Nodes/ComfyUI-NanoBanana2/NanoBanana - Vision Analysis
ComfyUI Node

NanoBanana - Vision Analysis

A ComfyUI node in NanoBanana2/Image with 12 inputs and 1 output.

By IxMxAMAR·Created 5 months ago·Updated 2 months ago· 4
NanoBanana - Vision Analysis
  • ref_image_1
  • ref_image_2
  • ref_image_3
  • ref_image_4
  • network
  • text
api_key
modelgemini-3.1-flash-lite-preview
custom_model
promptDescribe this image.
system_instruction
temperature0.10
losslessfalse
CategoryNanoBanana2/Image

Inputs (12)

NameTypeDefaultDescription
api_keySTRINGNanoBanana - API key. Leave blank to use GEMINI_API_KEY env var.
modelCOMBOgemini-3.1-flash-lite-previewNanoBanana - model for vision analysis.
custom_modelSTRINGOverride with a custom model ID.
promptSTRINGDescribe this image.What to ask about the image(s).
system_instructionoptSTRINGSystem instruction to guide analysis.
temperatureoptFLOAT0.100–2Controls randomness. Lower = more focused analysis.
losslessoptBOOLEANfalseEncode images as lossless PNG instead of JPEG. Use for OCR, small-text recognition, or fine-grained classification where JPEG artifacts degrade accuracy. Higher bandwidth.
ref_image_1optIMAGEFirst image to analyze.
ref_image_2optIMAGESecond image to analyze.
ref_image_3optIMAGEThird image to analyze.
ref_image_4optIMAGEFourth image to analyze.
networkoptNB_NETWORKOptional. Wire a NanoBanana - Network Route node here to route this request through that proxy (e.g. US egress).

Outputs (1)

NameTypeDescription
textSTRING