GeminiNanoBanana2 - ComfyUI Built-in Node Documentation - ComfyUI

The GeminiNanoBanana2 node generates or edits images using Google’s Vertex AI Gemini model. It sends a text prompt, along with optional reference images or files, to the API and returns the generated image and any accompanying text. This node is marked as deprecated.

Inputs

Parameter	Description	Data Type	Required	Range
`prompt`	Text prompt describing the image to generate or the edits to apply. Include any constraints, styles, or details the model should follow. Cannot be empty. (default: empty)	STRING	Yes	N/A
`model`	The specific Gemini model to use for image generation.	COMBO	Yes	”Nano Banana 2 (Gemini 3.1 Flash Image)“
`seed`	When the seed is fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn’t guaranteed. Also, changing the model or parameter settings, such as the temperature, can cause variations in the response even when you use the same seed value. By default, a random seed value is used. (default: 42)	INT	Yes	0 to 18446744073709551615
`aspect_ratio`	If set to ‘auto’, matches your input image’s aspect ratio; if no image is provided, a 16:9 square is usually generated. (default: “auto”)	COMBO	Yes	”auto" "1:1" "2:3" "3:2" "3:4" "4:3" "4:5" "5:4" "9:16" "16:9" "21:9”
`resolution`	Target output resolution. For 2K/4K the native Gemini upscaler is used.	COMBO	Yes	”1K" "2K" "4K”
`response_modalities`	Determines the type of content the model returns: “IMAGE” returns only an image, “IMAGE+TEXT” also returns text. (advanced)	COMBO	Yes	”IMAGE" "IMAGE+TEXT”
`thinking_level`	Controls the depth of the model’s reasoning process.	COMBO	Yes	”MINIMAL" "HIGH”
`images`	Optional reference image(s). To include multiple images, use the Batch Images node (up to 14).	IMAGE	No	1 to 14 images
`files`	Optional file(s) to use as context for the model. Accepts inputs from the Gemini Generate Content Input Files node.	CUSTOM	No	N/A
`system_prompt`	Foundational instructions that dictate an AI’s behavior. (default: a preset prompt that instructs the model to always produce an image) (advanced)	STRING	No	N/A

Note: The images input supports a maximum of 14 images. If more are provided, the node will raise an error. The prompt input must not be empty or whitespace-only.

Outputs

Output Name	Description	Data Type
`image`	The primary image generated or edited by the model.	IMAGE
`string`	Any text content returned by the model.	STRING
`thought_image`	First image from the model’s thinking process. Only available with thinking_level HIGH and IMAGE+TEXT modality.	IMAGE

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): d781c92f04d420985f8a5a593eb5f28f1f7b2af13abd11f2a7f6f285edcd9900