app.py

# Install necessary libraries if not already installed
# !pip install transformers diffusers torch torchvision accelerate huggingface_hub matplotlib Pillow

from huggingface_hub import login
from transformers import MarianTokenizer, MarianMTModel
from PIL import Image
import torch
from torchvision import transforms
from transformers import BlipProcessor, BlipForConditionalGeneration
import matplotlib.pyplot as plt

# Step 1: Login to Hugging Face
login("your_huggingface_token_here")  # 🔐 Replace this with your actual token

# Step 2: Tamil to English Translation
def translate_tamil_to_english(text):
    model_name = "Helsinki-NLP/opus-mt-ta-en"
    tokenizer = MarianTokenizer.from_pretrained(model_name)
    model = MarianMTModel.from_pretrained(model_name)

    inputs = tokenizer(text, return_tensors="pt", padding=True)
    translated = model.generate(**inputs)
    english_text = tokenizer.decode(translated[0], skip_special_tokens=True)
    return english_text

# Step 3: Generate Image (using any placeholder image here since BLIP is captioning-only)
# You can download a sample image or use a real generation model like Stable Diffusion
def get_sample_image():
    img_url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/coco_sample.png"
    img = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
    return img

# Step 4: Describe the Image
def describe_image(image):
    processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
    model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")

    inputs = processor(images=image, return_tensors="pt")
    out = model.generate(**inputs)
    caption = processor.decode(out[0], skip_special_tokens=True)
    return caption

# === MAIN ===
if __name__ == "__main__":
    import requests

    # Step A: Input Tamil text
    tamil_text = "ஒரு சிறிய வீடு கடற்கரைக்கு அருகிலுள்ளது"
    print("Tamil Input:", tamil_text)

    # Step B: Translate to English
    english_translation = translate_tamil_to_english(tamil_text)
    print("Translated English:", english_translation)

    # Step C: Get sample image (placeholder for now, since we aren't using text-to-image yet)
    image = get_sample_image()

    # Step D: Describe the image
    caption = describe_image(image)
    print("Image Caption:", caption)

    # Optional: Display the image
    plt.imshow(image)
    plt.title(caption)
    plt.axis("off")
    plt.show()