ComfyUI Node
GLM-OCR Run
A ComfyUI node in GLM-OCR with 5 inputs and 1 output.
GLM-OCR Run
- glm_ocr_model
- image
- text
◄task_prompt▾►
◄max_new_tokens2048►
◄custom_prompt►
CategoryGLM-OCR
Inputs (5)
| Name | Type | Default | Description |
|---|---|---|---|
| glm_ocr_model | GLM_OCR_MODEL | — | |
| image | IMAGE | — | |
| task_prompt | COMBO | 4 options: Text Recognition:, Formula Recognition:, Table Recognition:, Describe the image. | |
| max_new_tokens | INT | 204864–8192 | — |
| custom_promptopt | STRING | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |