PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text
•
Updated
•
15.8k
•
1.55k
PaddleOCR-VL
Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
-
-
PaddleOCR-VL Online Demo
📈232Extract text, tables, formulas, and charts from images
-
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper • 2510.14528 • Published • 116 -
PaddlePaddle/PP-DocLayoutV2
Object Detection • Updated • 19k • 23 -
PaddlePaddle/PP-DocLayoutV2_safetensors
Updated • 32 • 2