ComfyUI Node
PD: Nano Banana 2.1 (ComfyUI Key)
Generate or edit images synchronously via Google Vertex API.
PD: Nano Banana 2.1 (ComfyUI Key)
- IMAGE
- STRING
- thought_image
◄comfy_api_key►
◄prompt►
◄model▾►
◄seed42►
◄response_modalities▾►
◄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.►
◄temperature1.00►
◄top_p0.95►
CategoryPD_Tools/Image_Generation
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| comfy_api_key | STRING | Comfy.org API Key | |
| prompt | STRING | Text prompt describing the image to generate or the edits to apply. Include any constraints, styles, or details the model should follow. | |
| model | COMBO | 2 options: [object Object], [object Object] | |
| seed | INT | 420–18446744073709550000 | Matches the official node. The current Comfy.org endpoint does not receive seed; a fixed seed does not guarantee repeatable output. |
| response_modalities | COMBO | 2 options: IMAGE, IMAGE+TEXT | |
| 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. | Foundational instructions that dictate an AI's behavior. |
| temperatureopt | FLOAT | 1.000–2 | Controls randomness in generation. Lower is more focused/deterministic. Ignored by Nano Banana 2.1, matching the official endpoint. |
| top_popt | FLOAT | 0.950–1 | Nucleus sampling threshold. Lower is more focused, higher more diverse. Ignored by Nano Banana 2.1, matching the official endpoint. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| IMAGE | IMAGE | — |
| STRING | STRING | — |
| thought_image | IMAGE | First image from the model's thinking process. Only available with thinking_level HIGH and IMAGE+TEXT modality. |