Nodes/ComfyUI/Nano Banana 2
ComfyUI Node Runs on cloud

Nano Banana 2

Generate or edit images synchronously via Google Vertex API.

By Comfy-Org·Created 4 years ago·Updated 20 days ago· 121,575
Nano Banana 2
    • IMAGE
    • STRING
    • thought_image
    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
    Categorypartner/image/Gemini

    Inputs (7)

    NameTypeDefaultDescription
    promptSTRINGText prompt describing the image to generate or the edits to apply. Include any constraints, styles, or details the model should follow.
    modelCOMBO2 options: [object Object], [object Object]
    seedINT420–18446744073709550000When 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.
    response_modalitiesCOMBO2 options: IMAGE, IMAGE+TEXT
    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.
    temperatureoptFLOAT1.000–2Controls randomness in generation. Lower is more focused/deterministic.
    top_poptFLOAT0.950–1Nucleus sampling threshold. Lower is more focused, higher more diverse.

    Outputs (3)

    NameTypeDescription
    IMAGEIMAGE
    STRINGSTRING
    thought_imageIMAGEFirst image from the model's thinking process. Only available with thinking_level HIGH and IMAGE+TEXT modality.