GeminiNode - ComfyUI Built-in Node Documentation

This node allows users to interact with Google’s Gemini AI models to generate text responses. You can provide multiple types of inputs including text, images, audio, video, and files as context for the model to generate more relevant and meaningful responses. The node handles all API communication and response parsing automatically. Note: This node is marked as deprecated in the source code.

Inputs

Parameter	Description	Data Type	Required	Range
`prompt`	Text inputs to the model, used to generate a response. You can include detailed instructions, questions, or context for the model. Default: empty string.	STRING	Yes	-
`model`	The Gemini model to use for generating responses. Default: gemini-3-1-pro.	COMBO	Yes	”gemini-2.5-pro" "gemini-2.5-flash" "gemini-3-pro-preview" "gemini-3-1-pro" "gemini-3-1-flash-lite”
`seed`	When 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
`images`	Optional image(s) to use as context for the model. To include multiple images, you can use the Batch Images node. Default: None.	IMAGE	No	-
`audio`	Optional audio to use as context for the model. Default: None.	AUDIO	No	-
`video`	Optional video to use as context for the model. Default: None.	VIDEO	No	-
`files`	Optional file(s) to use as context for the model. Accepts inputs from the Gemini Generate Content Input Files node. Default: None.	GEMINI_INPUT_FILES	No	-
`system_prompt`	Foundational instructions that dictate an AI’s behavior. Default: empty string. This is an advanced parameter.	STRING	No	-

All connected images are used as context. When more than 10 images are provided, the first 10 are uploaded as file references and the remaining images are sent inline to the API. The node uses the selected model name as given in the list; some entries are internally mapped to their current API model identifiers before the request is sent.

Outputs

Output Name	Description	Data Type
`STRING`	The text response generated by the Gemini model. If the model produces no text, the node returns “Empty response from Gemini model…”.	STRING

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): d1c53a5d80182085a36302867c8875df696adec6aaea9a9519a21bd6b9543d8f

​Inputs

​Outputs

Inputs

Outputs