MinerU-Diffusion
by opendatalab (organization)
[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding. (description from the project’s GitHub page)
Repository facts
- Stars
- 620
- Forks
- 42
- Open issues and pull requests
- 9
- Primary language
- Python
- License
- MIT License (MIT)
- Owner
- opendatalab · Organization
- Created
- Mar 13, 2026
- Last push
- Jun 18, 2026
Topics
Add this badge to your README
Shows this repository’s rank in AI on GitHub and links back to this page. Ranks are by stars and change when the list is refreshed. The badge is not an endorsement or a rating. About the badges
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/github/opendatalab--mineru-diffusion/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/github/opendatalab--mineru-diffusion/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/github/opendatalab--mineru-diffusion.svg" alt="Ranked #8,329 in AI on GitHub" height="20"></a>
Related projects
Projects that share this one’s GitHub topics.
Rank 57: opendatalab/MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
81,973 starsPythonOther licenseLast push Oct 17, 2026
Rank 46: PaddlePaddle/PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
91,313 starsPythonApache-2.0Last push Sep 16, 2026
Rank 269: opendataloader-project/opendataloader-pdf
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
29,741 starsJavaApache-2.0Last push Oct 16, 2026
Rank 4,010: yobix-ai/extractous
Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.
1,783 starsRustApache-2.0Last push Dec 21, 2024
Rank 2,988: chrisryugj/kordoc
모두 파싱해버리겠다 — HWP·HWPX·PDF·Office 문서를 Markdown으로. 양식 자동 채우기와 신구대조를 갖춘 CLI·MCP 서버 | Convert Korean documents (HWP, HWPX, PDF, Office) to Markdown — CLI and MCP server with form fill…
2,573 starsTypeScriptMITLast push Oct 18, 2026
Rank 4,307: kotaro-kinoshita/yomitoku
YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.
1,634 starsPythonNo license file detectedLast push Oct 15, 2026