Nodes/ERPK Collection/Gemini Text Generation
ComfyUI Node

Gemini Text Generation

Generate text using Gemini models.

By eRepublik-Labs·Created 10 months ago·Updated about a month ago· 0
Gemini Text Generation
  • client
  • response
prompt
seed-1
modelgemini-3.5-flash
temperature0.70
max_tokens8192
top_p0.95
top_k40
stop_sequences
response_mime_typedefault
response_schema
thinking_levelnone
CategoryERPK/Gemini

Inputs (12)

NameTypeDefaultDescription
promptSTRINGText prompt for Gemini
seedINT-1-1–2147483647Seed for reproducible outputs. Randomizes by default.
clientoptGEMINI_API_CLIENTGemini API client from Gemini API Config node (optional if API key is configured in Settings)
modeloptCOMBOgemini-3.5-flashGemini model to use for generation
temperatureoptFLOAT0.700–2Creativity level (0.0=focused, 2.0=very creative)
max_tokensoptINT8192256–65536Maximum length of response
top_poptFLOAT0.950–1Nucleus sampling - cumulative probability threshold (0.0=disabled)
top_koptINT40-1–100Top-k sampling - limit token selection (0=disabled)
stop_sequencesoptSTRINGStop generation at these sequences (one per line, leave empty to disable)
response_mime_typeoptCOMBOdefaultOutput format (use application/json for JSON mode)
response_schemaoptSTRINGJSON schema for structured output (only used with application/json, leave empty for free-form JSON)
thinking_leveloptCOMBOnoneReasoning depth. Works on Gemini 2.5 and 3.x; the node translates to thinking_budget (2.5) or thinking_level enum (3.x) automatically.

Outputs (1)

NameTypeDescription
responseSTRING