Back to Catalog

AutoGen Wardrobe Wizard: A MultiAgent Fashion System

IntermediateGuided Project

Learn how to combine Meta's Llama vision model, OpenAI’s DALL·E, and Microsoft’s AutoGen, a framework for orchestrating collaborative AI agents, to build an AI-powered virtual fashion stylist. This project uses modular agents such as a Color Analyst, Style Planner, Silhouette Analyst, and Outfit Board Creator to generate personalised outfit recommendations based on your uploaded photos. By the end, you’ll have a complete multi-agent system that blends computer vision, intelligent coordination, and creative design for real-world fashion use.

Language

  • English

Topic

  • Artificial Intelligence

Skills You Will Learn

  • Generative AI, Autogen, Python, AI Agent, Artificial Intelligence, Computer Vision

Offered By

  • IBMSkillsNetwork

Estimated Effort

  • 50 minutes

Platform

  • SkillsNetwork

Last Update

  • November 12, 2025
About this Guided Project
Choosing the perfect outfit can often feel overwhelming—but not anymore. AutoGen Wardrobe Wizard is a multi-agent AI system designed to help you effortlessly plan stylish looks tailored to your wardrobe, personal style, and the occasion.

The process begins with Meta's Llama vision model, which analyses your uploaded photo and extracts clothing items to build a digital wardrobe—laying the groundwork for personalised recommendations.
Powered by Microsoft’s AutoGen framework, the system brings together a team of specialised AI agents that function like your own virtual styling team:
  • Color Analyst picks colors that complement your skin tone
  • Style Planner recommends outfit types based on your preferences and the occasion
  • Silhouette Analyst suggests flattering cuts and designs
  • Outfit Board Creator assembles everything into a cohesive final look
To complete the experience, OpenAI’s DALL·E generates a photorealistic outfit board, presenting your styled ensemble in a magazine-inspired flat lay.

By the end of this project, you'll have created a smart fashion assistant that combines visual recognition, collaborative AI, and creative design. It's a fun, real-world example of how multi-agent systems can solve everyday problems—with intelligence and style.

A Look at the Project Ahead

After completing this guided project, you will be able to do:
  • Understand AutoGen’s multi-agent architecture – Learn how to define and coordinate specialized agents to simulate real-world fashion consulting workflows.
  • Build intelligent fashion agents – Create agents with defined roles such as color analysis, style planning, and style advising.
  • Orchestrate collaborative outfit generation – Combine individual agent insights to produce a cohesive final outfit recommendation.
  • Learn to build and run agent workflows with AutoGen – Use Python and AutoGen to define agents, manage communication, and control task execution.
  • Generate visual outputs with DALL·E – Transform final outfit descriptions into AI-generated fashion boards using prompt-based image generation.
  • Deliver personalized styling experiences – Generate tailored fashion suggestions based on user profile inputs like skin tone, occasion, and preferences.

What You'll Need

Technical Requirements: A basic understanding of Python programming. Familiarity with AI agents or large language models (LLMs) is helpful but not mandatory.
Browser Setup: A modern web browser to access the AutoGen tools, follow the guided project environment, and run your code seamlessly.

Instructors

Jigisha Barbhaya

Data Scientist

I am a Data scientist at IBM and Lead instructor at Skills network. I love to learn and educate. I have completed my MSc(Computer Application) specialisation in Data science from Symbiosis University.

Read more

Contributors

Wojciech "Victor" Fulmyk

Data Scientist at IBM

Wojciech "Victor" Fulmyk is a Data Scientist and AI Engineer on IBM’s Skills Network team, where he focuses on helping learners build expertise in data science, artificial intelligence, and machine learning. He is also a Kaggle competition expert, currently ranked in the top 3% globally among competition participants. An economist by training, he applies his knowledge of statistics and econometrics to bring a distinctive perspective to AI and ML—one that considers both technical depth and broader socioeconomic implications.

Read more

Joseph Santarcangelo

Senior Data Scientist at IBM

Joseph has a Ph.D. in Electrical Engineering, his research focused on using machine learning, signal processing, and computer vision to determine how videos impact human cognition. Joseph has been working for IBM since he completed his PhD.

Read more