ComfyUI Node

Dia 1.6B

A ComfyUI node in Runware/Audio/runware with 11 inputs and 1 output.

By Runware·Created 2 years ago·Updated about a month ago· 140
Dia 1.6B
  • speech
  • audioSettings
  • audio
negativePrompt
seed0
CFGScale10.00
numberResults1
settings.temperature1.20
settings.topP0.95
ttlfalse
ttl_value60
outputFormatMP3
CategoryRunware/Audio/runware

Inputs (11)

NameTypeDefaultDescription
speechRUNWARE_SPEECH
audioSettingsoptRUNWARE_AUDIOSETTINGS
negativePromptoptSTRINGPrompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).
seedoptINT00–2147483647Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.
CFGScaleoptFLOAT10.001–30Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt.
numberResultsoptINT11–4Number of results to generate. Each result uses a different seed, producing variations of the same parameters.
settings.temperatureoptFLOAT1.200–5Controls overall confidence in outputs. Higher values produce more creative results with more artifacts. Lower values are more consistent with fewer outputs.
settings.topPoptFLOAT0.950–1Nucleus sampling parameter that controls diversity by limiting the probability mass. Lower values make outputs more focused, higher values increase diversity.
ttloptBOOLEANfalseEnable to set ttl. Off uses the model's default.
ttl_valueoptINT60Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.
outputFormatoptCOMBOMP3File format for the generated audio.

Outputs (1)

NameTypeDescription
audioAUDIO