import gradio as gr from transformers import CLIPProcessor, CLIPModel from PIL import Image import torch # Load a pre-trained CLIP model and processor from Hugging Face model_name = "openai/clip-vit-base-patch32" model = CLIPModel.from_pretrained(model_name) processor = CLIPProcessor.from_pretrained(model_name) # Define possible personas mapped to interests (added 15 more personas) predefined_personas = { "Fashion": { "Age": "18-30 years", "Gender": "Likely Female", "Interests": ["Fashion", "Trendy Clothing", "Social Media"], "Income Level": "Medium", "Psychographics": ["Fashion-conscious", "Socially active", "Trend-seeker"], "Behavioral Traits": ["Follows fashion influencers", "Buys seasonal items", "Active on Instagram"] }, "Technology": { "Age": "20-40 years", "Gender": "Likely Male", "Interests": ["Technology", "Gadgets", "Software"], "Income Level": "High", "Psychographics": ["Tech-savvy", "Innovative", "Early adopter"], "Behavioral Traits": ["Follows tech blogs", "Interested in product launches", "Buys online frequently"] }, "Sports": { "Age": "15-40 years", "Gender": "Likely Male", "Interests": ["Sports", "Fitness", "Outdoor Activities"], "Income Level": "Medium", "Psychographics": ["Active lifestyle", "Health-conscious", "Competitive"], "Behavioral Traits": ["Watches sports events", "Goes to the gym", "Buys athletic gear"] }, "Travel": { "Age": "25-45 years", "Gender": "Likely Female or Male", "Interests": ["Travel", "Adventure", "Culture"], "Income Level": "Medium to High", "Psychographics": ["Experience-seeker", "Open-minded", "Curious"], "Behavioral Traits": ["Follows travel blogs", "Likes outdoor activities", "Prefers unique experiences"] }, "Luxury": { "Age": "30-50 years", "Gender": "Likely Female or Male", "Interests": ["Luxury Goods", "High-end Fashion", "Fine Dining"], "Income Level": "High", "Psychographics": ["Status-conscious", "Exclusive-taste", "Prestige-oriented"], "Behavioral Traits": ["Buys luxury brands", "Frequent traveler", "Invests in high-end products"] }, "Fitness": { "Age": "20-40 years", "Gender": "Likely Female or Male", "Interests": ["Fitness", "Healthy Living", "Nutrition"], "Income Level": "Medium", "Psychographics": ["Health-conscious", "Goal-oriented", "Disciplined"], "Behavioral Traits": ["Goes to the gym regularly", "Buys fitness equipment", "Follows nutrition plans"] }, "Education": { "Age": "18-35 years", "Gender": "Likely Female or Male", "Interests": ["Education", "Learning", "Career Development"], "Income Level": "Medium", "Psychographics": ["Growth-oriented", "Knowledge-seeker", "Curious"], "Behavioral Traits": ["Follows online courses", "Interested in higher education", "Learns new skills"] }, "Entertainment": { "Age": "15-35 years", "Gender": "Likely Female or Male", "Interests": ["Movies", "Music", "Video Games"], "Income Level": "Medium", "Psychographics": ["Fun-seeking", "Relaxed", "Entertainment-driven"], "Behavioral Traits": ["Watches Netflix", "Plays video games", "Follows pop culture trends"] }, # Added 15 more personas below "Finance": { "Age": "25-50 years", "Gender": "Likely Male", "Interests": ["Investing", "Banking", "Stock Market"], "Income Level": "High", "Psychographics": ["Money-driven", "Risk-taker", "Analytical"], "Behavioral Traits": ["Reads financial news", "Invests in stocks", "Follows market trends"] }, "Health & Wellness": { "Age": "30-60 years", "Gender": "Likely Female or Male", "Interests": ["Wellness", "Meditation", "Mental Health"], "Income Level": "Medium", "Psychographics": ["Health-conscious", "Balanced", "Holistic"], "Behavioral Traits": ["Practices yoga", "Follows wellness blogs", "Interested in mental well-being"] }, "Automobiles": { "Age": "18-50 years", "Gender": "Likely Male", "Interests": ["Cars", "Motorcycles", "Electric Vehicles"], "Income Level": "Medium to High", "Psychographics": ["Thrill-seeker", "Tech-lover", "Adventure-prone"], "Behavioral Traits": ["Watches car reviews", "Attends auto expos", "Purchases EVs and accessories"] }, "Real Estate": { "Age": "30-60 years", "Gender": "Likely Male", "Interests": ["Real Estate", "Property Investment", "Architecture"], "Income Level": "High", "Psychographics": ["Status-conscious", "Wealth-oriented", "Investor"], "Behavioral Traits": ["Buys luxury properties", "Follows real estate market trends", "Invests in property"] }, "Gaming": { "Age": "15-35 years", "Gender": "Likely Male or Female", "Interests": ["Video Games", "Esports", "Streaming"], "Income Level": "Medium", "Psychographics": ["Competitive", "Fun-seeking", "Entertainment-driven"], "Behavioral Traits": ["Plays online games", "Watches gaming streams", "Active in gaming communities"] }, "Sustainability": { "Age": "20-50 years", "Gender": "Likely Female or Male", "Interests": ["Environment", "Eco-friendly Living", "Sustainability"], "Income Level": "Medium", "Psychographics": ["Eco-conscious", "Change-seeker", "Green living"], "Behavioral Traits": ["Follows sustainability blogs", "Supports eco-friendly brands", "Uses renewable products"] }, "Music": { "Age": "15-40 years", "Gender": "Likely Female or Male", "Interests": ["Music", "Concerts", "Instruments"], "Income Level": "Medium", "Psychographics": ["Creative", "Artistic", "Fun-loving"], "Behavioral Traits": ["Listens to new albums", "Attends live concerts", "Plays musical instruments"] }, "Parenting": { "Age": "25-45 years", "Gender": "Likely Female or Male", "Interests": ["Parenting", "Child Development", "Education"], "Income Level": "Medium", "Psychographics": ["Nurturing", "Family-oriented", "Protective"], "Behavioral Traits": ["Follows parenting blogs", "Buys children's educational products", "Active in parent groups"] }, "Food & Drink": { "Age": "18-50 years", "Gender": "Likely Female or Male", "Interests": ["Cooking", "Gourmet Food", "Restaurants"], "Income Level": "Medium", "Psychographics": ["Food-lover", "Adventurous", "Experience-seeker"], "Behavioral Traits": ["Follows food blogs", "Tries new recipes", "Dines at top-rated restaurants"] }, "Adventure": { "Age": "20-45 years", "Gender": "Likely Male or Female", "Interests": ["Adventure Sports", "Hiking", "Extreme Sports"], "Income Level": "Medium", "Psychographics": ["Thrill-seeker", "Adventurous", "Risk-taker"], "Behavioral Traits": ["Goes on outdoor adventures", "Follows extreme sports", "Buys adventure gear"] }, "Art & Design": { "Age": "20-45 years", "Gender": "Likely Female or Male", "Interests": ["Art", "Graphic Design", "Photography"], "Income Level": "Medium", "Psychographics": ["Creative", "Detail-oriented", "Artistic"], "Behavioral Traits": ["Visits art galleries", "Follows design trends", "Works with photography equipment"] }, "Pets": { "Age": "18-50 years", "Gender": "Likely Female or Male", "Interests": ["Pets", "Animal Care", "Pet Products"], "Income Level": "Medium", "Psychographics": ["Animal lover", "Caring", "Responsible"], "Behavioral Traits": ["Follows pet care blogs", "Buys pet supplies", "Takes pets to veterinary services"] }, "Home Improvement": { "Age": "25-55 years", "Gender": "Likely Female or Male", "Interests": ["DIY", "Interior Design", "Home Renovation"], "Income Level": "Medium to High", "Psychographics": ["Handy", "Creative", "Home-proud"], "Behavioral Traits": ["Follows DIY tutorials", "Buys home improvement tools", "Interested in interior design"] } } # List of interest categories to compare against interest_categories = list(predefined_personas.keys()) # Function to calculate similarity between the image and each interest category def get_most_similar_persona(image): """Infers the most similar predefined persona for the given image.""" inputs = processor(images=image, return_tensors="pt") with torch.no_grad(): image_features = model.get_image_features(**inputs) # Define descriptions of interest categories (texts) category_descriptions = [ f"A photo that represents {category.lower()}." for category in interest_categories ] # Tokenize the category descriptions and get text features text_inputs = processor(text=category_descriptions, return_tensors="pt", padding=True) text_features = model.get_text_features(**text_inputs) # Calculate similarity between image and text features image_features /= image_features.norm(dim=-1, keepdim=True) text_features /= text_features.norm(dim=-1, keepdim=True) similarities = torch.matmul(image_features, text_features.T) # Find the most similar category most_similar_idx = similarities.argmax().item() most_similar_category = interest_categories[most_similar_idx] return predefined_personas[most_similar_category] # Gradio interface function def persona_analysis(image): """Generates a marketing persona based on the image.""" persona = get_most_similar_persona(image) return "\n".join([f"{key}: {value}" for key, value in persona.items()]) # Build the Gradio interface iface = gr.Interface( fn=persona_analysis, inputs=gr.Image(type="pil"), # Accept image input in PIL format outputs=gr.Textbox(), #Display persona as text output title="Strata7 Persona Vista", description="Upload an image to generate a marketing persona based on the ad subject." ) # Launch the Gradio interface iface.launch()