Nano Banana (Google Gemini Image)

api node/image/Gemini

GeminiImageNode

Edit images synchronously via Google API.

Inputs

Name	Type	Status	Constraints	Default
`prompt`?	`STRING`	required	-	`""`
`model`?	`COMBO`	required	-	`"gemini-2.5-flash-image"`
`seed`?	`INT`	required	min: 0, max: 1.84e+19	`42`
`images`?	IMAGE	optional	-	`-`
`files`?	GEMINI_INPUT_FILES	optional	-	`-`
`aspect_ratio`?	`COMBO`	optional	-	`"auto"`
`response_modalities`?	`COMBO`	optional	-	`-`
`system_prompt`?	`STRING`	optional	-	`"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."`

Index	Name	Type	Is List	Connection Reference
`0`	`IMAGE`	IMAGE	No	`["{node_id}", 0]`
`1`	`STRING`	STRING	No	`["{node_id}", 1]`

How to connect to these outputs

To connect another node's input to an output from this node, use the connection reference format:

["node_id", output_index]

Where node_id is the ID of this GeminiImageNode node in your workflow, and output_index is the index from the table above.

If this node has ID "5" in your workflow:

Package: comfyui-api-nodes

Was this page helpful?