ComfyUI Node
OCR / Text Extraction
A ComfyUI node in Unlimited OCR/Inference with 4 inputs and 3 outputs.
OCR / Text Extraction
- unlimited_ocr
- image
- config
- extracted_text
- annotated_image
- debug_text
◄promptdocument parsing.►
CategoryUnlimited OCR/Inference
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| unlimited_ocr | unlimited_ocr_model | — | |
| image | IMAGE | — | |
| prompt | STRING | document parsing. | — |
| configopt | unlimited_ocr_config | — |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| extracted_text | text | — |
| annotated_image | IMAGE | — |
| debug_text | text | — |