PaddleOCR-VL - a PaddlePaddle Collection

PaddlePaddle 's Collections

PaddleOCR-VL-1.5

PaddleOCR-VL

updated Dec 16, 2025

Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

PaddlePaddle/PaddleOCR-VL

Image-Text-to-Text • 1.0B • Updated about 13 hours ago • 15.9k • 1.54k
Running

Featured

230

PaddleOCR-VL Online Demo

📈

230

Convert documents and images into structured text and markdown
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

Paper • 2510.14528 • Published Oct 16, 2025 • 113