VLM-AutoYOLO

AI Auto Annotation & YOLO Training Pipeline, End-to-end object detection auto-labeling and YOLO training platform. VLM-powered annotation with NVIDIA LocateAnyt

What is VLM-AutoYOLO?

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.

Overview of VLM-AutoYOLO

What it is

VLM-AutoYOLO is an end-to-end object detection auto-labeling and YOLO training platform. It uses a VLM (Vision Language Model) for automatic annotation, SAM2/SAM3 for mask refinement, and supports one-click YOLO training. The pipeline processes images or videos and outputs a YOLO model. It is GPU-accelerated on macOS MPS and Windows/Linux CUDA.

Key features

  • VLM auto-labeling: open-vocabulary object detection with NVIDIA LocateAnything-3B.
  • SAM2/SAM3 segmentation: bounding box to pixel-precise mask with SAM 2.1 or SAM3 text-driven detection+segmentation in one pass.
  • Video annotation: intelligent keyframe extraction (scene/motion/interval) with SSIM deduplication.
  • Manual refinement: canvas draw mode, NMS filtering, hide/show individual boxes.
  • Multi-format export/import: YOLO, YOLO-Seg, COCO JSON, Pascal VOC XML, CreateML JSON; chunked upload up to 10GB with resume support.
  • Training queue: sequential job processing with cancel support, one-click training (YOLOv8/v11/v26) with real-time SSE progress.
  • Model validation: batch image/video testing, MJPEG live stream, SSE video inference.

Use cases

This tool is designed for users who need to create custom object detection or segmentation datasets from images or videos, automatically annotate them using a VLM, refine annotations manually or with SAM, and train a YOLO model without writing code. It is suitable for researchers, engineers, and hobbyists working on computer vision projects.

Getting started

bashgit clone https://github.com/Somnusochi/VLM-AutoYOLO.gitcd VLM-AutoYOLOpython3 cli.py allFor Docker deployment, manual setup, and detailed instructions, see the repository README.

License and pricing

The license is AGPL-3.0. The project is open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/somnusochivlm-autoyolo.svg)](https://yunodb.com/tools/somnusochivlm-autoyolo?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/somnusochivlm-autoyolo?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/somnusochivlm-autoyolo.svg" alt="Featured on YunoDB" height="20"></a>