Offered By: IBMSkillsNetwork
Build a Style Finder using Llama, Gen AI & Computer Vision
Use the Llama 3.2 90B Vision Instruct multimodal model to decode Taylor Swift's iconic style just in time for Black Friday! With free, state-of-the-art AI tools, you'll analyze Taylor’s outfits while finding real-time, budget-friendly alternatives using live searches. Perfect for Swifties, AI/ML enthusiasts, and data scientists, this project transforms your shopping experience, helping you re-create Taylor’s looks without breaking the bank. Completely free and completed in just 60 minutes, it’s the ultimate tool for mastering fashion analysis and scoring deals this Black Friday.
Continue readingGuided Project
Computer Vision
At a Glance
Use the Llama 3.2 90B Vision Instruct multimodal model to decode Taylor Swift's iconic style just in time for Black Friday! With free, state-of-the-art AI tools, you'll analyze Taylor’s outfits while finding real-time, budget-friendly alternatives using live searches. Perfect for Swifties, AI/ML enthusiasts, and data scientists, this project transforms your shopping experience, helping you re-create Taylor’s looks without breaking the bank. Completely free and completed in just 60 minutes, it’s the ultimate tool for mastering fashion analysis and scoring deals this Black Friday.
- Match the outfit to our curated data set of Taylor’s iconic looks.
- Provide detailed descriptions of the outfit and links to purchase the items.
- Search the internet for visually similar items if no exact match is found.
- Suggest budget-friendly alternatives, helping you look like Taylor without breaking the bank.
Source: DALL-E
What You’ll Achieve
- Gain hands-on experience with Retrieval-Augmented Generation (RAG) and learn how to enhance AI responses with external data sets.
- Master the basics of image-to-vector encoding and visual similarity matching.
- Explore how to integrate APIs like SerpAPI to enhance the functionality of AI-driven applications.
- Build a Swift Style Finder tool that combines multimodal AI, fashion analysis, and real-time search to deliver personalized and engaging results.
- Sharpen your skills in prompt engineering and application development for AI-powered fashion tools.
Who Should Complete This Project?
- Swifties who want to explore Taylor Swift’s iconic style and learn how AI can help recreate her looks with budget-friendly alternatives.
- AI and Machine Learning Enthusiasts looking to explore multimodal AI models and real-world applications of image analysis.
- Data Scientists interested in how AI can analyze and recreate celebrity styles while offering affordable alternatives.
- Students and Beginners in AI who want hands-on experience with large language models, RAG workflows, and prompt engineering.
- Developers and Professionals seeking a practical project to explore how APIs and AI can be combined to build interactive applications.
What You’ll Need
- Basic familiarity with Python programming and libraries like pandas and numpy.
- An understanding of general AI concepts such as vectors, image analysis, and API integration (beginners will also find guidance throughout the project).
- A free account with SerpAPI for querying Google searches (we’ll walk you through setting this up).
- A modern version of web browsers (e.g., Chrome, Firefox, Edge, Safari).
Estimated Effort
60 Minutes
Level
Intermediate
Skills You Will Learn
API, Artificial Intelligence, Computer Vision, Deep Learning, Generative AI, LLM
Language
English
Course Code
GPXX0QZ2EN