This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass
What I Built
A virtual try-on web app. You upload a photo of yourself and a photo of a garment, and it shows you how the outfit might look on you. The results are image, size or fit suggestion
How it gets people off the screen: Shopping and outfit-picking usually mean an hour of scrolling, ordering multiple sizes and returning half of them. With a try-on, the decision takes a minute, and then you close the laptop and go out, whether that’s the market, campus or a trail.
Who it’s for: college students, online shoppers who want fewer returns and less screen time.
Demo
https://pic-wardrobe-ai.lovable.app
Code
https://github.com/min7-kushagrita/maomao-min
How I Built It
My first version was vibe coded: the interface worked and looked right, but there was no real AI doing the try-on. The rebuild was about replacing that with an actual open model.
Open-weight AI at the core:
Gemma (Google’s open-weight model):The model itself analyses the garment or the photo, suggesting an outfit, writing the fit description.]
The rest of the stack (not the open-source AI part):
Top comments (0)