Nodes/nbpOpenNode-ComfyUI/NBP Gemini Image 2
ComfyUI Node

NBP Gemini Image 2

Generate or edit images with Google Gemini image models via the ComfyUI Cloud API. Auth is handled automatically through your ComfyUI account.

By SorenWeile·Created 4 months ago·Updated 4 months ago· 0
NBP Gemini Image 2
  • images
  • IMAGE
  • STRING
prompt
modelgemini-3-pro-image-preview
seed42
aspect_ratioauto
resolution1K
temperature1.00
top_p0.95
top_k40
response_modalitiesIMAGE
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.
Categoryapi node/image/Gemini

Inputs (11)

NameTypeDefaultDescription
promptSTRINGDescribe the image you want to generate or the edits to apply.
modelCOMBOgemini-3-pro-image-previewWhich Gemini image model to use.
seedINT420–2147483647Fixed seed makes the model try to reproduce the same result. Determinism is best-effort — temperature and model changes still vary output.
aspect_ratioCOMBOauto'auto' matches the input image aspect ratio; if no image is provided a square is generated.
resolutionCOMBO1KOutput resolution. 2K/4K uses the Gemini native upscaler.
temperatureFLOAT1.000–2Controls randomness. Lower values (e.g. 0.2) produce more predictable results; higher values (e.g. 1.8) produce more varied, creative output.
top_pFLOAT0.950–1Nucleus sampling threshold. The model considers only the tokens whose cumulative probability reaches this value. Lower = more focused.
top_kINT401–100Limits the pool of tokens the model samples from at each step. Lower values make output more deterministic.
response_modalitiesCOMBOIMAGE'IMAGE' for image-only output; 'IMAGE+TEXT' also returns the model's reasoning.
imagesoptIMAGEOptional reference image(s). Use Batch Images for multiple (up to 14).
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.System-level instructions that shape the model's behavior.

Outputs (2)

NameTypeDescription
IMAGEIMAGEGenerated image(s).
STRINGSTRINGAny text the model returned alongside the image.