Artifacts

Converts an uploaded PDF into Markdown text.

Try several OCR models on Arabic documents and images.

Runs Chandra, Nanonets, olmOCR and Dots OCR models on a page image to extract text.

Lightweight OCR demo based on ONNX models that reads text from images.

Classic Tesseract OCR: upload an image and get the recognized text.

Reads Japanese text from an image, including manga-style text.

Extracts text from an image in many languages.

Parses digital and photographed documents into markdown.

Detect text blocks, tables, figures and other layout regions on document page images.

Parse digital and photographed documents into Markdown.

Try several small OCR vision-language models on the same image.

NVIDIA's OCR model extracting text from images.

Scene-text recognition using the PARSeq model.

Reads a single line of text from a cropped photo using TrOCR.

Recognizes text and structure in documents with FireRed-OCR.

Runs DeepSeek-OCR 2 on document images.

Detects and reads text in images using OnnxTR.

PaddleOCR v6 text detection and recognition running on ONNX Runtime CPU.

Reads text from an image and translates it.

Convert documents to Markdown or JSON with metadata using Docling.

Extracts Persian text from images.

Interactive demo of the DeepSeek-OCR model for reading text from images.

Convert PDFs and other documents to Markdown using the Docling library.

Chat with documents or websites using a small Gemma 3 1B model.