ComfyUI Node

Kimi K2.6

A ComfyUI node in Runware/Text/moonshotai with 22 inputs and 1 output.

By Runware·Created 2 years ago·Updated about a month ago· 140
Kimi K2.6
  • messages
  • images
  • text
seed0
numberResults1
includeUsagefalse
settings.frequencyPenalty0.00
settings.maxTokensfalse
settings.maxTokens_value1
settings.minP0.00
settings.presencePenalty0.00
settings.promptCacheKey
settings.repetitionPenalty1.00
settings.systemPrompt
settings.temperature1.00
settings.thinkingLevelnone
toolChoicefalse
toolChoice.name
toolChoice.type(default)
settings.topK0
settings.topP1.00
outputFormatTEXT
advanced_json
CategoryRunware/Text/moonshotai

Inputs (22)

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.frequencyPenaltyoptFLOAT0.00-2–2Penalizes 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_valueoptINT11–1000000Maximum 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.promptCacheKeyoptSTRINGCache key for reusing prompt cache across requests. Requests sharing the same key reuse cached prompt processing.
settings.repetitionPenaltyoptFLOAT1.000–5Penalizes 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.temperatureoptFLOAT1.000–2Controls randomness in generation. Lower values produce more deterministic outputs, higher values increase variation and creativity.
settings.thinkingLeveloptCOMBOnoneControls the depth of internal reasoning the model performs before generating a response.
toolChoiceoptBOOLEANfalseEnable to set toolChoice. Off uses the model's default.
toolChoice.nameoptSTRINGName of the specific tool the model must call. Required when type is `tool`.
toolChoice.typeoptCOMBO(default)Strategy the model uses to decide when and which tools to call.
settings.topKoptINT00–999Top-K sampling parameter that limits the number of highest-probability tokens considered at each step.
settings.topPoptFLOAT1.000–1Nucleus 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: settings.stopSequences, jsonSchema, tools

Outputs (1)

NameTypeDescription
textSTRING