YoloLabel is a free desktop GUI for drawing object bounding boxes on images used to train YOLO neural networks. It loads JPG or PNG files from a directory and creates boxes with a two-click method; users can also move, resize, copy, paste, undo, and redo annotations, then export them as YOLO TXT labels. For assisted labeling, it can run local inference with supported Ultralytics detection models exported to ONNX, including YOLOv5, YOLOv8, YOLO11, YOLO12, and YOLOv26. A loaded model can label the current image or process a dataset in batches. The app also connects to YoloLabel AI for cloud open-vocabulary detection using an API key and optional prompt; cloud batches contain up to 20 images per request. Prebuilt desktop downloads are listed for Windows x64, Linux x64, and macOS on Apple Silicon, and the project uses the MIT License. Building from source requires Qt 6; ONNX Runtime is optional unless local auto-labeling is wanted. The cloud service's free tier allows 100 images per month, has no SLA, and returns HTTP 402 for over-limit requests. The app warns that moving the horizontal image slider does not automatically save the last processed image.
Who it is for
YoloLabel suits people preparing image annotations for YOLO training who want manual box editing or assisted labeling. It offers local ONNX inference as well as an optional cloud detection service.
What is good
- Free desktop application with MIT-licensed repository
- Manual box editing includes undo and redo
- Can batch-label with a local ONNX model
- Downloads for Windows, Linux, and Apple Silicon
What to know first
- Cloud free tier allows 100 images monthly
- Cloud free tier has no SLA
- Slider movement does not save the last processed image
Verdict
YoloLabel combines manual bounding-box annotation with local and cloud-assisted labeling options. Keep its unsaved-slider warning and the cloud service's monthly quota in mind.
Compared on AI image annotation tools
- Free plan
- Yes
- Annotation types
- bounding boxes
- AI-assisted labeling
- Yes
- Review workflow
- Yes
- Export formats
- YOLO TXT
- Deployment
- self-hosted
