FreeAIRepo
Vision & OCR

opendatalab/MinerU-Diffusion

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

Really freeMITPython
Open on GitHub Website
Stars
620
Forks
42
Open issues
8
Last push
4mo ago

About MinerU-Diffusion

MinerU-Diffusion is a free, open-source computer vision tool by opendatalab, written mainly in Python. [ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding. It has 620 GitHub stars and 42 forks, and was last updated 4mo ago. It's released under the MIT license, a standard open-source license.

License
MIT
Language
Python
Stars
620
Last update
4mo ago
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not required
Self-hostable
Not stated

Similar free tools

All Vision & OCR tools →

MinerU-Diffusion FAQ

Is MinerU-Diffusion free?

Yes. MinerU-Diffusion is open source and free to use. It's released under the MIT license, a standard open-source license.

Does MinerU-Diffusion run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does MinerU-Diffusion need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is MinerU-Diffusion still maintained?

It was last updated 4mo ago. Check recent issues on GitHub to judge how active it is.

What are alternatives to MinerU-Diffusion?

Similar free, open-source tools include PaddleOCR, Stirling-PDF, pdf-craft, gradio.

Related topics

ai4sciencediffusiondlmdocument-analysisextract-datalayout-analysislladaocr