Tools

Classic open-source OCR engine and CLI that reads text from images and outputs plain text, hOCR, searchable PDF or TSV. Supports 100+ languages; install the language data for each language you need.

Lightweight OCR built on PaddleOCR models converted to ONNX, recognizing Chinese and English by default on CPU alone. The rapidocr CLI reads text from screenshots, photos and scanned page images. Needs Python; downloads models on first run, then works offline. Convert PDFs to images first.

Detects shot changes in video and splits long footage into scenes, exporting cut lists and per-scene thumbnails, useful for shot analysis, organizing footage and finding edit points. Runs locally; needs Python 3.10+, plus FFmpeg or mkvmerge for splitting.

Runs open image models like FLUX, Qwen Image and Z-Image locally on a Mac: text-to-image, reference-based edits, inpainting and upscaling, all on-device. Needs Apple Silicon and uv; the first run downloads models and is slow. Check each model's license before commercial use.

Local image processing MCP: crop, resize, rotate, add text and watermarks, blur, remove backgrounds, detect objects and extract text with OCR, with no images uploaded anywhere; handy for photos, scans and course visuals. Needs Python 3.10 and pipx; first install downloads detection models.

Lets agents upload, download and list files in Tencent Cloud Object Storage (COS), and use Cloud Infinite for image processing, QR code recognition, document-to-PDF conversion, video frame capture and natural-language search. Maintained by Tencent Cloud; needs a SecretId and SecretKey.