Nodes/ComfyUI-API-Toolkit/Gemini Image Generation (Nano Banana)
ComfyUI Node

Gemini Image Generation (Nano Banana)

A ComfyUI node in API Toolkit/Gemini/Image with 16 inputs and 1 output.

By IxMxAMAR·Created 5 months ago·Updated about a month ago· 1
Gemini Image Generation (Nano Banana)
  • ref_image_1
  • ref_image_2
  • ref_image_3
  • ref_image_4
  • image
api_key
modelgemini-3.1-flash-image-preview
custom_model
prompt
aspect_ratio16:9
image_size4K
system_instruction
thinking_levelNONE
temperature1.00
seed-1
candidate_count1
safety_settings_json
CategoryAPI Toolkit/Gemini/Image

Inputs (16)

NameTypeDefaultDescription
api_keySTRINGGemini API key. Leave blank to use GEMINI_API_KEY env var.
modelCOMBOgemini-3.1-flash-image-previewGemini image model. For Imagen models, use the dedicated Imagen Image Generation node instead.
custom_modelSTRINGOverride with a custom model ID.
promptSTRINGImage generation prompt. Use [Reference Image N] to refer to inputs.
aspect_ratioCOMBO16:9Output image aspect ratio.
image_sizeCOMBO4KOutput image resolution.
system_instructionoptSTRINGSystem instruction for the image generation model.
thinking_leveloptCOMBONONEHow much the model should reason before generating.
temperatureoptFLOAT1.000–2Controls randomness in generation.
seedoptINT-1-1–2147483647Random seed for reproducibility (-1 = random).
candidate_countoptINT11–4Number of image candidates to generate (returns first).
ref_image_1optIMAGEFirst reference image.
ref_image_2optIMAGESecond reference image.
ref_image_3optIMAGEThird reference image.
ref_image_4optIMAGEFourth reference image.
safety_settings_jsonoptSTRINGJSON safety settings from Safety Settings node.

Outputs (1)

NameTypeDescription
imageIMAGE