Models / PaddlePaddle / PP-DocLayoutV3 (SafeTensors)

PP-DocLayoutV3 (SafeTensors)

JSON →
vision

A document layout analysis model from PaddleOCR, detecting regions like text, table, and figure in documents.

imagevision
Specs
Context & limits
—
context window
—
max output
Lifecycle
Dates
released2024-06-01
Resources