NAVER

Detect Text Regions (CRAFT)

Runs a CRAFT text-detection checkpoint over each Image and emits one Polygon per detected text region — raw region geometry for cropping or masking rather than extracted text strings.

Analyze Document Layout (Donut)

OCR-free document understanding with a Donut model: reads one document Image end-to-end and emits a downstream-resolved oneof t[String, [(String, String)]] — either the raw decoded sequence as text, or the structured parse flattened to dotted key/value pairs.

Classify Document (Donut)

Reads a whole page Image end-to-end with an OCR-free Donut encoder-decoder and decodes the document type directly, emitting a single Classification whose confidence is the mean per-token probability of the generated label.