Workflow Hub

Share your best AI workflow. We could show it to 2M+ people.

Every day, we feature the community's top-voted AI workflow in The Rundown newsletter.

New here? Say hi + tell us what you’re working on 👋

Whether you joined five minutes ago or you’ve been lurking for months, I want to meet you! Tell us who you are and one thing you’re trying to figure out with AI. I read and reply to every intro 💜 Comment below with: Who you are: your name, what you do, and where you’re based What you’re working on: one thing you’d love to automate, speed up, or figure out with AI Your favorite tool right now (bonus points if it’s one we haven’t heard of) Your LinkedIn, if you’d like to connect. Totally optional

Brooke Benson Question
12

Build an AI Wardrobe Stylist with ChatGPT and Lovable

I built the M(AI)VENS Closet Lab, an AI-powered wardrobe stylist that helps women create more outfits using clothes they already own. I’m the founder of M(AI)VENS, a community helping women build confidence with AI. The idea was inspired by a friend who completed a 30-day challenge to restyle pieces from her closet instead of buying new clothes. I wondered whether AI could take the idea further by helping people rediscover what they already own, style overlooked pieces, pack for a trip, and pull outfits together more easily in everyday life. I have no coding experience, so I used ChatGPT and Lovable to build the app. Step-by-step: 1. I described the experience I wanted in ChatGPT: users would upload photos of their clothes, organize them in a visual wardrobe, select one or more pieces they wanted to wear, and ask an AI stylist to create complete outfits using their own clothing. I asked ChatGPT to turn the idea into a detailed build prompt for Lovable. 2. I pasted the ChatGPT prompt into Lovable. It created a mobile-friendly app with user accounts, photo uploads, clothing categories, descriptive tags, a visual closet gallery, and a “Style Me” feature. 3. I photographed 16 pieces from my personal wardrobe, including tops, pants, dresses, jackets, and shoes. I uploaded and categorized each item so I could test the app with a varied but manageable wardrobe. 4. I selected a pair of hot pink wide-leg pants and clicked “Style Me.” When the feature returned an error, I described exactly what happened in a new Lovable prompt and asked it to fix the problem. Testing also revealed that users needed to edit items after uploading them, so I prompted Lovable to add that capability. 5. I refined the AI’s approach to creating complete outfits. The first version treated selected clothes as the entire outfit, but I wanted each selection to serve as an anchor. I used ChatGPT to write a more precise prompt instructing Lovable to search the user’s full closet for complementary pieces. For example, if someone selects pants, the app recommends a top, shoes, and an optional jacket for each ensemble. Whenever possible, it returns three complete outfit suggestions, each with an outfit name, occasion, pieces used, and styling note. 6. I selected the hot pink pants again. This time, the app generated three complete looks using my uploaded clothing: a matching pink suit, a casual outfit with loafers, and a layered look with a white blouse, heels, and a denim jacket. 7. I tested and published the result. The working prototype took approximately five or six prompts across two days, mainly because I reached Lovable’s daily free-credit limit. Now I have a working tool that I find highly valuable and useful.

Cheyenne Dominguez
  • ChatGPT
21