ai_image_captioning_system.py

# -*- coding: utf-8 -*-
"""AI_IMAGE_CAPTIONING_SYSTEM

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/17dn1kTTvteSAZiPRPgyLACsRLmWg5JXU
"""

!pip install torch torchvision transformers pillow

import torch
from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image

# Load BLIP model
device = "cuda" if torch.cuda.is_available() else "cpu"
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to(device)

def generate_caption(image_path):
    image = Image.open(image_path).convert("RGB")
    inputs = processor(images=image, return_tensors="pt").to(device)

    with torch.no_grad():
        output = model.generate(**inputs, max_length=30)

    caption = processor.tokenizer.decode(output[0], skip_special_tokens=True)
    return caption

from transformers import pipeline

# Load a simple text-generation model
caption_generator = pipeline("text-generation", model="gpt2", device=0 if torch.cuda.is_available() else -1)

def generate_caption(prompt):
    result = caption_generator(prompt, max_length=30, num_return_sequences=1)
    return result[0]['generated_text']

image_path = "/content/download.jpg"  # Replace with your actual image path
caption = generate_caption(image_path)
print("Generated Caption:", caption)