Update app.py

app.py

@@ -12,73 +12,68 @@ if not hf_api_key:
     raise ValueError("Hugging Face API key not found! Please set the 'HF_API_KEY' environment variable.")
 headers = {"Authorization": f"Bearer {hf_api_key}"}
 
-# Define the text-to-image model URL
-API_URL = "https://api-inference.huggingface.co/models/CompVis/stable-diffusion-v1-4"
+# Define the text-to-image model URLs
+model_urls = {
+    "stable_diffusion_v1_4": "https://api-inference.huggingface.co/models/CompVis/stable-diffusion-v1-4",
+    "stable_diffusion_v1_5": "https://api-inference.huggingface.co/models/runwayml/stable-diffusion-v1-5",
+}
+API_URL = model_urls["stable_diffusion_v1_4"]
 
-# Use AutoTokenizer to avoid tokenizer mismatch warnings
+# Define the translation model for multilingual text inputs
 translation_model_name = "facebook/mbart-large-50-many-to-one-mmt"
-tokenizer = AutoTokenizer.from_pretrained(translation_model_name)  # Use AutoTokenizer to avoid warnings
+tokenizer = AutoTokenizer.from_pretrained(translation_model_name)
 translation_model = MBartForConditionalGeneration.from_pretrained(translation_model_name)
 
-# Load a text generation model from Hugging Face using accelerate for memory optimization
+# Load a text generation model from Hugging Face
 text_generation_model_name = "EleutherAI/gpt-neo-2.7B"
 text_tokenizer = AutoTokenizer.from_pretrained(text_generation_model_name)
-text_model = AutoModelForCausalLM.from_pretrained(
-    text_generation_model_name, 
-    device_map="auto", 
-    torch_dtype=torch.float32
-)
+text_model = AutoModelForCausalLM.from_pretrained(text_generation_model_name, device_map="auto", torch_dtype=torch.float32)
 
 # Create a pipeline for text generation
 text_generator = pipeline("text-generation", model=text_model, tokenizer=text_tokenizer)
 
 # Function to generate an image using Hugging Face's text-to-image model
 def generate_image_from_text(translated_text):
-    try:
-        response = requests.post(API_URL, headers=headers, json={"inputs": translated_text})
-        if response.status_code != 200:
-            return None, f"Error generating image: {response.text}"
-        
-        image_bytes = response.content
-        image = Image.open(io.BytesIO(image_bytes))
-        return image, None
-    except Exception as e:
-        return None, f"Error during image generation: {e}"
+    payload = {"inputs": translated_text, "options": {"wait_for_model": True}}
+    response = requests.post(API_URL, headers=headers, json=payload)
+    if response.status_code == 200:
+        image_data = response.content
+        image = Image.open(io.BytesIO(image_data))
+        return image
+    else:
+        # If the model is loading, check the estimated wait time
+        if response.status_code == 503:
+            error_message = response.json()
+            estimated_time = error_message.get("estimated_time", "Unknown")
+            return f"Model is currently loading. Estimated wait time: {estimated_time} seconds. Try again later."
+        else:
+            return f"Failed to generate image. Error: {response.status_code}, Message: {response.text}"
 
-# Define the function to translate Tamil text, generate an image, and create a descriptive text
-def translate_generate_image_and_text(tamil_text):
-    try:
-        tokenizer.src_lang = "ta_IN"
-        inputs = tokenizer(tamil_text, return_tensors="pt")
-        translated_tokens = translation_model.generate(**inputs, forced_bos_token_id=tokenizer.lang_code_to_id["en_XX"])
-        translated_text = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]
-    except Exception as e:
-        return f"Error during translation: {e}", None, None
+# Function to translate text using the MBart model
+def translate_text(input_text, src_lang="en"):
+    # Tokenize and translate
+    tokenizer.src_lang = src_lang
+    encoded_input = tokenizer(input_text, return_tensors="pt")
+    translated_tokens = translation_model.generate(**encoded_input)
+    translated_text = tokenizer.decode(translated_tokens[0], skip_special_tokens=True)
+    return translated_text
 
-    try:
-        image, error_message = generate_image_from_text(translated_text)
-        if error_message:
-            return translated_text, None, error_message
-    except Exception as e:
-        return translated_text, None, f"Error during image generation: {e}"
+# Function to generate text using the GPT-Neo model
+def generate_text(prompt, max_length=150):
+    generated_texts = text_generator(prompt, max_length=max_length, num_return_sequences=1)
+    return generated_texts[0]["generated_text"]
 
-    try:
-        descriptive_text = text_generator(translated_text, max_length=100, num_return_sequences=1, temperature=0.7, top_p=0.9)[0]['generated_text']
-    except Exception as e:
-        return translated_text, image, f"Error during text generation: {e}"
+# Define the Gradio Interface
+def app_interface(input_text, src_language="en"):
+    translated_text = translate_text(input_text, src_lang=src_language)
+    generated_image = generate_image_from_text(translated_text)
+    generated_text = generate_text(translated_text)
+    return generated_text, generated_image
 
-    return translated_text, image, descriptive_text
-
-# Gradio interface setup
-iface = gr.Interface(
-    fn=translate_generate_image_and_text,
-    inputs=gr.Textbox(lines=2, placeholder="Enter Tamil text here..."),
-    outputs=[gr.Textbox(label="Translated English Text"), 
-             gr.Image(label="Generated Image"),
-             gr.Textbox(label="Generated Descriptive Text")],
-    title="Tamil to English Translation, Image Creation, and Descriptive Text Generation",
-    description="Translate Tamil text to English using Facebook's mbart-large-50 model, create an image using the translated text, and generate a descriptive text based on the translated content.",
-)
-
-# Launch the Gradio app
-iface.launch()
+# Launch the Gradio App
+gr.Interface(
+    fn=app_interface,
+    inputs=[gr.inputs.Textbox(lines=2, placeholder="Enter text here..."), gr.inputs.Dropdown(["en", "fr", "de", "es"], default="en", label="Source Language")],
+    outputs=[gr.outputs.Textbox(label="Generated Text"), gr.outputs.Image(label="Generated Image")],
+    title="Multilingual Text-to-Image & Text Generation"
+).launch()