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.
☆100Updated last year
Related projects ⓘ
Alternatives and complementary repositories for fashion-assistant
- YOLOExplorer : Iterate on your YOLO / CV datasets using SQL, Vector semantic search, and more within seconds☆124Updated 2 weeks ago
- ☆27Updated 10 months ago
- Use Grounding DINO, Segment Anything, and GPT-4V to label images with segmentation masks for use in training smaller, fine-tuned models.☆65Updated 11 months ago
- Evaluate the performance of computer vision models and prompts for zero-shot models (Grounding DINO, CLIP, BLIP, DINOv2, ImageBind, model…☆34Updated last year
- EdgeSAM model for use with Autodistill.☆25Updated 5 months ago
- Run zero-shot prediction models on your data☆30Updated 4 months ago
- Simplify Your Visual Data Ops. Find and visualize issues with your computer vision datasets such as duplicates, anomalies, data leakage, …☆67Updated last year
- Convert yolo models to ONNX, TensorRT add NMSBatched.☆15Updated 7 months ago
- ☆13Updated 11 months ago
- Use Florence 2 to auto-label data for use in training fine-tuned object detection models.☆59Updated 3 months ago
- Flask-based web application designed to compare text and image embeddings using the CLIP model.☆22Updated 9 months ago
- ☆60Updated last year
- Eye exploration☆22Updated this week
- A curated list of papers that released datasets along with their work☆124Updated 3 weeks ago
- Using open-source LLM Llama2 by Meta on local CPU inference for document question-and-answer☆15Updated last year
- ☆29Updated last month
- FiftyOne Plugin for finding common image quality issues☆29Updated last month
- DETIC module for use with Autodistill.☆13Updated 11 months ago
- My journey during 10 weeks of building FiftyOne plugins☆19Updated last year
- Accurately locating each head's position in the crowd scenes is a crucial task in the field of crowd analysis. However, traditional densi…☆20Updated 8 months ago
- Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.☆92Updated 3 months ago
- The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained mode…☆10Updated 3 months ago
- ☆53Updated last year
- autoAnnoter its a tool to auto annotate data using a exisiting models☆43Updated 3 months ago
- GroundedSAM Base Model plugin for Autodistill☆45Updated 7 months ago
- GPT-4V(ision) module for use with Autodistill.☆25Updated 3 months ago
- Which model is the best at object detection? Which is best for small or large objects? We compare the results in a handy leaderboard.☆47Updated this week
- Everything you need to know about Transformers! 🤖☆127Updated last year
- Streamlit component for image annotation.☆82Updated 3 months ago
- The open source implementation of "NeVA: NeMo Vision and Language Assistant"☆18Updated last year