
Vision2U
vision2u.app
Open-source platform for modular, visual image-processing workflows with 200+ functions, OCR, object detection and an AI assistant.
Show more
Vision2U is an open-source platform for assembling image processing as a visual workflow. Python and React form the base, and an optional AI assistant helps with building. The site’s motto: “Complex image processing. Clear, visual workflows.”
- OCR with PaddleOCR (CPU) and object detection with Ultralytics YOLO (.pt models)
- Read and generate barcodes and QR codes, blob analysis
- Camera (OpenCV) and video as sources
- Portable .v2u projects


