ComfyUI Node

Gemma 4 31B

A ComfyUI node in Runware/Text/google with 21 inputs and 1 output.

By Runware·Created 2 years ago·Updated about a month ago· 140
Gemma 4 31B
  • messages
  • images
  • text
seed0
numberResults1
includeUsagefalse
settings.frequencyPenalty0.00
settings.maxTokensfalse
settings.maxTokens_value1
settings.minP0.00
settings.presencePenalty0.00
settings.repetitionPenalty1.00
settings.systemPrompt
settings.temperaturefalse
settings.temperature_value0.00
settings.thinkingLevelhigh
settings.topKfalse
settings.topK_value1
settings.topPfalse
settings.topP_value0.00
outputFormatTEXT
advanced_json
CategoryRunware/Text/google

Inputs (21)

NameTypeDefaultDescription
messagesRUNWARE_MESSAGES
imagesoptIMAGE
seedoptINT00–9223372036854776000Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.
numberResultsoptINT11–4Number of results to generate. Each result uses a different seed, producing variations of the same parameters.
includeUsageoptBOOLEANfalseInclude token usage statistics in the response.
settings.frequencyPenaltyoptFLOAT0.000–2Penalizes tokens based on their frequency in the output so far. A value of 0.0 disables the penalty.
settings.maxTokensoptBOOLEANfalseEnable to set settings.maxTokens. Off uses the model's default.
settings.maxTokens_valueoptINT1Maximum number of tokens to generate in the response.
settings.minPoptFLOAT0.000–1Minimum probability threshold. Tokens with probability below this value are excluded from sampling.
settings.presencePenaltyoptFLOAT0.00-2–2Encourages the model to introduce new topics. A value of 0.0 disables the penalty.
settings.repetitionPenaltyoptFLOAT1.000–2Penalizes tokens that have already appeared in the output. A value of 1.0 disables the penalty.
settings.systemPromptoptSTRINGSystem-level instruction that guides the model's behavior and output style across the entire generation.
settings.temperatureoptBOOLEANfalseEnable to set settings.temperature. Off uses the model's default.
settings.temperature_valueoptFLOAT0.000–2Controls randomness in generation. Lower values produce more deterministic outputs, higher values increase variation and creativity.
settings.thinkingLeveloptCOMBOhighControls the depth of internal reasoning the model performs before generating a response.
settings.topKoptBOOLEANfalseEnable to set settings.topK. Off uses the model's default.
settings.topK_valueoptINT11–100Top-K sampling parameter that limits the number of highest-probability tokens considered at each step.
settings.topPoptBOOLEANfalseEnable to set settings.topP. Off uses the model's default.
settings.topP_valueoptFLOAT0.000–1Nucleus sampling parameter that controls diversity by limiting the probability mass. Lower values make outputs more focused, higher values increase diversity.
outputFormatoptCOMBOTEXTOutput format for the generated text.
advanced_jsonoptSTRINGOptional JSON merged into the request. For: inputs.videos, settings.stopSequences

Outputs (1)

NameTypeDescription
textSTRING