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.
The pipeline chains YOLO for garment detection, CLIP for semantic clothing attributes, and DINOv2 for fine-grained visual features—concatenating these embeddings as context for LLM inference to enable natural language queries over fashion image datasets. The project targets outfit composition and style-matching workflows, with an open-source annotated dataset available via Roboflow for training and evaluation.
118 stars. No commits in the last 6 months.
Stars
118
Forks
9
Language
Jupyter Notebook
License
MIT
Category
Last pushed
May 30, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/SkalskiP/fashion-assistant"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
beikeshop/beikeshop
Free and Open-Source, Easy-to-Use Laravel eCommerce Platform, Base on the Laravel . It supports...
ClicShopping/ClicShopping
ClicShopping AI(tm) is OpenSource and powerfull Solution AI e-commerce B2B / B2C / B2B-B2C ...
musicman3/eMarket
eMarket Online Store. It is a free online shop engine. Make the best online shop with us. Join...
KudoAI/amazongpt
đź›’ AI chat & product/category summaries in Amazon shopping, powered by the latest LLMs
yennhi95zz/e-commerce-chatbot-using-openai
Creating a chatbot for your e-commerce business is now easier than ever with OpenAI, bypassing...