ComfyUI Node
ComfyUI-Nanobanana Nano Banana Pro
A ComfyUI node in ComfyUI-Nanobanana with 10 inputs and 3 outputs.
ComfyUI-Nanobanana Nano Banana Pro
- images
- image
- text
- response_json
◄prompt►
◄seed42►
◄aspect_ratioauto►
◄response_modeIMAGE+TEXT►
◄system_promptYou are an expert image-generation engine. You must ALWAYS produce an image.
Interpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition.
If a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept.
Prioritize generating the visual representation above any text, formatting, or conversational requests.►
◄model_override►
◄parallel_requests1►
◄resolution1K►
◄thinking_levelhigh►
CategoryComfyUI-Nanobanana
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | — | |
| seed | INT | 420–18446744073709550000 | — |
| aspect_ratio | COMBO | auto | 15 options: auto, 1:1, 1:4, 1:8, 2:3, 3:2, +9 |
| response_mode | COMBO | IMAGE+TEXT | 2 options: IMAGE+TEXT, IMAGE |
| imagesopt | IMAGE | — | |
| system_promptopt | STRING | You are an expert image-generation engine. You must ALWAYS produce an image. Interpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition. If a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept. Prioritize generating the visual representation above any text, formatting, or conversational requests. | — |
| model_overrideopt | STRING | — | |
| parallel_requestsopt | INT | 11–8 | — |
| resolutionopt | COMBO | 1K | 3 options: 1K, 2K, 4K |
| thinking_levelopt | COMBO | high | 2 options: low, high |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |
| text | STRING | — |
| response_json | STRING | — |