Nodes/ComfyUI/Nano Banana (Google Gemini Image)
ComfyUI Node Runs on cloud

Nano Banana (Google Gemini Image)

Edit images synchronously via Google API.

By Comfy-Org·Created 4 years ago·Updated 16 days ago· 121,575
Nano Banana (Google Gemini Image)
  • images
  • files
  • IMAGE
  • STRING
◄prompt►
◄model▾►
◄seed42►
◄aspect_ratioauto►
◄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.►
Categorypartner/image/Gemini

Inputs (8)

NameTypeDefaultDescription
promptSTRINGText prompt for generation
modelCOMBOThe Gemini model to use for generating responses.
seedINT420–18446744073709550000When 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.
imagesoptIMAGEOptional image(s) to use as context for the model. To include multiple images, you can use the Batch Images node.
filesoptGEMINI_INPUT_FILESOptional file(s) to use as context for the model. Accepts inputs from the Gemini Generate Content Input Files node.
aspect_ratiooptCOMBOautoDefaults to matching the output image size to that of your input image, or otherwise generates 1:1 squares.
response_modalitiesoptCOMBOChoose 'IMAGE' for image-only output, or 'IMAGE+TEXT' to return both the generated image and a text response.
system_promptoptSTRINGYou 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.

Outputs (2)

NameTypeDescription
IMAGEIMAGE—
STRINGSTRING—