https://github.com/skalskip/fashion-assistant

Our idea is to combine the power of computer vision model and LLMs. We use YOLO, CLIP and DINOv2 to extract high-level features from images. We pass the prompt, along with the extracted features, to LLM, allowing for advanced image dataset queries.
https://github.com/skalskip/fashion-assistant

computer-vision llm natural-language-processing openai openai-api yolo

Last synced: 13 days ago
JSON representation

Our idea is to combine the power of computer vision model and LLMs. We use YOLO, CLIP and DINOv2 to extract high-level features from images. We pass the prompt, along with the extracted features, to LLM, allowing for advanced image dataset queries.

• Host: GitHub
• URL: https://github.com/skalskip/fashion-assistant
• Owner: SkalskiP
• License: mit
• Created: 2023-05-29T13:52:33.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2023-05-30T21:52:39.000Z (over 1 year ago)
• Last Synced: 2024-10-04T12:49:08.441Z (about 1 month ago)
• Topics: computer-vision, llm, natural-language-processing, openai, openai-api, yolo
• Language: Jupyter Notebook
• Homepage:
• Size: 8.62 MB
• Stars: 98
• Watchers: 8
• Forks: 7
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
[![Github Stars](https://img.shields.io/badge/stars-nominate-brightgreen?logo=github)](https://stars.github.com/nominate/) 

[![Roboflow Dataset](https://app.roboflow.com/images/download-dataset-badge.svg)](https://universe.roboflow.com/roboflow-jvuqo/fashion-assistant-segmentation)

AI fashion assistant




    



## 👋 hello

Our idea is to combine the power of computer vision model and LLMs. We use YOLO, CLIP and DINOv2 to extract high-level features from images. Then we use natural language as an interface for the user. We pass the prompt, along with the extracted features, to LLM, allowing for advanced image dataset queries.

![fashion-assistant-diagram](https://github.com/SkalskiP/fashion-assistant/assets/26109316/2b52802a-ce55-4a60-9a7e-421463e6a9e9)

## 🎯 goals

Keep in mind that the project is still under 🚧 construction. We will successively publish updates and new features. Follow me on [Twitter](https://twitter.com/skalskip92) to stay up to date.

- [ ] Help me compose my outfit based on clothes from my closet.

- [ ] Rate my outfit.

- [ ] Help me search online for clothes that fit my style or for a special occasion.

## 🖼️ image dataset

You have a project idea and would like to use our data? No problem! Our data, just like [codebase](https://github.com/SkalskiP/fashion-assistant/blob/master/LICENSE) is open-source. Take a peek at our Roboflow [project](https://universe.roboflow.com/roboflow-jvuqo/fashion-assistant-segmentation) to access images and annotations.

## 🦸 contribution

Do you want to help me?

- Let GitHub know we're doing something cool here! - Leave a ⭐!

- Contribute to our open-source [dataset](https://universe.roboflow.com/roboflow-jvuqo/fashion-assistant-segmentation).

- Help us build advanced computer vision and natural language processing features.