Somnusochi/VLM-AutoYOLO
Somnusochi/VLM-AutoYOLO has 278 GitHub stars and 42 forks. Star changes are not measured yet. Last checked 2026-11-14 04:21 UTC. Last push 2026-09-22.
What you can do
- 🤖 VLM auto-labeling: Open-vocabulary object detection with LocateAnything-3B
- 🎯 SAM2 / SAM3 segmentation: Bbox → pixel-precise mask with SAM 2.1 or SAM3 text-driven detection+segmentation in one pass, BBox/Mask toggle on canvas
- 🎥 Video annotation: Intelligent keyframe extraction (scene / motion / interval), SSIM dedup
- ✏️ Manual refinement: Canvas draw mode, NMS filtering, hide/show individual boxes
Measured star growth
- in 24h
- Collecting history
- in 7 days
- Collecting history
- in 15 days
- Collecting history
- in 1 month
- Collecting history
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
About
AI Auto Annotation & YOLO Training Pipeline, End-to-end object detection auto-labeling and YOLO training platform. VLM-powered annotation with NVIDIA LocateAnything-3B, manual refinement, one-click YOLO training, video keyframe extraction, and model validation. Supports image and video.
Machine Learningdocs/guide/en/README.md
OriginalUser Guide
Welcome to VLM-AutoYOLO! This guide will help you get started and make the most of this end-to-end object detection auto-labeling and training platform.
Guide Contents
- Getting Started - Complete workflow from installation to your first detection
- Annotation Best Practices - Tips and tricks for VLM pre-labeling and manual refinement
- Training Parameter Tuning - YOLO training parameter selection and dataset preparation guide
System Requirements
| Resource | Minimum Configuration |
|---|---|
| NVIDIA GPU | 12GB VRAM (for VLM and YOLO training acceleration) |
| macOS (Apple Silicon) | 24GB Unified Memory (MPS) |
| Memory (CPU Mode) | 16GB System RAM (32GB recommended) |
| Storage | 50GB available space |
| OS | macOS 12+ / Ubuntu 20.04+ / Windows 10+ |
| Python | 3.12+ |
| Node.js | 22+ |
| PostgreSQL | 16+ |
| ffmpeg | Any version (for video keyframe extraction) |
Core Workflow
Upload Images/Video → VLM / SAM3 Auto-Labeling → Manual Refinement → Export Dataset → Train YOLO → Validate Model
- Choose Model: VLM+SAM2 (detection + segmentation) or SAM3 (text-driven end-to-end)
- Auto-Labeling: VLM or SAM3 generates bounding boxes and masks automatically
- Data Export: Export YOLO format annotation files (single image and batch supported)
- Model Training: One-click training for YOLOv5/v8/v11/v26 with real-time progress monitoring
- Model Validation: Validate training results on test images/videos
Quick Navigation
- First time user? → Getting Started
- Want to improve labeling quality? → Annotation Best Practices
- Training results not ideal? → Training Parameter Tuning
Getting Help
- Check the API Documentation for detailed backend interface information
- Having issues? Please submit feedback on GitHub Issues
Explore related projects
tensorflow/tensorflow
An Open Source Machine Learning Framework for Everyone
201,590 starshuggingface/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
168,957 starsAUTOMATIC1111/stable-diffusion-webui
Stable Diffusion web UI
165,307 starsComfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
146,728 stars