ComfyUI Node
NanoBanana - Vision OCR (lossless PNG)
A ComfyUI node in NanoBanana2/Image with 7 inputs and 1 output.
NanoBanana - Vision OCR (lossless PNG)
- image
- network
- text
◄api_key►
◄modelgemini-2.5-pro►
◄custom_model►
◄modeplain_text►
◄language_hint►
CategoryNanoBanana2/Image
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| api_key | STRING | — | |
| model | COMBO | gemini-2.5-pro | 35 options: gemini-pro-latest, gemini-flash-latest, gemini-flash-lite-latest, gemini-3-pro-preview, gemini-3-flash-preview, gemini-3.1-pro-preview, +29 |
| image | IMAGE | — | |
| custom_modelopt | STRING | — | |
| modeopt | COMBO | plain_text | Output format. structured_json returns {lines: [{text, bbox, confidence}, ...]}. |
| language_hintopt | STRING | Optional language hint (e.g. 'Japanese', 'Hindi'). | |
| networkopt | NB_NETWORK | Optional. Wire a NanoBanana - Network Route node here to route this request through that proxy (e.g. US egress). |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |