaFsBErJGnY1h5J
 """
@@ -20,9 +18,13 @@ if hf_token:
 else:
     raise ValueError("Hugging Face token not found in environment variables.")
 
-
 # Import necessary libraries
 from transformers import MarianMTModel, MarianTokenizer, pipeline
+import requests
+import io
+from PIL import Image
+import matplotlib.pyplot as plt
+import gradio as gr
 
 # Load the translation model and tokenizer
 model_name = "Helsinki-NLP/opus-mt-mul-en"
@@ -35,31 +37,19 @@ translator = pipeline("translation", model=model, tokenizer=tokenizer)
 # Function for translation
 def translate_text(tamil_text):
     try:
-        # Perform translation
         translation = translator(tamil_text, max_length=40)
         translated_text = translation[0]['translation_text']
         return translated_text
     except Exception as e:
         return f"An error occurred: {str(e)}"
 
-# Test translation with example Tamil text
-tamil_text = "மழையுடன் ஒரு பூ"  # "A flower with rain"
-translated_text = translate_text(tamil_text)
-print(f"Translated Text: {translated_text}")
-
-import requests
-import io
-from PIL import Image
-import matplotlib.pyplot as plt
-
 # API credentials and endpoint
 API_URL = "https://api-inference.huggingface.co/models/black-forest-labs/FLUX.1-dev"
-headers = {"Authorization": "Bearer HF_TOKEN"}
+headers = {"Authorization": f"Bearer {hf_token}"}
 
 # Function to send payload and generate image
 def generate_image(prompt):
     try:
-        # Send request to API
         response = requests.post(API_URL, headers=headers, json={"inputs": prompt})
 
         # Check if the response is successful
@@ -73,13 +63,15 @@ def generate_image(prompt):
                 return image
             except Exception as e:
                 print(f"Error opening image: {e}")
+                return None
         else:
-            # Handle non-200 responses
             print(f"Failed to get image: Status code {response.status_code}")
             print("Response content:", response.text)  # Print response for debugging
+            return None
 
     except Exception as e:
         print(f"An error occurred: {e}")
+        return None
 
 # Display image
 def show_image(image):
@@ -90,16 +82,8 @@ def show_image(image):
     else:
         print("No image to display")
 
-# Test the function with a prompt
-prompt = "A flower with rain"
-image = generate_image(prompt)
-
-# Display the generated image
-show_image(image)
-
-from transformers import AutoTokenizer, AutoModelForCausalLM
-
 # Load GPT-Neo model for creative text generation
+from transformers import AutoTokenizer, AutoModelForCausalLM
 gpt_neo_tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-125M")
 gpt_neo_model = AutoModelForCausalLM.from_pretrained("EleutherAI/gpt-neo-125M")
 
@@ -110,8 +94,6 @@ def generate_creative_text(translated_text):
     creative_text = gpt_neo_tokenizer.decode(generated_text_ids[0], skip_special_tokens=True)
     return creative_text
 
-import gradio as gr
-
 # Function to handle the full workflow
 def translate_generate_image_and_text(tamil_text):
     # Step 1: Translate Tamil text to English
@@ -135,4 +117,4 @@ interface = gr.Interface(
 )
 
 # Launch Gradio app
-interface.launch()
+interface.launch()