from transformers import Blip2Processor, Blip2ForConditionalGeneration
import torch
from PIL import Image
import requests
import matplotlib.pyplot as plt
import numpy as np
from io import BytesIO
# Load BLIP-2 model
processor = Blip2Processor.from_pretrained("Salesforce/blip2-opt-2.7b")
model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-2.7b", torch_dtype=torch.float16)
if torch.cuda.is_available():
model = model.to("cuda")
# Function to download image from URL
def download_image(url):
response = requests.get(url, stream=True)
return Image.open(BytesIO(response.content)).convert('RGB')
# Function for image captioning
def generate_caption(image_path):
# Load image from path or URL
if isinstance(image_path, str):
if image_path.startswith((' '
image = download_image(image_path)
else:
image = Image.open(image_path).convert('RGB')
else:
image = image_path
inputs = processor(images=image, return_tensors="pt")
if torch.cuda.is_available():
inputs = {k: v.to("cuda") for k, v in inputs.items()}
generated_ids = model.generate(**inputs, max_new_tokens=50)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0].strip()
return generated_text
# Function for visual question answering
def visual_qa(image_path, question):
# Load image from path or URL
if isinstance(image_path, str):
if image_path.startswith((' '
image = download_image(image_path)
else:
image = Image.open(image_path).convert('RGB')
else:
image = image_path
# FIX: Properly format the question for the model
# BLIP-2 needs a specific prompt format for QA
prompt = f"Question: {question} Answer:"
inputs = processor(images=image, text=prompt, return_tensors="pt")
if torch.cuda.is_available():
inputs = {k: v.to("cuda") for k, v in inputs.items()}
generated_ids = model.generate(
**inputs,
max_new_tokens=30,
do_sample=False # Use greedy decoding for more precise answers
)
answer = processor.batch_decode(generated_ids, skip_special_tokens=True)[0].strip()
# Remove the prompt part from the answer
answer = answer.replace(prompt, "").strip()
return answer
# Function to visualize image with caption and QA
def visualize_product_analysis(image_path, questions=None):
# Load image
if isinstance(image_path, str):
if image_path.startswith((' '
image = download_image(image_path)
else:
image = Image.open(image_path).convert('RGB')
else:
image = image_path
# Generate caption
caption = generate_caption(image)
# Default questions if none provided
if questions is None:
questions = [
"What color is this product?",
"What material is this product made of?",
"What is the target demographic for this product?",
"What is a key feature of this product?"
]
# Get answers
answers = []
for question in questions:
answer = visual_qa(image, question)
answers.append((question, answer))
# Create visualization
plt.figure(figsize=(12, 10))
# Display image
plt.subplot(2, 1, 1)
plt.imshow(np.array(image))
plt.title("Product Image", fontsize=14)
plt.axis('off')
# Display caption and Q&A
plt.subplot(2, 1, 2)
plt.axis('off')
text_content = f"Generated Description: {caption}nn"
text_content += "Product Analysis:n"
for q, a in answers:
text_content += f"Q: {q}nA: {a}nn"
plt.text(0.01, 0.99, text_content, transform=plt.gca().transAxes,
fontsize=12, verticalalignment="top", wrap=True)
plt.tight_layout()
plt.show()
return caption, answers
# Business application: Automated product listing
def create_product_listing(image_path):
# Load image
if isinstance(image_path, str):
if image_path.startswith((' '
image = download_image(image_path)
else:
image = Image.open(image_path).convert('RGB')
else:
image = image_path
# Get basic caption
caption = generate_caption(image)
# Extract product attributes with more specific prompting
color = visual_qa(image, "What colors are visible in this product?")
material = visual_qa(image, "What material does this product appear to be made of?")
use_case = visual_qa(image, "What would be the main use case for this product?")
unique_features = visual_qa(image, "What are any unique or notable features of this product?")
# Create structured listing
listing = {
"title": caption,
"attributes": {
"color": color,
"material": material,
"primary_use": use_case,
"unique_features": unique_features
}
}
# Visualize the listing
plt.figure(figsize=(14, 10))
# Display image
plt.subplot(1, 2, 1)
plt.imshow(np.array(image))
plt.title("Product Image", fontsize=14)
plt.axis('off')
# Display listing details
plt.subplot(1, 2, 2)
plt.axis('off')
listing_text = f"PRODUCT LISTINGnn"
listing_text += f"Title: {listing['title']}nn"
listing_text += "Product Attributes:n"
for attr, value in listing['attributes'].items():
listing_text += f"{attr.replace('_', ' ').title()}: {value}n"
plt.text(0.01, 0.99, listing_text, transform=plt.gca().transAxes,
fontsize=12, verticalalignment="top")
plt.tight_layout()
plt.show()
return listing
# Function for marketing content analysis
def analyze_marketing_content(image_path):
# Load image
if isinstance(image_path, str):
if image_path.startswith((' '
image = download_image(image_path)
else:
image = Image.open(image_path).convert('RGB')
else:
image = image_path
# Marketing-specific questions
marketing_questions = [
"What emotions does this image evoke?",
"What brand values are communicated in this image?",
"What target audience would this image appeal to?",
"What call to action would pair well with this image?",
"What marketing channel would this image be most effective on?"
]
# Get answers
marketing_insights = {}
for question in marketing_questions:
answer = visual_qa(image, question)
key = question.split("?")[0].strip().lower().replace(" ", "_")
marketing_insights[key] = answer
# Visualize the analysis
plt.figure(figsize=(14, 10))
# Display image
plt.subplot(1, 2, 1)
plt.imshow(np.array(image))
plt.title("Marketing Visual", fontsize=14)
plt.axis('off')
# Display marketing insights
plt.subplot(1, 2, 2)
plt.axis('off')
insights_text = "MARKETING CONTENT ANALYSISnn"
for question, key in zip(marketing_questions, marketing_insights.keys()):
insights_text += f"{question}n{marketing_insights[key]}nn"
plt.text(0.01, 0.99, insights_text, transform=plt.gca().transAxes,
fontsize=12, verticalalignment="top")
plt.tight_layout()
plt.show()
return marketing_insights
# Function for social media understanding
def analyze_social_media_content(image_path):
# Load image
if isinstance(image_path, str):
if image_path.startswith((' '
image = download_image(image_path)
else:
image = Image.open(image_path).convert('RGB')
else:
image = image_path
# Generate caption
caption = generate_caption(image)
# Social media specific analysis
engagement_potential = visual_qa(image, "How likely is this image to engage viewers on social media?")
suggested_hashtags = visual_qa(image, "What hashtags would be appropriate for this image on social media?")
platform_fit = visual_qa(image, "Which social media platform would this image perform best on?")
content_type = visual_qa(image, "What type of social media post would this image be suitable for?")
# Create analysis dict
social_analysis = {
"caption": caption,
"engagement_potential": engagement_potential,
"suggested_hashtags": suggested_hashtags,
"platform_fit": platform_fit,
"content_type": content_type
}
# Visualize the analysis
plt.figure(figsize=(14, 10))
# Display image
plt.subplot(1, 2, 1)
plt.imshow(np.array(image))
plt.title("Social Media Content", fontsize=14)
plt.axis('off')
# Display social media insights
plt.subplot(1, 2, 2)
plt.axis('off')
insights_text = "SOCIAL MEDIA CONTENT ANALYSISnn"
insights_text += f"Caption: {social_analysis['caption']}nn"
insights_text += f"Engagement Potential: {social_analysis['engagement_potential']}nn"
insights_text += f"Suggested Hashtags: {social_analysis['suggested_hashtags']}nn"
insights_text += f"Best Platform: {social_analysis['platform_fit']}nn"
insights_text += f"Content Type: {social_analysis['content_type']}n"
plt.text(0.01, 0.99, insights_text, transform=plt.gca().transAxes,
fontsize=12, verticalalignment="top")
plt.tight_layout()
plt.show()
return social_analysis
# Example usage
if __name__ == "__main__":
# Example: E-commerce product analysis
product_url = "
print("1. Basic Product Analysis")
caption, qa_results = visualize_product_analysis(product_url)
print("n2. Creating Automated Product Listing")
product_listing = create_product_listing(product_url)
print("n3. Marketing Content Analysis")
marketing_url = "
marketing_insights = analyze_marketing_content(marketing_url)
print("n4. Social Media Content Analysis")
social_url = "
social_analysis = analyze_social_media_content(social_url)
