🏆 #2,081 overall#238 of 696 in OCR & Documents

opendatalab /MinerU-Diffusion

[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.

$ git clone https://github.com/opendatalab/MinerU-Diffusion.git
GitHub social preview for opendatalab/MinerU-Diffusion
Stars
624
624
This week
+1 ★
Forks
42
42
Language
Python
License
MIT
Created
Mar 13, 2026
0.7 years old
Last push
Jun 18, 2026

Stars, last 15 days

Oct 30, 2026 → Nov 16, 2026
★ 623▲ +1★ 624

Categories

GitHub topics

More in OCR & Documents

OCR & Documents

opendatalab/MinerU🔥 active

▲ +441 ★ this week

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

PythonOtherupdated Nov 16, 2026
GitHub ↗★ 83.7K⑂ 6.9K
OCR & Documents

bytedance/Dolphin

▲ +2 ★ this week

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

PythonOtherupdated Mar 25, 2026
GitHub ↗★ 9.1K⑂ 771
OCR & Documents

DocumindHQ/documind

▲ +1 ★ this week

Open-source platform for extracting structured data from documents using AI.

JavaScriptOtherupdated May 15, 2025
GitHub ↗★ 1.5K⑂ 61
OCR & Documents

pymupdf/PyMuPDF🔥 active

▲ +59 ★ this week

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

💎 Text Mining
PythonAGPL-3.0updated Nov 16, 2026
GitHub ↗★ 11.1K⑂ 842
OCR & Documents

RapidAI/RapidDoc🔥 active

A high-performance, open-source PDF data extraction tool. 一站式开源高性能数据提取工具,将复杂 PDF 文档转换为 Markdown 和 JSON 格式,使用onnx模型。

PythonApache-2.0updated Nov 16, 2026
GitHub ↗★ 239⑂ 44
OCR & Documents

AdemBoukhris457/Doctra

📄🔍 Parse, extract, and analyze documents with ease 📄🔍

Jupyter NotebookApache-2.0updated Nov 29, 2025
GitHub ↗★ 214⑂ 33

Data from GitHub · snapshot Nov 16, 2026