Week №6 Report #
Links #
Specify here all the necessary links to your website, application installer, final demo, etc.
- Deployment: https://outfitpredict.ru/
- API Docs: https://outfitpredict.ru/api/docs#/
- Design: [CAPST] Outfit Predict: Design Screenshots
- Demo: demo_outfit_predict_16_07_2025
Final deliverables #
Project overview #
Problem: Imagine you have a lot of clothes, but cannot compose a suitable outfit from these.
Solution: We created a website, where you can upload your clothes, and it will create an outfit from your clothes for you.
Target Audience: Anyone who care about their look
Features #
- Landing Page: Here you can observe a short explanations of our project, some examples, and about page
- Signup & Login: Here you can register, and log in into your profile
- Upload images: You can upload images of your clothes from your wardrobe into your profile. Here they will be visible
- Generate outfits: You can generate suitable outfits from your clothes.
Tech stack #
- Frontend: React, Tailwind CSS
- Backend: FastAPI, MinIO, PostgreSQL, Qdrant, Alembic
- DevOps: Docker, Nginx, Docker-compose
- ML: Ultralytics, Transformers, fine-tuned YOLOv11, DINO v2, SAM, FashionCLIP
Setup instructions #
Look from Repository Setup section to Running the Application section:
https://github.com/IU-Capstone-Project-2025/Outfit_predict/blob/main/README.md
Presentation draft #
outfit_predict_presentation.pdf
Weekly commitments #
Individual contribution of each participant #
Victor Mazanov: Conducted Customer Development interview (
link) and add functionality of searching similar cloth on the internet by the description of the thing from outfit (
link)
Bulat Sharipov: Managed team work, distributed tasks, backend development, wrote report, created presentation
Danil Fathutdinov: Created ML class for determining the outfit class
Dinar Yakupov: Updated frontend pages, fixed bugs and introduced optimizations
Remal Gareev: Improved CI & CD. Fixed bugs and introduced optimizations in the backend.
Artyom Grishin: Performed backend development and product design (
link)
Plan for Next Week #
- Implement last features, such as choosing only subset of clothes to perform outfits
- Introduce style filtration to resulting outfits
- Introduce randomization to outfit search, or daily outfits
- Final polishing and presentation repetition
Confirmation of the code’s operability
We confirm that the code in the main branch:
- In working condition.
- Run via docker-compose (or another alternative described in the README.md).