MinerU-Diffusion
opendatalab
[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.
623
Stars
40
Forks
16
Watchers
Python
Language
mit
License
100
SrcLog Score
Growth over time
4 data points · 2026-04-07 → 2026-07-19
Stars
Forks
Watchers
💬
How do you feel about this project?
Ask AI about MinerU-Diffusion
Question copied to clipboardWhat is the opendatalab/MinerU-Diffusion GitHub project? Description: "[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding. ". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.
Question is copied to clipboard — paste it after the AI opens.
How to clone MinerU-Diffusion
Clone via HTTPS
git clone https://github.com/opendatalab/MinerU-Diffusion.git
Clone via SSH
[email protected]:opendatalab/MinerU-Diffusion.git
Download ZIP
Download main.zipFound an issue?
Report bugs or request features on the MinerU-Diffusion issue tracker:
Open GitHub Issues